CN111783777A

CN111783777A - Image processing method, image processing device, electronic equipment and computer readable medium

Info

Publication number: CN111783777A
Application number: CN202010648630.5A
Authority: CN
Inventors: 郭冠军
Original assignee: Beijing ByteDance Network Technology Co Ltd
Current assignee: Beijing ByteDance Network Technology Co Ltd
Priority date: 2020-07-07
Filing date: 2020-07-07
Publication date: 2020-10-16
Anticipated expiration: 2040-07-07
Also published as: CN111783777B

Abstract

The embodiment of the disclosure discloses an image processing method, an image processing device, an electronic device and a computer readable medium. One embodiment of the method comprises: identifying the contour of a target object in an image to be processed to obtain at least one contour of the object; generating a circumscribed rectangle of each outline to obtain at least one outline circumscribed rectangle; classifying the region to be processed surrounded by each outline circumscribed rectangle to obtain class information; and selecting a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information. The embodiment utilizes the outline of the target object in the image to circumscribe the rectangle to realize the positioning of the target object in the image.

Description

Image processing method, image processing device, electronic equipment and computer readable medium

Technical Field

Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to an image processing method and apparatus, an electronic device, and a computer-readable medium.

Background

An image processing technique is a technique of applying some kind of operation and processing to an image using a computer, a camera, and other digital processing techniques to extract various kinds of information in the image. Object detection is one of the image processing techniques, and can help identify and locate objects of interest in an image. The existing target detection algorithm has the problems of single detection method and low detection accuracy.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose an image processing method, apparatus, electronic device and computer readable medium to solve the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide an image processing method, including: identifying the contour of a target object in an image to be processed to obtain at least one contour of the object; generating a circumscribed rectangle of each outline to obtain at least one outline circumscribed rectangle; classifying the region to be processed surrounded by each outline circumscribed rectangle to obtain class information; and selecting a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information.

In a second aspect, some embodiments of the present disclosure provide an image processing apparatus comprising: the image processing device comprises an identification unit, a processing unit and a processing unit, wherein the identification unit is configured to identify the contour of a target object in an image to be processed to obtain at least one contour of the object; the generating unit is configured to generate a circumscribed rectangle of each outline, and obtain at least one outline circumscribed rectangle; the classification unit is configured to classify the to-be-processed area surrounded by each outline circumscribed rectangle to obtain class information; and the suppression processing unit is configured to select a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information.

In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.

In a fourth aspect, some embodiments of the disclosure provide a computer readable medium having a computer program stored thereon, where the program when executed by a processor implements a method as described in any of the implementations of the first aspect.

One of the above-described various embodiments of the present disclosure has the following advantageous effects: and identifying the contour of the target object in the image to be processed so as to obtain at least one contour of the object. And then, generating a circumscribed rectangle of each outline to obtain at least one outline circumscribed rectangle, thereby roughly determining the position information of the target object in the image. And finally, selecting a target outline bounding rectangle from the at least one outline bounding rectangle according to the category information obtained by classifying the to-be-processed area surrounded by the outline bounding rectangle. And further realize the positioning of the above objects. Therefore, the outline of the target object in the image is used for circumscribing the rectangle, so that the object included by the circumscribed rectangle is positioned, and the detection accuracy is improved.

Drawings

The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and features are not necessarily drawn to scale.

Fig. 1 is a schematic diagram of one application scenario of an image processing method of some embodiments of the present disclosure;

FIG. 2 is a flow diagram of some embodiments of an image processing method according to the present disclosure;

FIG. 3 is a flow diagram of further embodiments of an image processing method according to the present disclosure;

FIG. 4 is a schematic block diagram of some embodiments of an image processing apparatus according to the present disclosure;

FIG. 5 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.

It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.

The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 shows a schematic diagram of one application scenario in which the image processing method of some embodiments of the present disclosure may be applied.

As shown in fig. 1, a computing device 101 may acquire a to-be-processed image 102. Here, the to-be-processed image 102 includes a teaching aid drawing 103 and a teaching aid drawing 104 as an example. The computing device 101 recognizes the outlines of the teaching aid drawing 103 and the teaching aid drawing 104 in the image 102 to be processed through an outline extraction algorithm, and obtains outlines 105 and 106 of the teaching aid drawing 103 and outlines 107 and 108 of the teaching aid drawing 104. Thereafter, a circumscribed rectangle 109 of outline 105, a circumscribed rectangle 110 of outline 106, a circumscribed rectangle 112 of outline 107, and a circumscribed rectangle 111 of outline 108 are generated. Finally, image classification is carried out on the regions to be processed, which are surrounded by the outline bounding rectangle 109, the outline bounding rectangle 110, the outline bounding rectangle 111 and the outline bounding rectangle 112, so as to obtain the class information of the images and the classification probability corresponding to the class information. Finally, according to the classification probability of the region to be processed surrounded by the outline bounding rectangle 109 and the outline bounding rectangle 110, the outline bounding rectangle corresponding to the maximum classification probability is selected and mapped to the image to be processed 102 as the target outline bounding rectangle 113. Similarly, a target outline bounding rectangle 114 is obtained.

The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of multiple servers or terminal devices, or may be implemented as a single server or a single terminal device. When the computing device is embodied as software, it may be implemented as multiple pieces of software or software modules, for example, to provide distributed services, or as a single piece of software or software module. And is not particularly limited herein.

It should be understood that the number of computing devices 101 in FIG. 1 is merely illustrative. There may be any number of computing devices 101, as desired for implementation.

With continued reference to fig. 2, a flow 200 of some embodiments of an image processing method according to the present disclosure is shown. The image processing method comprises the following steps:

step 201, identifying the contour of the target object in the image to be processed, and obtaining at least one contour of the object.

In some embodiments, the executing subject of the image processing method (e.g., the computing device shown in fig. 1) may employ various contour detection algorithms to identify (e.g., edge-based contour extraction algorithms) the contour of a target object (e.g., a teaching aid) in the image to be processed.

Here, the image to be processed may be an image on which a target object is displayed. The target object includes, but is not limited to, at least one of the following: articles, such as teaching aids; a human. The contour of the target object in the image is composed of edge pixels of the target object. The width of the pixels of the contour is classified as a single-pixel width contour or a multi-pixel width contour. For an image with a contour of a single pixel width, at least one contour can be extracted by a contour detection algorithm. In practice, for an image with a contour of multiple pixel width, the inner contour and the outer contour can be extracted through a contour detection algorithm, so that at least two contours can be obtained.

In some embodiments, the performing the extracting the contour in the image by the subject may include: the picture is firstly subjected to gray processing, such as image binarization. And then, carrying out edge detection on the image after the gray processing, and extracting edge information. For example, the Sobel edge detection algorithm, the Canny edge detection algorithm or the Laplacian operator can be used to extract the edge information of the image. And finally, obtaining the contour information by removing noise existing in the edge information and repairing the edge information.

The edge information can be repaired by connecting the discrete edges in series by using an edge tracking method. The edge tracking method is divided into eight neighborhoods and four neighborhoods. The method is to perform edge tracking according to a preset tracking direction (for example, clockwise direction), and the termination condition of each tracking is that no contour exists in 8 neighborhoods or four neighborhoods.

Step 202, generating a circumscribed rectangle of each outline to obtain at least one outline circumscribed rectangle.

In some embodiments, the bounding rectangle of the outline may be the smallest rectangle that contains the outline region with sides parallel to the sides of the image. Wherein the outline region includes the outline and its inner region.

In this embodiment, the coordinate values (x, y) of the pixel points in the contour region may be counted for each contour region. The maximum and minimum values of the coordinate x and the coordinate y within the contour region are determined, respectively. Then, a circumscribed rectangle of the outline region is generated with four coordinate values of the minimum value and the maximum value of x and y as vertices. As an example, the coordinate value of the pixel point at the upper left corner of the image may be written as (0, 0).

And step 203, classifying the areas to be processed, which are surrounded by the outline circumscribed rectangles, respectively to obtain class information.

In some embodiments, the executing subject of the image processing method may employ various image classification algorithms (e.g., a transfer learning algorithm, an image classification algorithm based on a support vector machine), to classify the image of the region to be processed surrounded by each outline bounding rectangle, so as to obtain the category information of the image. Wherein the region to be processed surrounded by each outline bounding rectangle is the region surrounded by the corresponding outline bounding rectangle obtained in step 202 mapped to the image to be processed.

As an example, the executing body may perform image classification on the regions to be processed respectively as follows:

firstly, the circumscribed rectangle obtained in step 202 is mapped onto the image to be processed, so as to obtain the image to be processed with a rectangular frame. And cutting the image to be processed to obtain the area to be processed in each rectangular frame. Finally, an image classification algorithm based on a support vector machine can be adopted to classify the image of the region to be processed, so that the image classification information and the corresponding classification probability in each rectangular frame are obtained.

And 204, selecting a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information.

In some embodiments, as an example, for each contour circumscribed rectangle of each target object of the image to be processed, the contour circumscribed rectangles whose classification probabilities are smaller than a predetermined value among the contour circumscribed rectangles are removed, and one having the largest area is selected from the remaining contour circumscribed rectangles as the target circumscribed rectangle. Wherein, the outline bounding rectangle of the same target object can be obtained by calculating that the distance of the gravity center of the outline bounding rectangle is less than a predetermined value.

In some optional ways of some embodiments, the image processing method may perform the step of selecting a target bounding rectangle from the at least one outline bounding rectangle by the main body, and may be performed as follows:

firstly, selecting each outline circumscribed rectangle meeting preset conditions.

Wherein, as an example, the predetermined condition includes: the gravity center distance of each circumscribed rectangle is less than or equal to a preset value.

And secondly, selecting the outline circumscribed rectangle corresponding to the classification probability with the highest probability from the all classification probabilities corresponding to the outline circumscribed rectangle as the target outline circumscribed rectangle. One of the above-described various embodiments of the present disclosure has the following advantageous effects: and identifying the contour of the target object in the image to be processed so as to obtain at least one contour of the object. And then, generating a circumscribed rectangle of each outline to obtain at least one outline circumscribed rectangle, so that the position information of the target object in the image can be roughly determined. And finally, selecting a target outline bounding rectangle from the at least one outline bounding rectangle by utilizing the category information obtained by classifying the to-be-processed area surrounded by the outline bounding rectangle. And further realize the positioning of the target object. Therefore, the target object included by the circumscribed rectangle is positioned by utilizing the circumscribed rectangle of the outline of the target object in the image.

With further reference to fig. 3, a flow 300 of further embodiments of an image processing method is shown. The flow 300 of the image processing method comprises the following steps:

step 301, identifying the contour of the target object in the image to be processed, and obtaining at least one contour of the object.

In some embodiments, the subject of the image processing method performing the identifying of the contour of the target object in the image to be processed may proceed as follows:

and 3011, inputting the image to be processed into a pre-trained contour extraction network model, and outputting the contour of the target object in the image to be processed. The contour extraction network may be HED (monolithic-Nested Edge Detection), CEDN (complete Convolutional Encoder-decoder network).

Step 3012, selecting a closed candidate contour from the candidate contours as the at least one contour.

In practice, the idea of boundary tracking can be adopted to obtain closed candidate contours. The method comprises the following specific steps: starting from the top left-hand point of the output image of step 3011, pixel-by-pixel scanning, as a point on the contour is encountered, its coordinates are noted and sequential tracking begins until the tracked subsequent point returns to the starting point, or there is no new subsequent point location. And responding to the condition that the coordinate of the last subsequent point is the same as the coordinate of the starting point, wherein the candidate contour is a closed candidate contour.

Step 302, generating a circumscribed rectangle of each outline to obtain at least one outline circumscribed rectangle.

In some embodiments, the specific implementation of step 302 and the technical effect thereof may refer to step 202 in the embodiment corresponding to fig. 2, which is not described herein again.

And 303, respectively inputting the to-be-processed area surrounded by each outline circumscribed rectangle into a pre-trained classification network model to obtain the class information of the to-be-processed area and the classification probability corresponding to the class information.

In some embodiments, the performing body of the image processing method may implement image classification using a classification network such as ResNet (residual error network).

And 304, selecting a circumscribed rectangle corresponding to the maximum classification probability in the circumscribed rectangles of the outline of each target object in the image to be processed as the circumscribed rectangles of the outline of the target by using a non-maximum suppression algorithm.

The essence of the non-maximum suppression algorithm is to find local maxima and suppress non-maximum elements. In some embodiments, the outline bounding rectangle with the highest classification probability in the outline bounding rectangles of each target object is found according to the obtained classification probability and the coordinate information of the bounding rectangles. The method comprises the following specific implementation steps: first, the classification probabilities of the regions to be processed obtained in step 303 are sorted in descending order. And then, selecting a contour circumscribed rectangle corresponding to the region to be processed with the highest classification probability as a target contour circumscribed rectangle, and calculating an IOU (Intersection-over-Unit) of the contour circumscribed rectangle and other contour circumscribed rectangles. Then, the obtained IOU removal overlap is high, for example, the IOU is larger than a preset threshold. And repeating the steps for the remaining outline circumscribed rectangles, thereby obtaining the target outline circumscribed rectangles of all the target objects in the image to be processed.

In step 305, position information of the center of gravity of the target circumscribed rectangle is determined as position information of the object corresponding to the target circumscribed rectangle.

Here, the position information of the center of gravity of the target outline bounding rectangle is the position information of the target object.

As can be seen from fig. 3, compared with the description of some embodiments corresponding to fig. 2, the flow 300 of the image processing method in some embodiments corresponding to fig. 3 highlights the contour detection algorithm and the extraction algorithm of the target contour bounding rectangle. The pre-trained contour extraction network model is adopted to extract the contour of the target object, and the complicated steps of extracting the edge information and applying the edge repairing algorithm by the traditional algorithm are omitted. And then, by selecting the closed contour, information irrelevant to the contour of the target object is removed, so that the classification result is more accurate. And finally, a non-maximum value suppression algorithm is adopted to select a target outline circumscribed rectangle, so that compared with the method shown in the figure 2, the target object is positioned more accurately and reliably.

With further reference to fig. 4, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of an image processing apparatus, which correspond to those shown in fig. 2, and which may be applied in particular in various electronic devices.

As shown in fig. 4, an image processing apparatus 400 of some embodiments includes: a recognition unit 401, a generation unit 402, a classification unit 403, and a suppression processing unit 404. The identification unit 401 is configured to identify a contour of a target object in an image to be processed, and obtain at least one contour of the object; a generating unit 402 configured to generate a circumscribed rectangle of each outline, resulting in at least one outline circumscribed rectangle; a classification unit 403 configured to classify the region to be processed surrounded by each outline bounding rectangle, respectively, to obtain class information; a suppression processing unit 404 configured to select a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information.

In an optional implementation manner of some embodiments, the identification unit 401 of the image processing apparatus 400 is further configured to: inputting the image to be processed into a pre-trained contour extraction network model, and outputting a candidate contour of a target object in the image; and selecting a closed candidate contour from the candidate contours as the at least one contour.

In an optional implementation manner of some embodiments, the classification unit 403 of the image processing apparatus 400 is further configured to: and inputting the outline bounding rectangle into a pre-trained classification network model to obtain the class information of the bounding rectangle and the classification probability corresponding to the class information.

In an optional implementation manner of some embodiments, the suppression processing unit 404 of the image processing apparatus 400 is further configured to: and selecting a circumscribed rectangle corresponding to the maximum classification probability in the circumscribed rectangles of the outline of each displayed object in the image to be processed as the circumscribed rectangle of the target outline by using a non-maximum suppression algorithm.

In an optional implementation manner of some embodiments, the suppression processing unit 404 of the image processing apparatus 400 is further configured to: selecting each outline circumscribed rectangle meeting the preset conditions; and selecting the outline circumscribed rectangle corresponding to the classification probability with the highest probability from the all classification probabilities corresponding to the outline circumscribed rectangle as the target outline circumscribed rectangle.

In an optional implementation manner of some embodiments, the image processing apparatus 400 further includes: a determination unit. Wherein the determination unit is configured to determine position information of a center of gravity of the target outline bounding rectangle as position information of an object corresponding to the target outline bounding rectangle.

It will be understood that the elements described in the apparatus 400 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and will not be described herein again.

Referring now to FIG. 5, a block diagram of an electronic device (e.g., the computing device of FIG. 1) 500 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device in some embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle-mounted terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 5 may represent one device or may represent multiple devices as desired.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of some embodiments of the present disclosure.

It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (HyperText transfer protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: identifying the outline of an object displayed in an image to be processed to obtain at least one outline of the object; generating a circumscribed rectangle of each outline to obtain at least one outline circumscribed rectangle; classifying the region to be processed surrounded by each outline circumscribed rectangle to obtain class information; and selecting a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information.

Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an identifying unit, a generating unit, a classifying unit, and a suppressing unit. The names of the units do not in some cases constitute a limitation to the units themselves, and for example, the identification unit may also be described as "a unit that identifies an outline of an object displayed in the image to be processed, resulting in at least one outline of the object".

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.

According to one or more embodiments of the present disclosure, there is provided an image processing method including: identifying the outline of an object displayed in an image to be processed to obtain at least one outline of the object; generating a circumscribed rectangle of each outline to obtain at least one outline circumscribed rectangle; classifying the region to be processed surrounded by each outline circumscribed rectangle to obtain class information; and selecting a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information.

According to one or more embodiments of the present disclosure, the identifying a contour of a target object in an image to be processed to obtain at least one contour of the object includes: inputting the image to be processed into a pre-trained contour extraction network model, and outputting a candidate contour of a target object in the image; and selecting a closed candidate contour from the candidate contours as the at least one contour.

According to one or more embodiments of the present disclosure, the classifying the to-be-processed region surrounded by each outline bounding rectangle to obtain category information includes: and respectively inputting the to-be-processed area surrounded by each outline circumscribed rectangle into a pre-trained classification network model to obtain the class information of the to-be-processed area and the classification probability corresponding to the class information.

According to one or more embodiments of the present disclosure, the selecting a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information includes: selecting each outline circumscribed rectangle meeting the preset conditions; and selecting the outline circumscribed rectangle corresponding to the classification probability with the highest probability from the all classification probabilities corresponding to the outline circumscribed rectangle as the target outline circumscribed rectangle.

According to one or more embodiments of the present disclosure, the selecting a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information includes: selecting a circumscribed rectangle corresponding to the maximum classification probability in the circumscribed rectangles of the outline of each target object in the image to be processed by using a non-maximum suppression algorithm, and taking the circumscribed rectangle as the circumscribed rectangle of the outline of the target object according to one or more embodiments of the disclosure, wherein the method further comprises the following steps: and determining the gravity center of the target circumscribed rectangle as the position of the pattern corresponding to the target circumscribed rectangle.

According to one or more embodiments of the present disclosure, the method further includes: and determining the position information of the gravity center of the target outline circumscribed rectangle as the position information of the object corresponding to the target outline circumscribed rectangle.

According to one or more embodiments of the present disclosure, there is provided an image processing apparatus including: the image processing device comprises an identification unit, a processing unit and a processing unit, wherein the identification unit is configured to identify the contour of a target object in an image to be processed to obtain at least one contour of the object; the generating unit is configured to generate a circumscribed rectangle of each outline, and obtain at least one outline circumscribed rectangle; the classification unit is configured to classify the to-be-processed area surrounded by each outline circumscribed rectangle to obtain class information; and the suppression processing unit is configured to select a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information.

According to one or more embodiments of the present disclosure, the identification unit is further configured to: inputting the image to be processed into a pre-trained contour extraction network model, and outputting a candidate contour of a target object in the image; and selecting a closed candidate contour from the candidate contours as the at least one contour.

According to one or more embodiments of the present disclosure, the classification unit is further configured to: and inputting the outline bounding rectangle into a pre-trained classification network model to obtain the class information of the bounding rectangle and the classification probability corresponding to the class information.

In accordance with one or more embodiments of the present disclosure, the suppression processing unit is further configured to: and selecting a circumscribed rectangle corresponding to the maximum classification probability in the circumscribed rectangles of the outline of each displayed object in the image to be processed as the circumscribed rectangle of the target outline by using a non-maximum suppression algorithm.

In accordance with one or more embodiments of the present disclosure, the suppression processing unit is further configured to: selecting each outline circumscribed rectangle meeting the preset conditions; and selecting the outline circumscribed rectangle corresponding to the classification probability with the highest probability from the all classification probabilities corresponding to the outline circumscribed rectangle as the target outline circumscribed rectangle.

According to one or more embodiments of the present disclosure, the image processing apparatus described above further includes: a determination unit. Wherein the determination unit is configured to determine position information of a center of gravity of the target outline bounding rectangle as position information of an object corresponding to the target outline bounding rectangle.

According to one or more embodiments of the present disclosure, there is provided an electronic device including: one or more processors; a storage device having one or more programs stored thereon, which when executed by the one or more processors, cause the one or more processors to implement the method as described in any above.

According to one or more embodiments of the present disclosure, there is provided a computer readable medium having a computer program stored thereon, wherein the program when executed by a processor implements any of the methods described above.

The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims

1. An image processing method comprising:

identifying the contour of a target object in an image to be processed to obtain at least one contour of the object;

generating a circumscribed rectangle of each outline to obtain at least one outline circumscribed rectangle;

classifying the region to be processed surrounded by each outline circumscribed rectangle to obtain class information;

and selecting a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information.

2. The method of claim 1, wherein the identifying a contour of a target object in the image to be processed, resulting in at least one contour of the object, comprises:

inputting the image to be processed into a pre-trained contour extraction network model, and outputting a candidate contour of a target object in the image;

and selecting a closed candidate contour from the candidate contours as the at least one contour.

3. The method according to claim 1 or 2, wherein the classifying the region to be processed surrounded by each outline bounding rectangle respectively to obtain the category information comprises:

and respectively inputting the to-be-processed area surrounded by each outline circumscribed rectangle into a pre-trained classification network model to obtain the class information of the to-be-processed area and the classification probability corresponding to the class information.

4. The method of claim 3, wherein said selecting a target circumscribe rectangle from the at least one circumscribe rectangle based on the category information comprises:

selecting each outline circumscribed rectangle meeting the preset conditions;

and selecting the outline circumscribed rectangle corresponding to the classification probability with the highest probability in all the classification probabilities corresponding to the outline circumscribed rectangle from the outline circumscribed rectangle as the target outline circumscribed rectangle.

5. The method of claim 3, wherein said selecting a target circumscribe rectangle from the at least one circumscribe rectangle based on the category information comprises:

and selecting a circumscribed rectangle corresponding to the maximum classification probability in the circumscribed rectangles of the outline of each target object in the image to be processed as the circumscribed rectangle of the target outline by using a non-maximum suppression algorithm.

6. The method of claim 5, wherein the method further comprises:

and determining the position information of the gravity center of the target outline bounding rectangle as the position information of the object corresponding to the target outline bounding rectangle.

7. An image processing apparatus comprising:

the image processing device comprises an identification unit, a processing unit and a processing unit, wherein the identification unit is configured to identify the contour of a target object in an image to be processed to obtain at least one contour of the object;

the generating unit is configured to generate a circumscribed rectangle of each outline, and obtain at least one outline circumscribed rectangle;

the classification unit is configured to classify the to-be-processed area surrounded by each outline circumscribed rectangle to obtain class information;

a suppression processing unit configured to select a target outline bounding rectangle from the at least one outline bounding rectangle based on the category information.

8. The image processing apparatus according to claim 7, wherein the identifying unit is further configured to:

9. The image processing apparatus according to claim 7 or 8, wherein the classification unit is further configured to:

10. The image processing apparatus according to claim 9, wherein the suppression processing unit is further configured to:

selecting each outline circumscribed rectangle meeting the preset conditions;

11. The image processing apparatus according to claim 9, wherein the suppression processing unit is further configured to:

12. The image processing apparatus according to claim 9, wherein the apparatus further comprises:

a determination unit configured to determine position information of a center of gravity of the target contour bounding rectangle as position information of an object corresponding to the target contour bounding rectangle.

13. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon;

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-6.

14. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-6.