WO2018095059A1 - Image processing method and device - Google Patents

Abstract

Provided are an image processing method and device. The method comprises: acquiring an image to be processed; determining whether the image to be processed has a characteristic region satisfying a preset notification rule; and if the image to be processed has the characteristic region, generating notification information corresponding to the characteristic region.

Description

Image processing method and device Technical field

The present disclosure relates to the field of Internet technologies, for example, to an image processing method and apparatus.

Background technique

When taking pictures of people, sometimes the photographer is in a slack state, which causes the person being photographed to be dissatisfied with the photos taken. For example, people are getting bigger and bigger in middle-aged beer, but they don’t like beer belly when taking pictures. The appearance of the camera, if you can take a belly when you take a picture, to maintain a good body shape, then you can take a satisfactory picture.

However, in the actual photographing process, it is usually found that the photo has a poor shape when photographing the photograph, thereby affecting the user experience.

In response to the above problems, no effective solution has been proposed yet.

Summary of the invention

The present disclosure provides an image processing method and apparatus to solve the problem of low user experience when photographing in the related art.

This embodiment provides an image processing method, which may include:

Obtaining a to-be-processed image; determining whether there is a feature area on the image to be processed that meets a preset reminder rule;

And if the feature area is on the image to be processed, generating reminder information corresponding to the feature area.

Optionally, determining whether there are feature areas on the to-be-processed image that meet the preset reminder rule, including:

Identifying a plurality of target regions from the image to be processed;

Determining, in each of the plurality of target areas, whether there is a feature area that satisfies the preset reminder rule.

Optionally, determining, by one of the plurality of target areas, whether there is a feature area that satisfies the preset reminder rule, includes: performing the following operations one by one of the plurality of target areas:

Obtaining a pre-stored standard feature shape image corresponding to the current target area;

Comparing the current region with the standard feature morphology image to obtain a comparison error;

When the error is greater than a preset threshold, determining that the current target area is the feature area.

Optionally, the image to be processed is a preview image when the character is photographed.

Optionally, the target area comprises at least one of: a belly, a shoulder, a mouth, an eye, a neck, and a leg.

Optionally, generating the reminder information corresponding to the feature area includes: generating a reminder box corresponding to the feature area, wherein the reminder box is disposed at a location range where the feature area is located.

Optionally, after generating the alert box corresponding to the feature region, the method further includes: setting the alert frame to a blinking state.

Optionally, after generating the alert box corresponding to the feature area, the method further includes: performing a reminder by using at least one of a voice mode and a text mode.

Optionally, before acquiring the image to be processed, the method further includes: buffering the captured image in a storage area; and obtaining the image to be processed includes: reading the preview image from the storage area, and using the preview image As the image to be processed.

The embodiment further provides an image processing apparatus, which may include:

Obtain a module, set to obtain a to-be-processed image;

a determining module, configured to determine whether there is a feature area on the image to be processed that meets a preset reminder rule;

And generating a module, configured to generate reminder information corresponding to the feature area when the feature area is present on the image to be processed.

Optionally, the determining module includes:

An identification unit configured to identify a plurality of target regions from the image to be processed;

And determining, by one of the plurality of target areas, whether there is a feature area that satisfies the preset reminder rule.

Optionally, the determining unit is configured to perform the following operations on the plurality of target areas one by one: acquiring a pre-stored standard feature shape image corresponding to the current target area; and the current area and the standard feature form image Comparing, obtaining a comparison error; and when the error is greater than a preset threshold, determining that the current target area is the feature area.

Optionally, the generating module is configured to generate a reminder box corresponding to the feature area, wherein the reminder box is disposed at a location range where the feature area is located.

Optionally, the image processing apparatus further includes: a storage module, configured to cache the captured preview image in a storage area before acquiring the image to be processed; and the acquiring module is configured to read from the storage area The preview image is used as the image to be processed.

The embodiment further provides a computer readable storage medium storing computer executable instructions for performing any of the above methods.

The embodiment also provides an electronic device including one or more processors, a memory, and one or more programs, the one or more programs being stored in the memory when executed by one or more processors When performing any of the above methods.

The embodiment further provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions, when the program instructions are executed by a computer Having the computer perform any of the methods described above.

In this embodiment, by detecting an image, it is determined whether there is an area in the image that needs to be reminded to remind the user, thereby solving the technical problem that the user experience is not high when photographing in the related art, and the user experience is effectively improved. Technical effects.

DRAWINGS

1 is a flow chart 1 of an image processing method in this embodiment;

Figure 2a is a block diagram 1 of the structure of the image processing apparatus in this embodiment;

Figure 2b is a block diagram 2 of the structure of the image processing apparatus in this embodiment;

Figure 3 is a block diagram 3 of the structure of the image processing apparatus in this embodiment;

Figure 4 is a schematic view showing the identification of beer belly in the embodiment;

Figure 5 is a second flowchart of the image processing method in this embodiment;

FIG. 6 is a schematic structural diagram of an electronic device in the embodiment.

detailed description

This embodiment can find a relatively insufficient place in the photo during the photo preview to remind the person who takes the photo, thereby improving the satisfaction of taking the photo.

An image processing method is provided in the embodiment. FIG. 1 is a flowchart 1 of the image processing method in the embodiment. As shown in FIG. 1 , the method may include the following steps:

In step 110, an image to be processed is acquired.

The image to be processed may be an image that needs to be recognized, such as a preview image when photographing. For example, the storage and presence of the image to be processed can be determined according to actual needs.

If the image to be processed is a preview image at the time of photographing, the captured preview image may be cached in the storage area; the captured preview image is read from the storage area, and the read preview image is taken as the image to be processed.

In step 120, it is determined whether there is a feature area on the image to be processed that satisfies a preset reminder rule.

After the image to be processed is acquired, the image to be processed may be subjected to image recognition processing, for example, some preset region positions in the image to be processed may be determined. If the image to be processed is a preview image when the person takes a picture, it can be determined whether there is a beer belly in the preview image, that is, the position of the belly in the preview image is first recognized, and then it is determined whether the position area of the belly in the preview image conforms to the preset. The position area of the beer belly, if it is met, determines that the area corresponding to the belly in the preview image is the area to be reminded, that is, the above characteristic area.

It is also possible to perform identification analysis on other areas in the image, for example, to identify whether the shoulder is high or low, and the process of recognition is similar to the process of identifying the beer belly described above, and details are not described herein again.

Optionally, when the image reminding operation is performed, a plurality of target areas may be identified from the to-be-processed image, and whether the plurality of target areas have the feature areas satisfying the preset reminding rule are determined one by one. Wherein, one or more of the feature regions may exist in the plurality of target regions.

Optionally, whether the feature area that meets the preset reminder rule is determined by the plurality of target areas may be determined one by one according to the following manner:

Perform the following operations one by one for the multiple target areas:

In S1, a pre-stored standard feature morphological image corresponding to the current target area is acquired.

In S2, the current region is compared with the standard feature image to obtain a contrast error.

In S3, when the error is greater than a preset threshold, determining that the current target area is the feature area.

The image to be processed may be a preview image when the person takes a picture. Accordingly, the target area may include at least one of the following: a belly, a shoulder, a mouth, an eye, a neck, and a leg, but is not limited thereto.

In step 130, if there is the feature area on the image to be processed, the reminder information corresponding to the feature area is generated.

Optionally, generating the reminder information corresponding to the feature area may include: generating a reminder box corresponding to the feature area, where the reminder box is disposed at a location range where the feature area is located. It is also possible to set the reminder box to a blinking state after generating the reminder box.

Optionally, after the reminder box is generated, in order to make the user know the problem in the photograph taken, pay attention to the place in the photo that needs to be optimized, the user may be reminded by at least one of a voice mode and a text mode. For example, the voice prompts the user to have a poor physical appearance, such as "please take a stomach", etc., and can also display text prompt information in the interface of the preview image, such as displaying "beer belly" and "high and low shoulder" and other text prompt information.

An image processing apparatus is also provided in this embodiment. The implementation of the image processing apparatus may refer to the implementation of the image processing method described above, and details are not described herein again.

2a is a block diagram of the structure of the image processing apparatus of the present embodiment. As shown in FIG. 2a, the apparatus may include an acquisition module 201, a determination module 202, and a generation module 203.

The obtaining module 201 can be configured to acquire an image to be processed.

The determining module 202 may be configured to determine whether there is a feature area on the image to be processed that meets a preset reminder rule.

The generating module 203 may be configured to generate reminder information corresponding to the feature area when the feature area is present on the image to be processed.

Optionally, as shown in FIG. 2b, the determining module 202 may include: an identifying unit 2021 configured to identify a plurality of target regions from the to-be-processed image; and a determining unit 2022 configured to determine the plurality of target regions one by one Whether there is a feature area that satisfies the preset reminder rule.

Optionally, the determining unit 2022 is configured to perform the following operations on the plurality of target areas one by one: acquiring a pre-stored standard feature morphogram corresponding to the current target area; performing the current area and the standard feature morphological image In contrast, a comparison error is obtained; when the error is greater than a preset threshold, it is determined that the current target area is the feature area.

Optionally, the generating module 203 is configured to generate a reminder box corresponding to the feature area, wherein the reminder box is disposed at a location range where the feature area is located.

Optionally, as shown in FIG. 2b, the image processing apparatus may further include: a storage module 204 configured to cache the captured preview image in a storage area before acquiring the image to be processed; the obtaining module 201 is configured to The preview image is read from the storage area, and the preview image is used as the image to be processed.

In the embodiment, the image recognition method and the device in the embodiment are further applied to other image processing scenarios.

The image recognition method provided in this embodiment can identify shortcomings such as poor appearance of a person in a photo when photographing a character, for example, beer belly, cold face, hunchback and high and low shoulders, etc., can remind the photographer to improve these when the photo is previewed. Problems that effectively improve the user experience.

When taking a picture, some implementations use smile recognition or other gesture recognition to take pictures. That is, the purpose of these feature recognition is to determine whether the preset photo conditions are currently being met, so that the pictures can be taken automatically, but these methods cannot be performed. The user's photographing is guided as a whole and the defects of the photographed person at the time of photographing are not reminded.

In this example, some human body feature recognition comparison rules may be preset. When the photo preview is performed, the preview photo obtained by the photograph is identified according to a preset comparison rule to determine whether there is a place in the current photo that needs to be reminded of the photographed person. That is, it is determined whether the physical appearance of the person being photographed needs to be adjusted in order to obtain a photo with better effect and improve the user experience.

3 is a block diagram of the structure of the image processing apparatus in the embodiment. As shown in FIG. 3, an image processing apparatus is provided, which may include: a central processing unit 101, a photographing module 102, a physical feature recognition module 103, and a reminder module 104. And a display module 105, wherein

The photographing module 102 may include: a camera, an image processing module, a storage area, and the like. After the camera captures the image before the lens, the image is processed by the image processing module and displayed on the display screen of the display module 105, and the collected image is cached in the storage. region.

The physical feature recognition module 103 may be configured to: in the preview state, extract a preview image of the cache from the storage area, identify the person information in the image, and extract feature information of the character for analysis, wherein the feature information of the character may include at least the following One: "Beer belly", "pouting", "different shoulder height" and "humpback" and other physical features, but not limited to this, analyze whether these feature information belongs to the characteristics that need to be adjusted, when determining that the information needs to be adjusted At the same time, the reminder module 104 is activated.

The reminding module 104 can display the preset reminder mark in the display area of the corresponding position after the human object feature is recognized in the preview state, for example, display a red dotted frame, and set the dotted frame to a blinking state. Reminders can also include, but are not limited to, text reminders and voice reminders.

The display module 105 can display the photo preview image and the reminder information of the reminder module 104.

Based on the above image processing apparatus, an image processing method is further provided in this embodiment, which may include the following steps:

In S1, after the camera module is activated, the physical feature recognition module is activated.

In S2, the physical feature recognition module recognizes a feature to be reminded that needs to be reminded of the user in the appearance of the object. And start the reminder module.

In S3, the reminding module displays a red dotted frame around the position of the feature to be reminded according to the feature of the character, and flashes a reminder.

Based on the identification of the physical characteristics of the character and the photo reminder as an example:

The body shape recognition module identifies the body part that needs to be reminded. Taking the belly as an example, the recognition module recognizes a closed area of the area of the belly in the picture to be recognized, taking the upper left corner of the picture as the coordinate origin (0, 0) and the right direction as the x direction. , the downward direction is the y direction, and the position of the minimum value of the x coordinate of all the pixel points on the edge of the closed area is generated by a dotted line parallel to the y axis, corresponding to the leftmost side of the dotted line frame, and is generated at the position where the maximum value of the x coordinate is located. The dotted line parallel to the y-axis corresponds to the rightmost line of the dotted line frame, and the position of the minimum value of the y coordinate of all the pixel points on the edge of the closed area generates a dotted line parallel to the x-axis, corresponding to the uppermost side of the dotted line frame, at the y coordinate The position where the maximum value is located generates a broken line parallel to the x-axis, corresponding to the lowermost side of the dotted line frame, and the generated four lines intersect to form a rectangular frame as shown in FIG. 4;

The display module 105 displays the image acquired and processed by the camera in the preview state, and the reminder module 104 generates a reminder graphic or data. As shown in FIG. 4, 401 represents a person image collected in a preview state of the camera, and 402 represents the identified "beer belly". ", 403 indicates the reminder wireframe.

FIG. 5 is a second flowchart of the image processing method in the embodiment. As shown in FIG. 5, the method may include the following steps:

In step 510, after the camera module is activated, the physical feature recognition module is activated.

In step 520, the physical feature recognition module recognizes the feature to be reminded that needs to be reminded of the user in the appearance of the object, and activates the reminder module.

Wherein, the physical feature module can pre-store a plurality of feature location areas, for example, may include: correct or beautiful physical features of the face, shoulders, back, abdomen and legs, etc., and adjusting these physical features can better Take a photo, when the physical character recognition module recognizes the physical appearance of these locations When there are features to be reminded in the levy, such as beer belly, etc., the reminder module is activated.

In step 530, the reminding module displays the position and the area of the feature to be reminded according to the physical feature recognition module, displays a red dotted frame around the position of the feature to be reminded, and flashes a reminder.

Here are a few examples to illustrate the process of identifying features such as beer belly and high and low shoulders:

Example 1

The method for identifying "beer belly" may include the following steps:

In S1, the physical feature recognition module extracts the cached image.

In S2, the human body features are identified, for example, the position of the human head, the stomach and the legs are recognized, the edge of the tummy region is recognized in the tummy region, the condition of the edge is judged to be a striped reference, and the striped reference is folded by the clothes. The gully formed, or the protrusion of the human body at the edge of the belly area.

In S3: comparing the presence or absence of a striped pattern on the edge of the belly, comparing the similarity between the striped pattern and the stored striped reference pattern, and if it is similar, it is judged as "beer belly".

For example, the similarity threshold may be set, and when the similarity value obtained after the similarity comparison reaches the preset similarity threshold, it is determined as “beer belly”.

In S4, in the preview interface, a reminder wireframe is displayed around the belly area.

Example 2

The method of identifying the "mouth" can include the following steps:

In S1, the physical feature recognition module extracts the cached image and recognizes the facial features, for example, identifying the positions of the human eye, the nose, and the mouth.

In S2, a horizontal straight line is drawn at the position of the upper and lower edges of both eyes, and the horizontal straight line is drawn on the left and right sides of the nose and both eyes.

In S3, calculate the distance from the left corner to the left vertical line, and calculate the distance from the right mouth angle to the right vertical line. When the two distance differences calculated above exceed a certain ratio (for example, 10%), judge For "Pouting."

Example 3

The identification method of "different shoulder height" may include the following steps:

In S1, the physical feature recognition module extracts the cached image, recognizes the head and the upper body, and takes the central positions of the two to form a straight line.

In S2, the left and right shoulders are identified and connected in a straight line.

In S3, the angle between the two straight lines in S1 and S2 is between 0 and 85 degrees, and it is judged that "the shoulder height is different".

Example 4

The "humpback" identification method may include the following steps:

In S1, the physical feature recognition module extracts the cached image, identifying the head and upper body, and the neck.

In S2, the center position of the head and the center of the neck are in a straight line, and the center position of the upper body and the center of the neck are in a straight line.

In S3, if the angle between the two straight lines in S2 is greater than 15 degrees, it is judged as "humpback".

In this embodiment, by identifying the image, it is determined whether there is an area in the image that needs to be reminded to the user, so as to remind the user, thereby solving the problem that the user experience is not high when the user takes a picture in the related art, and the user experience is effectively improved.

The embodiment further provides a computer readable storage medium storing computer executable instructions for performing the above method.

FIG. 6 is a schematic diagram showing the hardware structure of an electronic device according to the embodiment. As shown in FIG. 6, the electronic device may include: one or more processors 610 and a memory 620. One processor 610 is taken as an example in FIG.

The electronic device may further include: an input device 630 and an output device 640.

The processor 610, the memory 620, the input device 630, and the output device 640 in the electronic device may be connected by a bus or other means, and the connection through the bus is taken as an example in FIG.

The input device 630 can receive input numeric or character information, and the output device 640 can include a display device such as a display screen.

The memory 620 is a computer readable storage medium that can be used to store software programs, computer executable programs, and modules. The processor 610 performs various functional applications and data processing by executing software programs, instructions, and modules stored in the memory 620 to implement any of the above embodiments. The memory 620 may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to usage of the electronic device, and the like. In addition, the memory may include volatile memory such as random access memory (RAM), and may also include non-volatile memory such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device.

Memory 620 can be a non-transitory computer storage medium or a transitory computer storage medium. The non-transitory computer storage medium, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. The memory 620 can optionally include a memory remotely disposed relative to the processor 610, which can be connected to the electronic device through a network. The above network may include the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

Input device 630 can be used to receive input digital or character information and to generate key signal inputs related to user settings and function controls of the electronic device. The output device 640 can include a display device such as a display screen.

The electronic device of the present embodiment may further include a communication device 650 that transmits and/or receives information over a communication network.

All or part of the processes provided by the foregoing embodiments may be implemented by a computer program executing related hardware, and the program may be stored in a non-transitory computer readable storage medium, and when executed, the program may be executed. The flow of an embodiment of the method as described above, wherein the non-transitory computer readable storage medium can be a magnetic disk, an optical disk, a read only memory (ROM) or a random access memory (RAM), or the like.

Industrial applicability

The invention discloses an image processing method and device, which can remind a position of a poor effect in an image, so that the user can timely adjust the position and effectively improve the user experience.

Claims (15)

An image processing method comprising: Get the image to be processed; Determining whether there is a feature area on the image to be processed that meets a preset reminder rule; In the case where the feature area is present on the image to be processed, reminder information corresponding to the feature area is generated. The method of claim 1, wherein determining whether there is a feature area on the image to be processed that meets a preset reminder rule comprises: Identifying a plurality of target regions from the image to be processed; Determining, in each of the plurality of target areas, whether there is a feature area that satisfies the preset reminder rule. The method of claim 2, wherein determining, by one of the plurality of target areas, whether there is a feature area that satisfies the preset reminder rule comprises: Perform the following operations one by one for the multiple target areas: Obtaining a pre-stored standard feature shape image corresponding to the current target area; Comparing the current region with the standard feature morphology image to obtain a comparison error; When the error is greater than a preset threshold, determining that the current target area is the feature area. The method of claim 2, wherein the image to be processed is a preview image when a person is photographed. The method of claim 4, wherein the target area comprises at least one of: a belly, a shoulder, a mouth, an eye, a neck, and a leg. The method of claim 1, wherein generating reminder information corresponding to the feature area comprises: Generating a reminder box corresponding to the feature area, wherein the reminder box is disposed in the feature area The location range where the domain is located. The method of claim 6, wherein after generating the reminder box corresponding to the feature area, the method further comprises: The reminder box is set to a blinking state. The method of claim 6, wherein after generating the reminder box corresponding to the feature area, the method further comprises: Remind by at least one of voice and text. The method according to any one of claims 1 to 8, wherein, before acquiring the image to be processed, further comprising: buffering the captured preview image in a storage area; The acquiring the image to be processed includes: reading the preview image from the storage area, and using the preview image as the image to be processed. An image processing apparatus comprising: Obtain a module, set to obtain a to-be-processed image; a determining module, configured to determine whether there is a feature area on the image to be processed that meets a preset reminder rule; And generating a module, configured to generate reminder information corresponding to the feature area when the feature area is present on the image to be processed. The apparatus of claim 10 wherein said determining module comprises: An identification unit configured to identify a plurality of target regions from the image to be processed; And determining, by one of the plurality of target areas, whether there is a feature area that satisfies the preset reminder rule. The apparatus according to claim 11, wherein said determining unit is configured to perform the following operations one by one of said plurality of target areas: Obtaining a pre-stored standard feature shape image corresponding to the current target area; Comparing the current region with the standard feature morphology image to obtain a comparison error; When the error is greater than a preset threshold, determining that the current target area is the feature area. The apparatus of claim 10, wherein the generating module is configured to generate a reminder box corresponding to the feature area, wherein the reminder box is disposed at a location range where the feature area is located. The apparatus of any one of claims 10 to 13 further comprising: a storage module, configured to cache the captured preview image in a storage area before acquiring the image to be processed; The acquiring module is configured to read the preview image from the storage area, and use the preview image as the image to be processed. A computer readable storage medium storing computer executable instructions for performing the method of any of claims 1-9.

Images