WO2020077912A1

WO2020077912A1 - Image processing method, device, and hardware device

Info

Publication number: WO2020077912A1
Application number: PCT/CN2019/073082
Authority: WO
Inventors: 范旭; 李琰; 杨辉; 沈言浩
Original assignee: 北京微播视界科技有限公司
Priority date: 2018-10-19
Filing date: 2019-01-25
Publication date: 2020-04-23
Also published as: CN110070554A

Abstract

Disclosed are an image processing method, device, and hardware device. The image processing method comprises: segmenting a target image to obtain an outline of a target object; generating inner outline feature points of the target object according to the outline of the target object; generating outer outline feature points according to the inner outline feature point; filling a preset material into a region between the inner outline feature points and the outer outline feature points. In the image processing method of the embodiments of the present disclosure, it is possible to segment from an image a target object which needs to be processed and add material to a relevant region of the target object to form a special effect; when modifying the special effect, it is necessary only to modify the material and there is no need to re-edit the image again, thus efficiency and flexibility in producing a special effect is improved.

Description

Image processing method, device and hardware device

cross reference

This disclosure cites the Chinese patent application with the application number 201811222643.5 filed on October 19, 2018 and titled "Image Processing Method, Device, Hardware Device", which is fully incorporated by reference into this application.

Technical field

The present disclosure relates to the field of image processing, and in particular, to an image processing method, device, and hardware device.

Background technique

With the development of computer technology, the application range of smart terminals has been widely improved. For example, you can listen to music, play games, chat online and take pictures through smart terminals. For the photographing technology of the smart terminal, its photographic pixels have reached more than ten million pixels, which has a higher definition and a photographic effect comparable to that of professional cameras.

At present, when taking pictures with a smart terminal, not only can the camera software built in the factory be used to achieve the traditional effect of taking pictures, but also the application with additional functions can be achieved by downloading the application (Application, referred to as: APP) from the network side , For example, an APP that can realize functions such as dark light detection, beauty camera and super pixels. The beautification function of the smart terminal usually includes beautification processing effects such as skin tone adjustment, dermabrasion, big eyes, and thin face, and can perform the same degree of beautification processing on all the faces recognized in the image. There are currently APPs that can achieve simple special effects.

However, the current special effects function can only pre-set the special effects and synthesize them into the video or image. If you need to modify the special effects, you need to re-create the special effects and then synthesize them into the video or image, making the special effects very inflexible.

Summary of the invention

According to an aspect of the present disclosure, the following technical solutions are provided:

An image processing method includes: segmenting a target image to obtain a contour of a target object; generating an inner contour feature point of the target object according to the contour of the target object; generating an outer contour feature point according to the inner contour feature point Filling the preset material into the area between the inner contour feature point and the outer contour feature point;

Further, the generating the inner contour feature point of the target object according to the contour of the target object includes generating the inner contour feature point along the contour line of the target object.

Further, the distance between adjacent inner contour feature points is the same. .

Further, the generating an outer contour feature point according to the inner contour feature point includes generating an outer contour feature point in a direction of the inner contour feature point away from the target object according to the inner contour feature point.

Further, the generating the outer contour feature point in the direction of the inner contour feature point away from the target object according to the inner contour feature point includes: the first inner contour feature point and The line segment connected by the second inner contour feature point is a vertical line, and the first inner contour feature point and the second inner contour feature point are adjacent inner contour feature points; in the direction of the vertical line away from the target object Take the first point, the length of the line segment between the first point and the first inner contour feature point is a predetermined length, and use the first point as the outer contour feature corresponding to the first inner contour feature point point.

Further, the generating an outer contour feature point in the direction of the inner contour feature point away from the target object according to the inner contour feature point further includes: generating two different outer contour features via the third inner contour feature point Points are the first auxiliary outer contour feature point and the second auxiliary outer contour feature point, where the third inner contour point is the inner contour feature point at the inflection point of the contour; the first auxiliary outer contour feature point and the second outer contour feature The intersection of the line where the point is located and the line where the second auxiliary outer contour feature point and the fourth outer contour feature point are located, wherein the second outer contour feature point is the outer contour feature point corresponding to the second inner contour feature point, so The fourth outer contour feature point is an outer frame contour feature point corresponding to a fourth inner contour feature point, wherein the second inner contour feature point and the fourth inner contour feature point are associated with the third inner contour feature Two inner contour feature points adjacent to the point; use the intersection point as the third outer contour feature point corresponding to the third inner contour feature point.

Further, the distance between the inner contour feature point and the outer contour feature point corresponding to the inner contour feature point is the width of the material.

Further, the filling of the preset material into the area between the inner contour feature point and the outer contour feature point includes: filling the material into two adjacent inner contour feature points and the The filling operation in the area formed by the two adjacent outer contour feature points corresponding to the two adjacent inner contour feature points; repeat the above filling operation until all the inner contour feature points and the outer contour features The areas between the points are filled with the material.

Further, the segmentation of the target image to obtain the outline of the target object includes: acquiring a video; segmenting the video frame image in the video; separating the target object in the video frame image from other objects to obtain The outline of the target object.

Further, before segmenting the target image to obtain the outline of the target object, the method further includes: setting a correspondence between the preset material and the target image.

According to another aspect of the present disclosure, the following technical solutions are also provided:

An image processing device, including:

The contour acquisition module is used to segment the target image to obtain the contour of the target object;

An inner contour feature point generating module, configured to generate an inner contour feature point of the target object according to the contour of the target object;

An outer contour feature point generating module, configured to generate an outer contour feature point according to the inner contour feature point;

The filling module is used to fill the preset material into the area between the inner contour feature point and the outer contour feature point.

Further, the inner contour feature point generating module is configured to generate the inner contour feature point along the contour line of the target object.

Further, the distance between adjacent inner contour feature points is the same.

Further, the outer contour feature point generating module includes an outer contour feature point generating sub-module for generating an outer contour feature point in a direction of the inner contour feature point away from the target object according to the inner contour feature point.

Further, the outer contour feature point generating sub-module is used to make a vertical line through the first inner contour feature point to a line segment connected by the first inner contour feature point and the second inner contour feature point, the first inner An outline feature point and the second inner outline feature point are adjacent inner outline feature points; a first point is taken in the direction of the vertical line away from the target object, the first point and the first inner outline feature point The length of the line segment between the points is a predetermined length, and the first point is used as the outer contour feature point corresponding to the first inner contour feature point.

Further, the outer contour feature point generation sub-module is also used to generate two different outer contour feature points via the third inner contour feature point, which are the first auxiliary outer contour feature point and the second auxiliary outer contour feature, respectively Point, where the third inner contour point is the inner contour feature point at the inflection point of the contour; calculate the line where the first auxiliary outer contour feature point and the second outer contour feature point are located, and the second auxiliary outer contour feature point and the fourth outer contour feature The intersection point of the straight line where the point is located, wherein the second outer contour feature point is the outer contour feature point corresponding to the second inner contour feature point, and the fourth outer contour feature point is the outer contour feature point corresponding to the fourth inner contour feature point A frame outline feature point, wherein the second inner outline feature point and the fourth inner outline feature point are two inner outline feature points adjacent to the third inner outline feature point; The third outer contour feature point corresponding to the third inner contour feature point.

Further, the filling module is configured to fill the material into two adjacent inner contour feature points and two adjacent outer contour feature points corresponding to the two adjacent inner contour feature points The filling operation in the area of the above; repeat the above filling operation until all the areas between the inner contour feature point and the outer contour feature point are filled with the material.

Further, the contour acquisition module is used to acquire video; segment the video frame image in the video; separate the target object in the video frame image from other objects to obtain the contour of the target object.

Further, the image processing device further includes a correspondence relationship setting module, configured to set a correspondence relationship between the preset material and the target image.

According to yet another aspect of the present disclosure, the following technical solutions are also provided:

An electronic device includes: a memory for storing non-transitory computer-readable instructions; and a processor for running the computer-readable instructions so that the processor executes any of the above image processing methods when executed A step of.

A computer-readable storage medium is used to store non-transitory computer-readable instructions. When the non-transitory computer-readable instructions are executed by a computer, the computer is caused to perform the steps described in any of the above methods.

The present disclosure discloses an image processing method, device, and hardware device. Wherein, the image processing method includes: segmenting the target image to obtain the contour of the target object; generating an inner contour feature point of the target object according to the contour of the target object; generating an outer contour feature point according to the inner contour feature point Filling the preset material into the area between the inner contour feature point and the outer contour feature point; In the image processing method of the embodiment of the present disclosure, the target object to be processed can be segmented from the image, and the material can be added to the relevant area of the target object to form a special effect. When modifying the special effect, only the material needs to be modified without re-editing the image again , Improve the efficiency and flexibility of special effects production.

The above description is only an overview of the technical solutions of the present disclosure. In order to understand the technical means of the present disclosure more clearly, it can be implemented in accordance with the content of the specification, and to make the above and other purposes, features and advantages of the present disclosure more obvious and understandable In the following, the preferred embodiments are described in detail, together with the drawings, which are described in detail below.

BRIEF DESCRIPTION

1 is a schematic flowchart of an image processing method according to an embodiment of the present disclosure;

2 is a schematic diagram of a method for generating an outline feature point according to the present disclosure;

3 is a schematic diagram of a material filling method according to the present disclosure;

4 is a schematic diagram of the effect after an image is processed by an image processing method according to an embodiment of the present disclosure;

5 is a schematic structural diagram of an image processing apparatus according to an embodiment of the present disclosure;

6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

detailed description

The following describes the embodiments of the present disclosure through specific specific examples. Those skilled in the art can easily understand other advantages and effects of the present disclosure from the contents disclosed in the present specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, but not all the embodiments. The present disclosure can also be implemented or applied through other different specific embodiments, and various details in this specification can also be based on different viewpoints and applications, and various modifications or changes can be made without departing from the spirit of the present disclosure. It should be noted that the following embodiments and the features in the embodiments can be combined with each other without conflict. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein may be embodied in a wide variety of forms, and any specific structures and / or functions described herein are merely illustrative. Based on the present disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein may be used to implement equipment and / or methods of practice. In addition, other apparatuses and / or functionalities in addition to one or more of the aspects set forth herein may be used to implement this apparatus and / or practice this method.

It should also be noted that the illustrations provided in the following embodiments only illustrate the basic concept of the present disclosure in a schematic manner, and the drawings only show components related to the present disclosure rather than the number, shape, and shape of components in actual implementation. Dimensional drawing, the type, number and proportion of each component can be changed at will during its actual implementation, and its component layout type may also be more complicated.

In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the aspects can be practiced without these specific details.

An embodiment of the present disclosure provides an image processing method. The image processing method provided in this embodiment may be executed by a computing device, which may be implemented as software or a combination of software and hardware. The computing device may be integrated in a server, a terminal device, or the like. As shown in FIG. 1, the image processing method mainly includes the following steps S101 to S104. among them:

Step S101: Segment the target image to obtain the outline of the target object;

In this step, the target image may be any image. In one embodiment, the target image is a picture, where the target image includes a target object, and the target object may be any object. In one embodiment, the target The object is the human body. The target image is segmented, and the objects in the image are segmented and separated from other objects to obtain the outline of the target object. In one embodiment, when the target image is a video, the video needs to be acquired first; the video frame image in the video is segmented; the target object in the video frame image is separated from other objects to obtain the target object ’s profile.

Image segmentation is generally divided into interactive image segmentation and automatic image segmentation. Traditional image processing generally uses interactive image segmentation, which requires human participation in image segmentation. In this disclosure, automatic image segmentation is used, and the following uses human body image segmentation as an example to describe automatic image segmentation.

In general, automatic human image segmentation methods can be divided into the following types: (1) Model-based human image segmentation methods. For this method, the human face is first detected based on the prior knowledge of the human face, and then the torso model is used to find The torso under the human face, then estimate the position of the lower body according to the segmented torso, and finally use the estimated torso and upper leg regions to provide seed points for image segmentation to complete the segmentation of the human body image; (2) based on the hierarchical tree Human body image segmentation method. For this method, the adjacent body parts are first modeled, then the entire human body pose is modeled, and the different body poses are modeled as the sum of nodes on different paths in the hierarchical detection tree, Different layers in the hierarchical detection tree correspond to different models of adjacent human parts, along different paths on the hierarchical detection tree, corresponding to different human postures, are detected down the root node of the tree during detection, and are segmented along different paths Different postures of the human body; (3) based on the independent component analysis of the reference signal, the human body image segmentation method, for this method, the first The human face is detected according to the prior knowledge of the human face, then the torso model is used to find the torso under the human face, and then the reference signal is obtained from the detected torso, and then the torso is highlighted from the image using the independent component analysis method of the reference signal Complete the segmentation of the torso, the segmentation of other body parts is similar, and finally complete the segmentation of the entire human body image; (4) The human body image segmentation method based on the expectation maximization algorithm, for this method, first use the pattern structure model to the human body pose in the image Estimate to obtain the probability map of human posture, and then use the image segmentation method to obtain the final human segmented image based on the probability map. Of course, other human image segmentation methods can also be used, which will not be described in detail in this disclosure, any image segmentation method can be introduced into this disclosure to segment the target object from the target image.

Step S102: Generate an inner contour feature point of the target object according to the contour of the target object;

In this step, an inner contour feature point of the target object is generated according to the contour of the target object obtained in step S101, and the inner contour feature point may be located directly on the contour line of the target object, or maintained at a predetermined distance from the contour line, For example, the inner contour feature point can be kept at a distance of 0.1 cm from the contour line. In one embodiment, the distance between the inner contour feature points is the same, that is to say, the inner contour feature points are evenly distributed with respect to the contour of the target object.

Step S103: generating an outer contour feature point according to the inner contour feature point;

In this step, an outer contour feature point is generated according to the inner contour feature point generated in step S102. In one embodiment, the inner contour feature point is generated in a direction away from the target object according to the inner contour feature point For outer contour feature points, the generating process may be an interpolation process. Taking the target object as a human body for example, the inner contour feature points are located on the contour line of the human body, and for each inner contour feature point, an outer contour feature point corresponding to it is generated outside the human body. In one embodiment, the first inner contour feature point and the second inner contour feature point are perpendicular to a line segment connected by the first inner contour feature point and the second inner contour feature point, and the first inner contour feature point and the second inner contour feature point The contour feature points are adjacent inner contour feature points; the first point is taken in the direction of the vertical line away from the target object, and the length of the line segment between the first point and the first inner contour feature point is a predetermined length , Using the first point as the outer contour feature point corresponding to the first inner contour feature point. After that, the above two steps may be repeated until all the first inner contour points generate corresponding outer contour feature points. Generate two different outer contour feature points via the third inner contour feature point, which are the first auxiliary outer contour feature point and the second auxiliary outer contour feature point, where the third inner contour point is the inner contour feature point at the contour inflection point ; Calculate the intersection of the line where the first auxiliary outer contour feature point and the second outer contour feature point are located and the line where the second auxiliary outer contour feature point and the fourth outer contour feature point are located, where the second outer contour feature point is An outer contour feature point corresponding to a second inner contour feature point, the fourth outer contour feature point is an outer frame contour feature point corresponding to a fourth inner contour feature point, wherein the second inner contour feature point and the The fourth inner contour feature point is two inner contour feature points adjacent to the third inner contour feature point; the intersection point is used as the third outer contour feature point corresponding to the third inner contour feature point.

Refer to FIG. 2 for a specific example of the above embodiment. As shown in FIG. 2, the inner contour feature points include

points

1, 2, 3, 4, 5, and 6, of which points 1, 2, 3, 5, 6 Corresponding to the first inner contour point and the second inner contour point in the above embodiment, point 4 is the contour inflection point of the target object, which corresponds to the third inner contour point in the above embodiment. Take point 2 as an example, make a vertical line to line segment 12 through point 2, and take a point b in the direction of the vertical line away from the target object, and make the length of line segment 1b H, where H is the preset length, for each Each inner contour feature point has two inner contour feature points adjacent to it. For point 2, in addition to point 1 being adjacent to it, there is also point 3 adjacent to it, so do it after point 2 A vertical line, making it perpendicular to the line segment 23, in this embodiment, point 1, point 2 and point 3 are located on the same straight line, so the vertical line of line segment 12 passing through point 2 coincides with the vertical line of line segment 23, The two points b obtained at this time coincide, and it can be determined that the point b is the outer contour feature point corresponding to the point 2, thus repeating the above operation for each point can obtain the inner contour feature points 1, 2, 3, 5, 6 Corresponding outer contour feature points a, b, c, f, g; in this specific example, it also includes a special case, as shown in Figure 2, point 4 is an inflection point, which is located in the corner of the target object contour At this time, since point 4 and its adjacent points 3 and 5, the three points are not on a straight line, so through point 4 to do line segment 34 and line segment 45 respectively Vertical line, the two vertical lines do not coincide, at this time two points d and e will appear, at this time, the line segment cd and line segment fe are extended, the extension line intersects at point h, and the point h is determined as the inner contour feature point 4 Corresponding outer contour feature points.

It should be noted that the above method for generating outer contour feature points is only an example and does not constitute a limitation to the present disclosure. In fact, any method for generating outer contour points based on inner contour points can be used in the present disclosure.

Step S104: Fill the preset material into the area between the inner contour feature point and the outer contour feature point.

In the present disclosure, the preset material may be a color card with a fixed size, and in this step, the material is filled into the area between the inner contour feature point and the outer contour feature point, To form a stroke on the target object. In one embodiment, the filling process is: the material is filled into two adjacent inner contour feature points and two adjacent outer contour feature points corresponding to the two adjacent inner contour feature points In the composed area; repeat the above filling operation until all the areas between the inner contour feature point and the outer contour feature point are filled with the material. Figure 3 shows an example of material filling. In this example, the length of the material is L, and the width is H, that is, the distance between the inner contour feature points is L, and the inner contour feature points and their corresponding The distance between the outer contour feature points is H, and the area 1ab2 is the size of a material, and the preset material just fills it, as shown in the shaded area of the area 1ab2 in FIG. 3. In one embodiment, the length and width attributes of the preset material are obtained in advance, and when the inner contour feature point is generated in step S102, the inner contour feature point is sampled on the contour of the target object using the length of the preset material as the sampling distance In step S103, the outer contour feature points of the inner contour feature points are taken with the width of the preset material. In another embodiment, the distance between the inner contour feature points is not L, which may be n times or 1 / n times of L. At this time, when the material is filled, the material may be stretched or expanded. After filling.

In one embodiment, before segmenting the target image to obtain the outline of the target object, the method further includes: setting a correspondence between the preset material and the target image. In this embodiment, multiple materials may be prepared in advance, corresponding to multiple target images. The multiple target objects may be pictures or video frames of video. When the target image is a video frame of video, multiple The video frame sets the corresponding material to generate different stroke effects for each frame of video. When the video plays, the stroke effect will change as the video plays.

In one embodiment, before segmenting the target image to obtain the outline of the target object, the method further includes: selecting the target object. The target object may be any object that can be segmented from the target image. In this embodiment, the target object may be a human body, various animals such as cats, dogs, plants, buildings, and the like. When different target objects are selected, different object segmentation algorithms are called, and users can flexibly adjust the objects that need to be segmented.

In one embodiment, before segmenting the target image to obtain the outline of the target object, it further includes: selecting the serial number of the target object to be segmented. In one embodiment, there may be multiple target objects in the target image, such as multiple human bodies in the video frame, at this time, the serial number of the target object that needs to be processed can be set in advance, if the serial number is set to 1, the first The segmented human body performs image processing in the present disclosure. If the setting needs to be 0, then the image processing in the present disclosure is performed on all segmented human bodies.

In one embodiment, the display properties of the outline can be set, for example, a certain section of the outline can be set not to be displayed in a certain frame or some frames or a certain section of the outline is displayed randomly, etc., so that the effect of the material flickering appears.

As shown in FIG. 4, it is an example of the effect of the image processing method disclosed in this disclosure after processing an image. In this example, the target object is a human body, and the human body is stroked to highlight the position of the human body in the image .

The present disclosure discloses an image processing method, device, and hardware device. Wherein, the image processing method includes: segmenting the target image to obtain the contour of the target object; generating an inner contour feature point of the target object according to the contour of the target object; generating an outer contour feature point according to the inner contour feature point Filling the preset material into the area between the inner contour feature point and the outer contour feature point; In the image processing method of the embodiment of the present disclosure, the target object to be processed can be segmented from the image, and the material can be added to the relevant area of the target object to form a special effect. When modifying the special effect, only the material needs to be modified without re-editing the image , Improve the efficiency and flexibility of special effects production.

In the above, although the steps in the above method embodiments are described in the above order, those skilled in the art should understand that the steps in the embodiments of the present disclosure are not necessarily performed in the above order, and they can also be reversed, parallel, and cross Other procedures are executed in sequence, and on the basis of the above steps, those skilled in the art can also add other steps. These obvious modifications or equivalent replacements should also be included in the scope of protection of the present disclosure, which will not be repeated here. .

The following is a device embodiment of the present disclosure. The device embodiment of the present disclosure can be used to perform the steps implemented by the method embodiments of the present disclosure. For ease of description, only parts related to the embodiment of the present disclosure are shown. Specific technical details are not disclosed. Please Refer to the method embodiment of the present disclosure.

An embodiment of the present disclosure provides an image processing device. The device may perform the steps described in the above embodiments of the image processing method. As shown in FIG. 5, the device 500 mainly includes a contour acquisition module 501, an inner contour feature point generation module 502, an outer contour feature point generation module 503 and a filling module 504. among them,

The contour acquisition module 501 is used to segment the target image to obtain the contour of the target object;

An inner contour feature point generating module 502, configured to generate an inner contour feature point of the target object according to the contour of the target object;

An outer contour feature point generating module 503, configured to generate an outer contour feature point according to the inner contour feature point;

The filling module 504 is used to fill the preset material into the area between the inner contour feature point and the outer contour feature point.

Further, the inner contour feature point generating module 502 is configured to generate the inner contour feature point along the contour line of the target object, wherein the distance between adjacent inner contour feature points is the same.

Further, the distance between the adjacent inner contour feature points is the length of the material.

Further, the outer contour feature point generation module 503 includes an outer contour feature point generation sub-module for generating an outer contour feature point in a direction of the inner contour feature point away from the target object according to the inner contour feature point.

Further, the outer contour feature point generating sub-module makes a vertical line through the first inner contour feature point to a line segment connected by the first inner contour feature point and the second inner contour feature point, and the first inner contour feature The point and the second inner contour feature point are adjacent inner contour feature points; the first point is taken in the direction of the vertical line away from the target object, the first point and the first inner contour feature point The length of the line segment between is a predetermined length, and the first point is used as the outer contour feature point corresponding to the first inner contour feature point.

Further, the filling module 504 is configured to fill the material to two adjacent inner contour feature points and two adjacent outer contour feature points corresponding to the two adjacent inner contour feature points Filling operation in the composed area; repeating the above filling operation until all areas between the inner contour feature point and the outer contour feature point are filled with the material.

Further, the contour acquisition module 501 is used to acquire a video; segment the video frame image in the video; and separate the target object in the video frame image from other objects to obtain the contour of the target object.

Further, the image processing apparatus 500 further includes a correspondence relationship setting module, which is used to set a correspondence relationship between the preset material and the target image.

The device shown in FIG. 5 can execute the method of the embodiment shown in FIG. For the execution process and technical effect of the technical solution, refer to the description in the embodiment shown in FIG. 1, and details are not described herein again.

Reference is made to FIG. 6 below, which shows a schematic structural diagram of an electronic device 600 suitable for implementing embodiments of the present disclosure. Electronic devices in the embodiments of the present disclosure may include, but are not limited to, such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g. Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers and the like. The electronic device shown in FIG. 6 is only an example, and should not bring any limitation to the functions and use scope of the embodiments of the present disclosure.

As shown in FIG. 6, the electronic device 600 may include a processing device (such as a central processing unit, a graphics processor, etc.) 601, which may be loaded into random access according to a program stored in a read only memory (ROM) 602 or from the storage device 608 The program in the memory (RAM) 603 performs various appropriate operations and processes. In the RAM 603, various programs and data necessary for the operation of the electronic device 600 are also stored. The processing device 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

Generally, the following devices can be connected to the I / O interface 605: include input devices 606 including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc .; An output device 607 such as a vibrator; a storage device 608 including, for example, a magnetic tape, a hard disk, etc .; and a communication device 609. The communication device 609 may allow the electronic device 600 to perform wireless or wired communication with other devices to exchange data. Although FIG. 4 shows an electronic device 600 having various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or provided instead.

In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product that includes a computer program carried on a computer-readable medium, the computer program containing program code for performing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 609, or from the storage device 608, or from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiments of the present disclosure are executed.

It should be noted that the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer diskettes, hard drives, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device. In this disclosure, the computer-readable signal medium may include a data signal that is propagated in baseband or as part of a carrier wave, in which computer-readable program code is carried. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable signal medium may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device . The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: electric wire, optical cable, RF (radio frequency), etc., or any suitable combination of the foregoing.

The computer-readable medium may be included in the electronic device; or it may exist alone without being assembled into the electronic device.

The computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to: segment the target image to obtain the outline of the target object; according to the target object The contour generates an inner contour feature point of the target object; generates an outer contour feature point according to the inner contour feature point; fills a preset material into the area between the inner contour feature point and the outer contour feature point .

The computer program code for performing the operations of the present disclosure can be written in one or more programming languages or a combination thereof. The above programming languages include object-oriented programming languages such as Java, Smalltalk, C ++, and also include conventional Procedural programming language-such as "C" language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as an independent software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In situations involving remote computers, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, through an Internet service provider Internet connection).

The flowchart and block diagrams in the drawings illustrate the possible implementation architecture, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, program segment, or part of code that contains one or more logic functions Executable instructions. 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 can actually be executed in parallel, and sometimes they can also be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented with dedicated hardware-based systems that perform specified functions or operations Or, it can be realized by a combination of dedicated hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented in software or hardware. Among them, the name of the unit does not constitute a limitation on the unit itself under certain circumstances.

The above description is only the preferred embodiment of the present disclosure and the explanation of the applied technical principles. Those skilled in the art should understand that the scope of the disclosure in this disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover the above technical features or without departing from the above disclosed concepts. Other technical solutions formed by arbitrary combinations of equivalent features. For example, the above features and the technical features disclosed in this disclosure (but not limited to) having similar functions are replaced with each other to form a technical solution.

Claims

An image processing method, including:

Segment the target image to get the outline of the target object;

Generating an inner contour feature point of the target object according to the contour of the target object;

Generating an outer contour feature point according to the inner contour feature point;

Fill the preset material into the area between the inner contour feature point and the outer contour feature point.
The image processing method according to claim 1, wherein generating the inner contour feature points of the target object according to the contour of the target object comprises:

The inner contour feature point is generated along the contour line of the target object.
The image processing method according to claim 2, wherein the distances between adjacent inner contour feature points are the same.
The image processing method according to claim 1, wherein generating an outer contour feature point from the inner contour feature point includes:

An outer contour feature point is generated in the direction of the inner contour feature point away from the target object according to the inner contour feature point.
The image processing method according to claim 4, wherein the generating an outer contour feature point in a direction of the inner contour feature point away from the target object according to the inner contour feature point includes:

The first inner contour feature point is perpendicular to a line segment connected by the first inner contour feature point and the second inner contour feature point, the first inner contour feature point and the second inner contour feature point are adjacent Inner contour feature points;

Take a first point in the direction of the vertical line away from the target object, the length of the line segment between the first point and the first inner contour feature point is a predetermined length, and use the first point as the first An outer contour feature point corresponding to an inner contour feature point.
The image processing method according to claim 5, wherein the generating an outer contour feature point in the direction of the inner contour feature point away from the target object according to the inner contour feature point further comprises:

Generate two different outer contour feature points via the third inner contour feature point, which are the first auxiliary outer contour feature point and the second auxiliary outer contour feature point, where the third inner contour point is the inner point at the contour inflection point of the target object Contour feature points;

Calculate the intersection point of the straight line where the first auxiliary outer contour feature point and the second outer outline feature point are located and the straight line where the second auxiliary outer contour feature point and the fourth outer outline feature point are located, wherein An outer contour feature point corresponding to the second inner contour feature point, the fourth outer contour feature point is an outer frame contour feature point corresponding to the fourth inner contour feature point, wherein the second inner contour feature point and the first Four inner contour feature points are two inner contour feature points adjacent to the third inner contour feature point;

The intersection point is used as a third outer contour feature point corresponding to the third inner contour feature point.
The image processing method according to claim 1, wherein the distance between the inner contour feature point and the outer contour feature point corresponding to the inner contour feature point is the width of the material.
The image processing method according to claim 1, wherein the filling of the preset material into the area between the inner contour feature point and the outer contour feature point includes:

A filling operation of filling the material into an area composed of two adjacent inner contour feature points and two adjacent outer contour feature points corresponding to the two adjacent inner contour feature points;

The above filling operation is repeated until all areas between the inner contour feature point and the outer contour feature point are filled with the material.
The image processing method according to claim 1, wherein the segmentation of the target image to obtain the outline of the target object includes:

Get video

Segment the video frame image in the video;

The target object in the video frame image is separated from other objects to obtain the outline of the target object.
The image processing method according to claim 1, wherein before the segmenting the target image to obtain the outline of the target object, further comprising:

Set the correspondence between the preset material and the target image.
An image processing device, including:

The contour acquisition module is used to segment the target image to obtain the contour of the target object;

An inner contour feature point generating module, configured to generate an inner contour feature point of the target object according to the contour of the target object;

An outer contour feature point generating module, configured to generate an outer contour feature point according to the inner contour feature point;

The filling module is used to fill the preset material into the area between the inner contour feature point and the outer contour feature point.
An electronic device, including:

Memory for storing non-transitory computer-readable instructions; and

A processor, configured to execute the computer-readable instructions, so that the processor executes the image processing method according to any one of claims 1-10 when executed.
A computer-readable storage medium for storing non-transitory computer-readable instructions, when the non-transitory computer-readable instructions are executed by a computer, causing the computer to execute any one of claims 1-10 Image processing method.