CN112862714A - Image processing method and device - Google Patents
Image processing method and device Download PDFInfo
- Publication number
- CN112862714A CN112862714A CN202110147559.7A CN202110147559A CN112862714A CN 112862714 A CN112862714 A CN 112862714A CN 202110147559 A CN202110147559 A CN 202110147559A CN 112862714 A CN112862714 A CN 112862714A
- Authority
- CN
- China
- Prior art keywords
- image
- area
- shadow
- preset
- communication
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 27
- 238000004891 communication Methods 0.000 claims abstract description 65
- 238000012549 training Methods 0.000 claims abstract description 52
- 238000012937 correction Methods 0.000 claims abstract description 39
- 238000012545 processing Methods 0.000 claims description 78
- 238000000034 method Methods 0.000 claims description 51
- 238000001914 filtration Methods 0.000 claims description 24
- 238000005286 illumination Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 15
- 238000011084 recovery Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 238000007600 charging Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The application discloses an image processing method and device, and belongs to the technical field of communication. The image processing method comprises the following steps: inputting the first image to a preset model under the condition that a shadow region exists in the first image; carrying out color correction on the shadow area by using a preset model to obtain a second image; the training stopping condition of the preset model is that the color loss values of the predicted shadowless image of the training sample image and the label shadowless image of the training sample image meet the preset condition. By the image processing method, the shadow area in the image can be removed, the information integrity and the definition of the image are improved, the identifiability of the image is improved, and the user experience is improved.
Description
Technical Field
The present application belongs to the field of communication technologies, and in particular, to an image processing method and apparatus.
Background
An image is used as an information carrier which can contain various elements such as characters, pictures, tables and the like, and can be used for recording and transmitting information.
However, once the image is shaded, the information integrity and the definition of the image may be affected, so that the image is less recognizable, and the user experience may be poor. Therefore, there is a need for an image processing method capable of removing shadow areas in an image to improve the information integrity and definition of the image and improve the recognizability of the image.
Disclosure of Invention
An object of the embodiments of the present application is to provide an image processing method and apparatus, which can remove a shadow region in an image, improve information integrity and definition of the image, and improve image recognizability.
In order to solve the technical problem, the present application is implemented as follows:
in a first aspect, an embodiment of the present application provides an image processing method, which may include:
inputting a first image to a preset model under the condition that a shadow region exists in the first image; carrying out color correction on the shadow area by using the preset model to obtain a second image;
the training stopping condition of the preset model is that the color loss values of the predicted shadow-free image of the training sample image and the label shadow-free image of the training sample image meet the preset condition.
In a second aspect, an embodiment of the present application provides an apparatus for image processing, which may include:
the device comprises a first input module, a second input module and a display module, wherein the first input module is used for inputting a first image to a preset model under the condition that a shadow area exists in the first image;
the correction module is used for carrying out color correction on the shadow area by utilizing the preset model to obtain a second image;
the training stopping condition of the preset model is that the color loss values of the predicted shadow-free image of the training sample image and the label shadow-free image of the training sample image meet the preset condition.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instructions stored on the memory and executable on the processor, and when executed by the processor, the program or instructions implement the steps of the method according to the first aspect.
In a fourth aspect, embodiments of the present application provide a readable storage medium, on which a program or instructions are stored, which when executed by a processor implement the steps of the method according to the first aspect.
In a fifth aspect, an embodiment of the present application provides a chip, where the chip includes a processor and a communication interface, where the communication interface is coupled to the processor, and the processor is configured to execute a program or instructions to implement the method according to the first aspect.
In the embodiment of the present application, when a shadow region exists in a first image, the first image is input to a preset model, and color correction is performed on the shadow region by using the preset model. The training stopping condition of the preset model is that the predicted shadowless image of the training sample image and the color loss value of the label shadowless image of the training sample image meet the preset condition. Therefore, on the one hand, the color correction can be carried out on the shadow area in the first image by utilizing the preset model, the illumination compensation and the brightness recovery of the shadow area in the first image can be realized by carrying out the color correction, and the shadow area in the first image is removed, so that the color of the second image is more actually fitted, the information integrity and the definition of the second image are improved, the identifiability of the second image is improved, and the user experience can be effectively improved. On the other hand, the color of the first image is corrected by using the preset model, the shadow area in the first image is removed to obtain the second image, and the second image is more attractive, so that the user experience can be further improved.
Drawings
Fig. 1 is a schematic flowchart of an image processing method according to an embodiment of the present application;
FIG. 2 is a schematic flowchart of another image processing method provided in the embodiment of the present application;
fig. 3 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present application;
fig. 4 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms first, second and the like in the description and in the claims of the present application are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application are capable of operation in sequences other than those illustrated or described herein. In addition, "and/or" in the specification and claims means at least one of connected objects, a character "/" generally means that a preceding and succeeding related objects are in an "or" relationship.
Based on the background art, in the prior art, due to a shadow area in an image, the information integrity and the definition of the image are low, and the recognizability of the image is low, so that the user experience is poor.
Specifically, the image may generally include elements such as characters, pictures, tables, etc., which are used for recording and transmitting information, etc., and are common in the learning, working, and living processes. The image generally needs to guarantee higher information integrity and definition, and once a shadow area exists in the image, the image color of the shadow area in the image may be distorted, so that the information integrity and definition of the shadow area in the image are lower, and the legibility of the image is poorer, and the shadow area in the image also affects the beauty of the image, and the user experience is poorer.
In the prior art, shadow areas in an image are usually removed by using an image processing technology. However, the image processing technology usually only performs brightness recovery on an image, and cannot correct the color of a shadow region, and the brightness recovery usually only performs the function of fading the shadow region, and cannot correct the color of the shadow region, and the image after the brightness recovery may also have color distortion, which causes mottled image color. Therefore, the image with recovered brightness still has the technical problems of low information integrity and definition, low image recognizability and unattractive image.
Based on the above findings, embodiments of the present application provide an image processing method and an image processing apparatus, which may input a first image to a preset model when a shadow region exists in the first image, and perform color correction on the shadow region by using the preset model. The training stopping condition of the preset model is that the predicted shadowless image of the training sample image and the color loss value of the label shadowless image of the training sample image meet the preset condition. Therefore, on the one hand, the color correction can be carried out on the shadow area in the first image by utilizing the preset model, the illumination compensation and the brightness recovery of the shadow area in the first image can be realized by carrying out the color correction, and the shadow area in the first image is removed, so that the color of the second image is more actually fitted, the information integrity and the definition of the second image are improved, the identifiability of the second image is improved, and the user experience can be effectively improved. On the other hand, the color of the first image is corrected by using the preset model, the shadow area in the first image is removed to obtain the second image, and the second image is more attractive, so that the user experience can be further improved.
The image processing method provided by the embodiment of the present application is described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios thereof.
Fig. 1 shows a flowchart of an image processing method provided in an embodiment of the present application, where an execution subject of the method may be an electronic device. As shown in fig. 1, the image processing method may include the steps of:
s110, the electronic equipment inputs the first image to a preset model under the condition that the shadow area exists in the first image.
The first image may be any image including a shadow area.
The preset model may be a pre-trained model for removing a shadow region in the first image.
When the electronic device processes the first image with the shadow area, a pre-trained preset model can be obtained. And inputting the first image into a preset model so as to remove the shadow area in the first image by using the preset model.
And S120, the electronic equipment performs color correction on the shadow area by using a preset model to obtain a second image.
The second image may be an image output after the preset model performs color correction on the shadow area of the first image.
The training stopping condition of the preset model can be a predicted shadowless image of the training sample image, the color loss value of the predicted shadowless image and a label shadowless image of the training sample image meets the preset condition, and the color loss value can be the distance between the predicted shadowless image and the label shadowless image in the HSV color model.
The prediction shadow-free image can be an image which is input into a preset model for a training sample image, processed by the preset model and output by the preset model; the label unshaded image may be an unshaded real image corresponding to the training sample image. For example, taking a cover of a certain book as an example, an image of a shadow area obtained by shooting the cover is a training sample image, an image output after color correction is performed on the training sample image by a preset model after the training sample image is input to the preset model is a predicted shadow-free image, and an image of a shadow-free area obtained by shooting the cover is a label shadow-free image, that is, a real image.
After the electronic device inputs the first image into the preset model, the preset model can be used for performing color correction processing on the first image according to a logic trained in advance by the preset model, illumination compensation and brightness recovery of a shadow region in the first image are achieved through color correction, removal of the shadow region in the first image is achieved, and the second image is obtained.
It should be noted that the preset model may be a model that trains a deep convolution generation type countermeasure network using a training sample including a pair of an image with a shadow region (i.e., the training sample image) and an image without a shadow region (i.e., the label non-shadow image), and the learned training sample image may be processed to obtain a predicted non-shadow image whose color loss value and the label non-shadow image satisfy a preset condition. Compared with the existing shadow removing method based on the image processing technology, the method and the device can learn to obtain the preset model with scene universality by utilizing the guidance of paired data and the function fitting capacity of the depth convolution generation type countermeasure network, and the prediction model can be suitable for the shadow removing processing of various image types including black and white images, color images and the like of shadow areas.
In addition, in order to correct the color of the shadow area, in the preset model training stage, the embodiment of the present invention may also randomly change the color of the shadow area of the input training sample image with the shadow area, so as to construct a training sample image with color shadow. When the label shadow-free image is used for supervising the training of the preset model, the color loss value can be added and improved besides the conventional reconstruction loss value, the perception loss value and the countermeasure loss value, and the predicted shadow-free image output by the preset model can be driven to approach the label shadow-free image, so that the color correction of a shadow area is realized. The color loss value may be a predicted shadowless image corresponding to the training sample image, a distance between the label shadowless image corresponding to the training sample image and the HSV color model, such as a cosine distance, and a calculation formula of the color loss value may be as shown in formula (1).
color_loss＝1–cos((Ho,So,Vo),(Hgt,Sgt,Vgt)) (1)
Wherein color _ loss represents a color loss value, Ho represents a hue of the predicted non-shadow image, So represents a saturation of the non-shadow image, Vo represents a brightness of the non-shadow image, Hgt represents a hue of the label non-shadow image, Sgt represents a saturation of the label non-shadow image, and Vgt represents a brightness of the label non-shadow image.
It is understood that the training sample image and the label shadow-free image in the training sample may be the captured real photographed image or may be artificially synthesized.
In the embodiment of the present application, when a shadow region exists in a first image, the first image is input to a preset model, and color correction is performed on the shadow region by using the preset model. The training stopping condition of the preset model is that the predicted shadowless image of the training sample image and the color loss value of the label shadowless image of the training sample image meet the preset condition. Therefore, on the one hand, the color correction can be carried out on the shadow area in the first image by utilizing the preset model, the illumination compensation and the brightness recovery of the shadow area in the first image can be realized by carrying out the color correction, and the shadow area in the first image is removed, so that the color of the second image is more actually fitted, the information integrity and the definition of the second image are improved, the identifiability of the second image is improved, and the user experience can be effectively improved. On the other hand, the color of the first image is corrected by using the preset model, the shadow area in the first image is removed to obtain the second image, and the second image is more attractive, so that the user experience can be further improved.
In some embodiments, before performing color correction on the first image, the electronic device may first determine whether a shadow region exists in the first image, and accordingly, before the step S110, the following steps may be further performed:
the electronic equipment calculates the proportion of the shadow area in the first image;
the electronic device determines that a shadow area exists in the first image when the occupancy is greater than or equal to a preset occupancy.
Considering that when the area of the shadow area in the first image is small, the information integrity and the definition of the first image are not generally affected, and the recognizability of the first image is affected, the electronic device may calculate the total area of the shadow area in the first image and the full image area of the first image before inputting the first image in which the shadow area exists to the preset model. Then, the ratio of the shadow area in the first image, that is, the ratio of the total area of the shadow area in the first image in the total image area of the first image, is calculated, and the specific calculation mode can be seen in formula (2):
shadow_ratio＝sum_area/whole_area (2)
wherein, shadow _ ratio represents the ratio of the total area of the shadow region in the full map area of the first image, sum _ area represents the total area of the shadow region in the first image, and whole _ area represents the full map area of the first image.
After calculating the ratio of the shadow area in the first image, a preset ratio may be obtained, for example, the preset ratio may be 0.01, 0.02, and the specific data may be set according to actual needs. And comparing the ratio of the shadow area in the first image with the preset ratio to determine whether the ratio of the shadow area in the first image is greater than or equal to the preset ratio. When the ratio of the shadow area in the first image is greater than or equal to the preset ratio, it may be considered that the shadow area existing in the first image may affect the information integrity and the definition of the first image and affect the legibility of the first image, and at this time, it may be determined that the shadow area exists in the first image. After determining that the shadow region exists in the first image, the processes of the above steps S110, S120 may be performed.
Therefore, only when the ratio of the shadow area in the first image is greater than the preset ratio, that is, the shadow area in the first image may affect the information integrity and the definition of the first image and affect the legibility of the first image, the first image is subjected to image processing, so that some unnecessary image processing processes can be avoided, thereby effectively reducing power consumption and improving image processing efficiency.
In some embodiments, the electronic device may calculate a ratio of the shadow area in the first image based on a third image capable of reflecting the illumination information of the first image, and accordingly, a specific implementation manner of calculating the ratio of the shadow area in the first image in the above steps may be as follows:
the electronic equipment performs Gaussian filtering processing on the first image to obtain a third image;
the electronic equipment carries out binarization processing on the third image to obtain a fourth image;
the electronic equipment analyzes the connected components of the fourth image and calculates the area of the connected components in the fourth image;
the electronic device calculates a ratio of the area of the connected component in the full-map area of the first image.
The third image may be obtained by performing gaussian filtering on the first image, and may be an image that reflects illumination information of the first image.
In view of utilizing the illumination information of the first image, it is more convenient to calculate the occupation ratio of the shadow area in the first image, and therefore, when calculating the occupation ratio of the shadow area in the first image, the electronic device may perform gaussian filtering processing on the first image first, for example, may perform large-scale gaussian filtering processing on the first image to weaken local texture details in the first image, and only retain the low-frequency component in the first image, that is, the illumination information of the first image.
After the electronic device performs the gaussian filtering process on the first image to obtain a third image, the electronic device may perform a binarization process on the third image, so that the third image exhibits an obvious black-and-white effect, and a fourth image is obtained. For example, a pixel with a gray value of the third image being less than or equal to a preset pixel threshold (for example, 50) may be classified as a candidate shadow pixel, a value of the candidate shadow pixel is marked as 1, a pixel with a gray value being greater than the preset pixel threshold is classified as a non-shadow pixel, and a value of the non-shadow pixel is marked as 0, so as to obtain a binarized image, that is, a fourth image.
After the electronic device performs binarization processing on the third image to obtain a fourth image, the electronic device may perform connected component analysis on the fourth image to obtain all connected components in the fourth image, that is, all shadow areas in the fourth image. Then, the area of the connected component in the fourth image, that is, the total area of all the connected components in the fourth image is calculated, and the full-image area of the first image can be calculated. After the area of the connected component in the fourth image is calculated, the occupation ratio of the area of the connected component in the fourth image in the full-map area of the first image may be calculated.
In this way, by performing binarization processing on the third image reflecting the illumination information of the first image to obtain the fourth image, the amount of data in the fourth image can be greatly reduced. In this way, the ratio of the area of the connected component in the fourth image to the full-map area of the first image is calculated based on the fourth image with a small data amount, so that the data calculation amount can be effectively reduced, and the image processing efficiency can be further improved.
In some embodiments, the gaussian filtering processing is performed on the first image in the above steps, and a specific implementation manner of obtaining the third image may be as follows:
the electronic equipment performs scaling processing on the first image to obtain a fifth image;
and the electronic equipment performs Gaussian filtering processing on the fifth image to obtain a third image.
The fifth image may be an image with an area smaller than or equal to the first preset area, for example, the area may be smaller than or equal to 1000 pixels × 1000 pixels, that is, the fifth image is an image with a side length smaller than or equal to 1000 pixels.
Considering that the first image is typically large in area, image processing of the large image may result in large power and power consumption. Therefore, before the electronic device performs the gaussian filtering on the first image to obtain the third image, the electronic device may perform scaling processing on the first image to scale the first image to a fifth image with an area smaller than or equal to the first preset area. And performing Gaussian filtering processing on the fifth image to obtain a third image. In this way, scaling the first image to the fifth image smaller than or equal to the first preset area can reduce power and power consumption, and thus can further improve image processing efficiency.
In some embodiments, in the above step, the electronic device performs connected component analysis on the fourth image, and a specific implementation manner of calculating the area of the connected component in the fourth image may be as follows:
the electronic equipment analyzes the connected components of the fourth image to obtain M connected regions in the fourth image;
the electronic equipment removes a first communication area in the M communication areas;
the electronic equipment calculates the total area of a second communication area in the M communication areas;
in this case, the calculating a ratio of the area of the connected component to the entire area of the first image may include:
the electronic device calculates a ratio of a total area of the second connected regions in a full-map area of the first image.
Wherein M may be a positive integer. The first connected region may be a connected region having an area smaller than a second preset area, that is, a shadow region having an area smaller than the second preset area, where the second preset area may be a minimum value of an area of the connected region that needs to be removed, and if the second preset area may be 625 pixels, the connected region smaller than the second preset area may be considered as a region that does not affect the information integrity and the definition of the image and does not affect the legibility of the image.
The second communication region may be a communication region other than the first communication region among the M communication regions, that is, a communication region having an area larger than a second predetermined area.
When the electronic device performs connected component analysis on the fourth image and calculates the area of the connected component in the fourth image, the electronic device may perform connected component analysis on the fourth image to obtain M connected regions in the fourth image, that is, each connected region in the fourth image. The area of each of the M communication areas is calculated respectively, a second preset area is obtained, the area of each of the M communication areas is compared with the second preset area, and the communication areas with the areas smaller than the second preset area in the M communication areas, namely the first communication areas, are determined.
After the electronic device determines the first communication areas with the areas smaller than the second preset area in the M communication areas, the first communication areas can be removed from the M communication areas of the fourth image to obtain the second communication areas in the M communication areas, and the second communication areas are actually the communication areas with the areas larger than the second preset area, so that the information integrity and the definition of the image can be influenced, and the shadow areas of the image with the identifiability can be influenced. And respectively calculating the area of each second communication area in the M communication areas, calculating the total area of the second communication areas in the M communication areas, and calculating the occupation ratio of the total area of the second communication areas in the M communication areas in the whole area of the first image.
In this way, in the fourth image obtained after the binarization processing of the third image, the first communication area with the area smaller than the second preset area is removed, that is, the shadow area in the fourth image, which does not affect the information integrity and the definition of the image and the legibility of the image, is removed. Thus, unnecessary image processing of the first connected region can be reduced, so that power consumption can be further reduced, and image processing efficiency can be improved.
In some embodiments, the electronic device may further save the second image when the definition of the second image meets the requirement, and accordingly, after the step S120, the following steps may be further performed:
the electronic device calculates a sharpness value of the second image;
and the electronic equipment saves the second image under the condition that the definition value of the second image is greater than or equal to the preset definition value.
The electronic device may further calculate a sharpness value of the second image after performing color correction on the first image by using the preset model to obtain the second image, for example, the sharpness value of the second image may be calculated by a sharpness evaluation method of a spatial domain gradient field, a sharpness evaluation method based on transform domain frequency analysis, or the like. After calculating the definition value of the second image, a preset definition value can be acquired, and the definition value of the second image is compared with the preset definition value to judge whether the definition value of the second image is greater than or equal to the preset definition value. The second image may be saved if the sharpness value of the second image is greater than or equal to a preset sharpness value. Otherwise, if the definition value of the second image is smaller than the preset definition value, the image processing step can be continuously returned, and the image processing is carried out on the first image again.
Therefore, on one hand, the second image is a shadow-free area, and the information integrity and the definition value of the second image are higher than those of the first image, so that the user can view and use the image with higher identification degree, and the user experience can be further improved. On the other hand, on the basis of the non-shadow area of the second image, only the second image with the definition value larger than or equal to the preset definition value is stored for the user to check and use, so that the definition value of the second image checked and used by the user is higher, the recognizability is higher, and the user experience can be further improved.
In some embodiments, the image processing method may be further applied to a photographing process, in which the first image may be a photographing preview image, and accordingly, before the step S110, the following steps may be further performed:
and the electronic equipment inputs the shooting preview image into a preset model under the condition that the shooting program is in the target shooting mode and the shadow area exists in the shooting preview image.
At this time, after the step S120, the following steps may be further performed:
and the electronic equipment takes a picture of the second image and stores the second image.
When the image processing method is applied to the photographing process, the electronic device may first open the photographing program and start a target photographing mode of the photographing program, such as a document photographing mode, a shadow photographing mode, and the like. In the case where the photographing program is in the target photographing mode, it can be determined whether there is a shadow area in the photographing preview image. And under the condition that the shooting program is in the target shooting mode and shadow areas exist in the shooting preview image, inputting the shooting preview image into a preset model, and performing color correction on the shooting preview image by using the preset model to obtain a second image. After the second image is obtained, the second image can be photographed, if a photographing button can be triggered to photograph, the second image is stored, if the second image can be stored in an album, a user can directly view and use the image which does not contain the shadow area, has clear and visible information and is harmonious and attractive in color by opening the album application.
It will be appreciated that after the second image is obtained, the sharpness value of the second image may also be calculated; and under the condition that the definition value of the second image is greater than or equal to the preset definition value, saving the second image, wherein the implementation principle and the technical effect of the method are similar to those of the embodiment of the method, and for the sake of brevity, the description is omitted here. And the second image can be displayed on the shooting preview interface when the second image is obtained, so that the user can visually see the second image on the shooting preview interface.
It should be noted that, when the shooting program is in the target shooting mode, but the shooting preview image does not have a shadow region, the definition value of the shooting preview image may be calculated, and when the definition value of the shooting preview image is greater than or equal to the preset definition value, the shooting preview image is shot, and the shooting preview image is saved. And under the condition that the definition value of a second image obtained by performing color correction on the photographed preview image by using a preset model is smaller than a preset definition value, acquiring a next image, determining whether a shadow area exists in the image, and executing the image processing process.
Therefore, in the photographing process, the color correction of the photographing preview image with the shadow area can be realized, the shadow area in the photographing preview image is removed, so that the user can directly obtain the image without shadow, high in information integrity and high in definition in the photographing process, the recognizability of the photographed image is improved, and the user experience can be further improved.
Fig. 2 illustrates, by taking an example that the image processing method provided in the embodiment of the present application is applied to a photographing process, yet another image processing method provided in the embodiment of the present application, as shown in fig. 2, the method may include the following steps:
s210, the electronic equipment starts a target photographing mode of the photographing program.
S220, the electronic equipment determines whether a shadow area exists in the shooting preview image.
When determining whether the shadow area exists in the photo preview image, the electronic device may perform gaussian filtering on the photo preview image to obtain a third image, where the third image is used to reflect illumination information of the photo preview image. And performing binarization processing on the third image to obtain a fourth image, performing connected component analysis on the fourth image, and calculating the area of connected components in the fourth image. Then, the ratio of the area of the connected component in the full-image area of the photo preview image is calculated, and in the case that the ratio of the area of the connected component in the full-image area of the photo preview image is greater than or equal to the preset ratio, it is determined that a shadow region exists in the photo preview image, and step S230 is executed. Otherwise, step S240 is directly performed without performing step S230.
And S230, inputting the photographing preview image into a preset model by the electronic equipment, and performing color correction on the shadow area by using the preset model to obtain a second image.
S240, the electronic device calculates a sharpness value of the second image.
S250, the electronic equipment determines whether the definition value of the second image is greater than or equal to a preset definition value.
The electronic device performs step S260 if the sharpness value of the second image is greater than or equal to the preset sharpness value. Otherwise, step S270 is executed.
And S260, the electronic equipment photographs the second image and stores the second image.
S270, the electronic equipment acquires the next image.
The implementation principle and technical effect of the image processing method provided by the embodiment of the present application are similar to those of the above method embodiments, and are not described herein again for the sake of brevity.
It should be noted that, in the image processing method provided in the embodiment of the present application, the execution subject may be an image processing apparatus, or a control module in the image processing apparatus for executing the loaded image processing method. In the embodiment of the present application, an image processing apparatus executes a loaded image processing method as an example, and the image processing method provided in the embodiment of the present application is described.
Fig. 3 shows a schematic structural diagram of an image processing apparatus according to an embodiment of the present application. As shown in fig. 3, the image processing apparatus 300 may include:
a first input module 310, configured to input the first image to a preset model in a case where a shadow region exists in the first image;
the correcting module 320 may be configured to perform color correction on the shadow region by using a preset model to obtain a second image;
the training stopping condition of the preset model is that the color loss values of the predicted shadowless image of the training sample image and the label shadowless image of the training sample image meet the preset condition.
In the embodiment of the present application, when a shadow region exists in a first image, the first image is input to a preset model, and color correction is performed on the shadow region by using the preset model. The training stopping condition of the preset model is that the predicted shadowless image of the training sample image and the color loss value of the label shadowless image of the training sample image meet the preset condition. Therefore, on the one hand, the color correction can be carried out on the shadow area in the first image by utilizing the preset model, the illumination compensation and the brightness recovery of the shadow area in the first image can be realized by carrying out the color correction, and the shadow area in the first image is removed, so that the color of the second image is more actually fitted, the information integrity and the definition of the second image are improved, the identifiability of the second image is improved, and the user experience can be effectively improved. On the other hand, the color of the first image is corrected by using the preset model, the shadow area in the first image is removed to obtain the second image, and the second image is more attractive, so that the user experience can be further improved.
In some embodiments, the image processing apparatus 300 may further include:
the first calculation module can be used for calculating the proportion of a shadow area in the first image;
the determining module may be configured to determine that a shadow region exists in the first image when the occupancy is greater than or equal to a preset occupancy.
Therefore, only when the ratio of the shadow area in the first image is greater than the preset ratio, that is, the shadow area in the first image may affect the information integrity and the definition of the first image and affect the legibility of the first image, the first image is subjected to image processing, so that some unnecessary image processing processes can be avoided, thereby effectively reducing power consumption and improving image processing efficiency.
In some embodiments, the first calculation module may include:
the filtering unit can be used for carrying out Gaussian filtering processing on the first image to obtain a third image; the third image is used for reflecting the illumination information of the first image;
a binarization unit, configured to perform binarization processing on the third image to obtain a fourth image;
the first calculation unit can be used for analyzing the connected components of the fourth image and calculating the area of the connected components in the fourth image;
the second calculation unit may be configured to calculate a ratio of an area of the connected component in a whole map area of the first image.
In this way, by performing binarization processing on the third image reflecting the illumination information of the first image to obtain the fourth image, the amount of data in the fourth image can be greatly reduced. In this way, the ratio of the area of the connected component in the fourth image to the full-map area of the first image is calculated based on the fourth image with a small data amount, so that the data calculation amount can be effectively reduced, and the image processing efficiency can be further improved.
In some embodiments, the filtering unit may include:
the scaling subunit is configured to scale the first image to obtain a fifth image; the area of the fifth image is smaller than or equal to the first preset area;
and the filtering subunit may be configured to perform gaussian filtering processing on the fifth image to obtain a third image.
In this way, scaling the first image to the fifth image smaller than or equal to the first preset area can reduce power and power consumption, and thus can further improve image processing efficiency.
In some embodiments, the first computing unit comprises:
the analysis component can be used for performing connected component analysis on the fourth image to obtain M connected regions in the fourth image; m is a positive integer;
a removal component that can be configured to remove a first connected region of the M connected regions; the first communication area is a communication area with an area smaller than a second preset area;
a computing component operable to compute a total area of a second one of the M connected regions; the second communication area is a communication area except the first communication area in the M communication areas;
the second computing unit may specifically be configured to:
the ratio of the total area of the second connected regions in the full-map area of the first image is calculated.
In this way, in the fourth image obtained after the binarization processing of the third image, the first communication area with the area smaller than the second preset area is removed, that is, the shadow area in the fourth image, which does not affect the information integrity and the definition of the image and the legibility of the image, is removed. Thus, unnecessary image processing of the first connected region can be reduced, so that power consumption can be further reduced, and image processing efficiency can be improved.
In some embodiments, the image processing apparatus 300 may further include:
a second calculation module, which can be used for calculating the definition value of the second image;
and the saving module can be used for saving the second image under the condition that the definition value of the second image is greater than or equal to the preset definition value.
Therefore, on one hand, the second image is a shadow-free area, and the information integrity and the definition value of the second image are higher than those of the first image, so that the user can view and use the image with higher identification degree, and the user experience can be further improved. On the other hand, on the basis of the non-shadow area of the second image, only the second image with the definition value larger than or equal to the preset definition value is stored for the user to view and use, so that the definition and the recognizability of the second image viewed and used by the user are higher, and the user experience can be further improved.
In some embodiments, the first image is a photographed preview image;
the image processing apparatus may further include:
the second input module can be used for inputting the shooting preview image into the preset model under the condition that the shooting program is in the target shooting mode and a shadow region exists in the shooting preview image;
a photographing module operable to:
and photographing the second image and storing the second image.
Therefore, in the photographing process, the color correction of the photographing preview image with the shadow area can be realized, the shadow area in the photographing preview image is removed, so that the user can directly obtain the image without shadow, high in information integrity and high in definition in the photographing process, the recognizability of the photographed image is improved, and the user experience can be further improved.
The image processing apparatus in the embodiment of the present application may be an apparatus, or may be a component, an integrated circuit, or a chip in a terminal. The device can be mobile electronic equipment or non-mobile electronic equipment. By way of example, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palm top computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), and the like, and the non-mobile electronic device may be a server, a Network Attached Storage (NAS), a Personal Computer (PC), a Television (TV), a teller machine or a self-service machine, and the like, and the embodiments of the present application are not particularly limited.
The image processing apparatus in the embodiment of the present application may be an apparatus having an operating system. The operating system may be an Android operating system (Android), an iOS operating system, or other possible operating systems, which is not specifically limited in the embodiments of the present application.
The image processing apparatus provided in the embodiment of the present application can implement each process implemented by the image processing apparatus in the method embodiments of fig. 1 to fig. 2, and is not described herein again to avoid repetition.
Optionally, an electronic device is further provided in this embodiment of the present application, and includes a processor 410, a memory 409, and a program or an instruction stored in the memory 409 and executable on the processor 410, where the program or the instruction is executed by the processor 410 to implement each process of the above-mentioned embodiment of the image processing method, and can achieve the same technical effect, and in order to avoid repetition, details are not described here again.
It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and the non-mobile electronic devices described above.
Fig. 4 is a schematic diagram of a hardware structure of an electronic device implementing an embodiment of the present application.
The electronic device 400 includes, but is not limited to: radio unit 401, network module 402, audio output unit 403, input unit 404, sensor 405, display unit 406, user input unit 407, interface unit 408, memory 409, and processor 410.
Those skilled in the art will appreciate that the electronic device 400 may further include a power source (e.g., a battery) for supplying power to various components, and the power source may be logically connected to the processor 410 through a power management system, so as to implement functions of managing charging, discharging, and power consumption through the power management system. The electronic device structure shown in fig. 4 does not constitute a limitation of the electronic device, and the electronic device may include more or less components than those shown, or combine some components, or arrange different components, and thus, the description is omitted here.
Wherein, the processor 410 is configured to input the first image to a preset model in a case that a shadow region exists in the first image; and carrying out color correction on the shadow area by using a preset model to obtain a second image.
In the embodiment of the present application, when a shadow region exists in a first image, the first image is input to a preset model, and color correction is performed on the shadow region by using the preset model. The training stopping condition of the preset model is that the predicted shadowless image of the training sample image and the color loss value of the label shadowless image of the training sample image meet the preset condition. Therefore, on the one hand, the color correction can be carried out on the shadow area in the first image by utilizing the preset model, the illumination compensation and the brightness recovery of the shadow area in the first image can be realized by carrying out the color correction, and the shadow area in the first image is removed, so that the color of the second image is more actually fitted, the information integrity and the definition of the second image are improved, the identifiability of the second image is improved, and the user experience can be effectively improved. On the other hand, the color of the first image is corrected by using the preset model, the shadow area in the first image is removed to obtain the second image, and the second image is more attractive, so that the user experience can be further improved.
Optionally, the processor 410 is further configured to:
calculating the occupation ratio of the shadow area in the first image;
and determining that a shadow area exists in the first image under the condition that the occupation ratio is greater than or equal to a preset occupation ratio.
Therefore, only when the ratio of the shadow area in the first image is greater than the preset ratio, that is, the shadow area in the first image may affect the information integrity and the definition of the first image and affect the legibility of the first image, the first image is subjected to image processing, so that some unnecessary image processing processes can be avoided, thereby effectively reducing power consumption and improving image processing efficiency.
Optionally, the processor 410 is further configured to:
performing Gaussian filtering processing on the first image to obtain a third image; the third image is used for reflecting the illumination information of the first image;
carrying out binarization processing on the third image to obtain a fourth image;
performing connected component analysis on the fourth image, and calculating the area of the connected component in the fourth image;
the ratio of the area of the connected component in the whole map area of the first image is calculated.
In this way, by performing binarization processing on the third image reflecting the illumination information of the first image to obtain the fourth image, the amount of data in the fourth image can be greatly reduced. In this way, the ratio of the area of the connected component in the fourth image to the full-map area of the first image is calculated based on the fourth image with a small data amount, so that the data calculation amount can be effectively reduced, and the image processing efficiency can be further improved.
Optionally, the processor 410 is further configured to:
zooming the first image to obtain a fifth image;
and performing Gaussian filtering processing on the fifth image to obtain a third image.
In this way, scaling the first image to the fifth image smaller than or equal to the first preset area can reduce power and power consumption, and thus can further improve image processing efficiency.
Optionally, the processor 410 is further configured to:
performing connected component analysis on the fourth image to obtain M connected regions in the fourth image;
removing a first communication area in the M communication areas;
calculating the total area of a second communication area in the M communication areas;
the ratio of the total area of the second connected regions in the full-map area of the first image is calculated.
In this way, in the fourth image obtained after the binarization processing of the third image, the first communication area with the area smaller than the second preset area is removed, that is, the shadow area in the fourth image, which does not affect the information integrity and the definition of the image and the legibility of the image, is removed. Thus, unnecessary image processing of the first connected region can be reduced, so that power consumption can be further reduced, and image processing efficiency can be improved.
Optionally, the processor 410 is further configured to:
calculating a sharpness value of the second image;
and saving the second image under the condition that the definition value of the second image is greater than or equal to the preset definition value.
Therefore, on one hand, the second image is a shadow-free area, and the information integrity and the definition value of the second image are higher than those of the first image, so that the user can view and use the image with higher identification degree, and the user experience can be further improved. On the other hand, on the basis of the non-shadow area of the second image, only the second image with the definition value larger than or equal to the preset definition value is stored for the user to view and use, so that the definition and the recognizability of the second image viewed and used by the user are higher, and the user experience can be further improved.
Optionally, the processor 410 is further configured to:
inputting the shooting preview image into a preset model under the condition that the shooting program is in a target shooting mode and a shadow region exists in the shooting preview image;
and photographing the second image and storing the second image.
Therefore, in the photographing process, the color correction of the photographing preview image with the shadow area can be realized, the shadow area in the photographing preview image is removed, so that the user can directly obtain the image without shadow, high in information integrity and high in definition in the photographing process, the recognizability of the photographed image is improved, and the user experience can be further improved.
The embodiment of the present application further provides a readable storage medium, where a program or an instruction is stored on the readable storage medium, and when the program or the instruction is executed by a processor, the program or the instruction implements each process of the embodiment of the image processing method, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here.
The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and so on.
An embodiment of the present application further provides a chip, where the chip includes a processor and a communication interface, the communication interface is coupled to the processor, and the processor is configured to execute a program or an instruction to implement the foregoing methodxxxThe processes of the method embodiment can achieve the same technical effect, and are not described herein again to avoid repetition.
It should be understood that the chips mentioned in the embodiments of the present application may also be referred to as system-on-chip, system-on-chip or system-on-chip, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Further, it should be noted that the scope of the methods and apparatus of the embodiments of the present application is not limited to performing the functions in the order illustrated or discussed, but may include performing the functions in a substantially simultaneous manner or in a reverse order based on the functions involved, e.g., the methods described may be performed in an order different than that described, and various steps may be added, omitted, or combined. In addition, features described with reference to certain examples may be combined in other examples.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present application.
While the present embodiments have been described with reference to the accompanying drawings, it is to be understood that the invention is not limited to the precise embodiments described above, which are meant to be illustrative and not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (12)
1. An image processing method, comprising:
inputting a first image to a preset model under the condition that a shadow region exists in the first image;
carrying out color correction on the shadow area by using the preset model to obtain a second image;
the training stopping condition of the preset model is that the color loss values of the predicted shadow-free image of the training sample image and the label shadow-free image of the training sample image meet the preset condition.
2. The method according to claim 1, wherein before inputting the first image to the preset model in the case that the shadow region exists in the first image, further comprising:
calculating the proportion of the shadow area in the first image;
determining that a shadow region exists in the first image when the ratio is greater than or equal to a preset ratio.
3. The method of claim 2, wherein the calculating the proportion of the shadow region in the first image comprises:
performing Gaussian filtering processing on the first image to obtain a third image; the third image is used for reflecting illumination information of the first image;
carrying out binarization processing on the third image to obtain a fourth image;
performing connected component analysis on the fourth image, and calculating the area of a connected component in the fourth image;
and calculating the ratio of the area of the connected component in the whole image area of the first image.
4. The method of claim 3, wherein the performing the Gaussian filter processing on the first image to obtain a third image comprises:
zooming the first image to obtain a fifth image; the area of the fifth image is smaller than or equal to a first preset area;
and performing Gaussian filtering processing on the fifth image to obtain a third image.
5. The method according to claim 3 or 4, wherein the performing connected component analysis on the fourth image and calculating the area of the connected component in the fourth image comprises:
performing connected component analysis on the fourth image to obtain M connected regions in the fourth image; m is a positive integer;
removing a first communication area in the M communication areas; the first communication area is a communication area with an area smaller than a second preset area;
calculating the total area of a second communication region of the M communication regions; the second communication area is a communication area of the M communication areas except the first communication area;
the calculating a ratio of the area of the connected component in the full-map area of the first image includes:
calculating a ratio of a total area of the second connected regions in a full-map area of the first image.
6. The method according to any one of claims 1 to 5, wherein after the color correction of the shadow region by using the preset model to obtain the second image, the method further comprises:
calculating a sharpness value of the second image;
and saving the second image under the condition that the definition value of the second image is greater than or equal to a preset definition value.
7. An image processing apparatus characterized by comprising:
the device comprises a first input module, a second input module and a display module, wherein the first input module is used for inputting a first image to a preset model under the condition that a shadow area exists in the first image;
the correction module is used for carrying out color correction on the shadow area by utilizing the preset model to obtain a second image;
the training stopping condition of the preset model is that the color loss values of the predicted shadow-free image of the training sample image and the label shadow-free image of the training sample image meet the preset condition.
8. The apparatus according to claim 7, wherein the image processing apparatus further comprises:
a first calculation module, configured to calculate a ratio of a shadow area in the first image to the shadow area in the first image;
a determining module, configured to determine that a shadow region exists in the first image when the ratio is greater than or equal to a preset ratio.
9. The apparatus of claim 8, wherein the first computing module comprises:
the filtering unit is used for carrying out Gaussian filtering processing on the first image to obtain a third image; the third image is used for reflecting illumination information of the first image;
a binarization unit, configured to perform binarization processing on the third image to obtain a fourth image;
a first calculation unit, configured to perform connected component analysis on the fourth image, and calculate an area of a connected component in the fourth image;
and a second calculation unit configured to calculate a ratio of an area of the connected component to an entire map area of the first image.
10. The apparatus of claim 9, wherein the filtering unit comprises:
the scaling subunit is used for scaling the first image to obtain a fifth image; the area of the fifth image is smaller than or equal to a first preset area;
and the filtering subunit is used for performing Gaussian filtering processing on the fifth image to obtain a third image.
11. The apparatus according to claim 9 or 10, wherein the first computing unit comprises:
the analysis component is used for carrying out connected component analysis on the fourth image to obtain M connected regions in the fourth image; m is a positive integer;
a removal component for removing a first communication region of the M communication regions; the first communication area is a communication area with an area smaller than a second preset area;
a calculation component for calculating a total area of second connected regions of the M connected regions; the second communication area is a communication area of the M communication areas except the first communication area;
the second computing unit is specifically configured to:
calculating a ratio of a total area of the second connected regions in a full-map area of the first image.
12. The apparatus according to any one of claims 7 to 11, wherein the image processing apparatus further comprises:
the second calculation module is used for calculating the definition value of the second image;
and the storage module is used for storing the second image under the condition that the definition value of the second image is greater than or equal to a preset definition value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110147559.7A CN112862714A (en) | 2021-02-03 | 2021-02-03 | Image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110147559.7A CN112862714A (en) | 2021-02-03 | 2021-02-03 | Image processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112862714A true CN112862714A (en) | 2021-05-28 |
Family
ID=75986425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110147559.7A Pending CN112862714A (en) | 2021-02-03 | 2021-02-03 | Image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112862714A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108305217A (en) * | 2017-12-28 | 2018-07-20 | 北京大学深圳研究生院 | Image shadow removing method and apparatus |
| CN109587466A (en) * | 2017-09-29 | 2019-04-05 | 华为技术有限公司 | The method and apparatus of colored shadow correction |
| CN110415185A (en) * | 2019-07-02 | 2019-11-05 | 长江大学 | A kind of improved Wallis shade automatic compensating method and device |
| CN110443763A (en) * | 2019-08-01 | 2019-11-12 | 山东工商学院 | A kind of Image shadow removal method based on convolutional neural networks |
| CN111667420A (en) * | 2020-05-21 | 2020-09-15 | 维沃移动通信有限公司 | Image processing method and device |
-
2021
- 2021-02-03 CN CN202110147559.7A patent/CN112862714A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109587466A (en) * | 2017-09-29 | 2019-04-05 | 华为技术有限公司 | The method and apparatus of colored shadow correction |
| CN108305217A (en) * | 2017-12-28 | 2018-07-20 | 北京大学深圳研究生院 | Image shadow removing method and apparatus |
| CN110415185A (en) * | 2019-07-02 | 2019-11-05 | 长江大学 | A kind of improved Wallis shade automatic compensating method and device |
| CN110443763A (en) * | 2019-08-01 | 2019-11-12 | 山东工商学院 | A kind of Image shadow removal method based on convolutional neural networks |
| CN111667420A (en) * | 2020-05-21 | 2020-09-15 | 维沃移动通信有限公司 | Image processing method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11410277B2 (en) | Method and device for blurring image background, storage medium and electronic apparatus | |
| US11830230B2 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| CN112308095A (en) | Picture preprocessing and model training method and device, server and storage medium | |
| US20110211233A1 (en) | Image processing device, image processing method and computer program | |
| CN107172354B (en) | Video processing method and device, electronic equipment and storage medium | |
| CN105243371A (en) | Human face beauty degree detection method and system and shooting terminal | |
| US9704227B2 (en) | Method and apparatus for image enhancement | |
| CN108805838B (en) | Image processing method, mobile terminal and computer readable storage medium | |
| CN112308797A (en) | Corner detection method and device, electronic equipment and readable storage medium | |
| CN113158773B (en) | Training method and training device for living body detection model | |
| CN112651953A (en) | Image similarity calculation method and device, computer equipment and storage medium | |
| CN112837251B (en) | Image processing method and device | |
| CN108289176B (en) | Photographing question searching method, question searching device and terminal equipment | |
| WO2006081018A1 (en) | Object-of-interest image capture | |
| CN108769521B (en) | Photographing method, mobile terminal and computer readable storage medium | |
| CN113688839B (en) | Video processing method and device, electronic equipment and computer readable storage medium | |
| CN112449115B (en) | Shooting method and device and electronic equipment | |
| CN112532884B (en) | Identification method and device and electronic equipment | |
| CN113391779A (en) | Parameter adjusting method, device and equipment for paper-like screen | |
| US20240086661A1 (en) | Method and apparatus for processing graphic symbol and computer-readable storage medium | |
| CN112511890A (en) | Video image processing method and device and electronic equipment | |
| CN112862714A (en) | Image processing method and device | |
| WO2023001110A1 (en) | Neural network training method and apparatus, and electronic device | |
| CN107103321B (en) | The generation method and generation system of road binary image | |
| CN105893578A (en) | Method and device for selecting photos |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |