A method, device, equipment and readable storage medium for assisting blind people to verify

Abstract

The application discloses a method, device and equipment for assisting blind people in verification and a readable storage medium. The method comprises the following steps: acquiring a reference picture and a moving picture to be matched; performing adaptive threshold calculation and binarization processing on the reference picture to generate a binarized reference picture; determining a vacancy area in the binarized reference picture which is matched with the outline of the moving picture through template matching; determining the direction and distance that the moving picture needs to move to the vacancy area in real time; and converting the direction and distance into a voice form for broadcasting. The blind people can control the moving picture to move to the vacancy area according to the direction and distance broadcasted in the application, so as to complete the picture verification and overcome the problem that the blind people cannot normally browse the webpage due to the fact that they cannot pass the picture verification.

Description

Technical Field

[0001] This application relates to the field of assisted identification, and more specifically, to a method, apparatus, device, and readable storage medium for assisting blind people in verification. Background Technology

[0002] With the rapid development of internet technology, CAPTCHA technology is often used to prevent malicious bulk operations and protect account security. Users need to complete the corresponding verification before logging in and querying information. Image verification is a common verification method embedded in corporate websites, apps, and other applications. Users need to recognize the image and perform the required actions before they can use a certain function.

[0003] As attached Figure 1 As shown, users must complete image verification before posting articles or comments in an application. Specifically, they must drag and move image A to the gap in image B, ensuring that image A successfully fills the gap, thus completing the image verification.

[0004] Because these types of CAPTCHAs vary greatly and contain many interfering pixels, blind people cannot pass the image verification using ordinary screen readers for the blind, which creates an obstacle for blind people to browse the web.

[0005] Based on the above situation, providing a solution to assist blind people in verification through images has become an urgent technical problem to be solved. Summary of the Invention

[0006] In view of this, this application provides a method, apparatus, device, and readable storage medium to assist blind people in verification, overcoming the problem that blind people cannot browse web pages normally because they cannot verify images.

[0007] To achieve the above objectives, the following solution is proposed:

[0008] A method for assisting blind people in verification, characterized by comprising:

[0009] Obtain the baseline image and the moving image to be matched, wherein the moving image is obtained by extracting a sub-image from the original verification image, and the baseline image is the remaining part after extracting the sub-image from the original verification image;

[0010] The reference image is subjected to adaptive threshold calculation and binarization processing to generate a binarized reference image;

[0011] The missing regions in the binarized reference image that match the contour of the moving image are determined by template matching;

[0012] The direction and distance that the currently moving image needs to move to the vacant area can be determined in real time.

[0013] The required direction and distance of movement are converted into speech and broadcast to assist blind people in controlling the moving image to the empty area according to the required direction and distance, so as to complete the image verification.

[0014] Optionally, adaptive threshold calculation and binarization processing are performed on the reference image to generate a binarized reference image, including:

[0015] An adaptive threshold calculation is performed on each sub-image that makes up the reference image to obtain a binarization threshold for each sub-image.

[0016] Binarization processing is performed on each sub-image that makes up the reference image based on each binarization threshold of each sub-image;

[0017] A binarized reference image is generated based on each sub-image of the reference image after binarization processing.

[0018] Optionally, the real-time determination of the direction and distance that the moving image needs to move to the vacant area includes:

[0019] Define any point in the currently moving image as the target point;

[0020] Determine the matching point in the missing region that corresponds to the target point;

[0021] Determine the direction and distance that the current target point needs to move to the matching point, and use this as the direction and distance that the current moving image needs to move to the empty area.

[0022] Optionally, obtaining the baseline image and moving image to be matched includes:

[0023] Download the baseline image and the moving image to be matched to your local machine;

[0024] The baseline image and the moving image to be matched are converted into Mat data format.

[0025] Optionally, the moving image is obtained by extracting a sub-image from the original verification image and processing the edges of the extracted sub-image with fixed pixel values;

[0026] Before determining the missing region in the binarized reference image that matches the contour of the moving image through template matching, the method further includes:

[0027] The moving image is binarized based on the fixed pixel values.

[0028] A device for assisting blind people in verification, characterized in that it comprises:

[0029] The acquisition unit is used to acquire a reference image and a moving image to be matched, wherein the moving image is obtained by extracting a sub-image from the original verification image and processing the edges of the extracted sub-image with fixed pixel values, and the reference image is the remaining part after the sub-image in the original verification image is extracted;

[0030] The benchmark processing is used to perform adaptive threshold calculation and binarization on the benchmark image to generate a binarized benchmark image;

[0031] The second processing unit is used to perform binarization processing on the moving image based on the fixed pixel values ​​to generate a binarized moving image;

[0032] A matching unit is used to determine, through template matching, the missing region in the binarized reference image that matches the binarized moving image;

[0033] The determining unit is used to determine in real time the direction and distance that the current binarized moving image needs to move to the empty area that matches the binarized moving image;

[0034] The voice broadcasting unit is used to convert the required direction and distance of movement into voice form and broadcast it to assist blind people in controlling the moving image to move to the empty area that matches the moving image according to the required direction and distance of movement, so as to complete the image verification.

[0035] Optionally, the benchmark processing includes:

[0036] The calculation unit is used to adaptively threshold the calculation to obtain the average pixel value of each sub-image that makes up the baseline image;

[0037] The sub-image processing unit is used to perform binarization processing on each sub-image of the constituent reference image, using each average pixel value as the binarization threshold of each sub-image of the corresponding constituent reference image.

[0038] The generation unit is used to generate a binarized reference image based on each sub-image of the reference image after binarization processing.

[0039] Optionally, the determining unit includes:

[0040] The target point determination unit is used to determine any point in the current binary moving image as a target point;

[0041] A matching point determination unit is used to determine the matching point corresponding to the target point in the empty region that matches the binarized moving image;

[0042] The distance and direction determination unit is used to determine the direction and distance that the current target point needs to move to the matching point, and to determine the direction and distance that the current binary moving image needs to move to the empty area that matches the binary moving image.

[0043] A device to assist blind people in verification, including a memory and a processor;

[0044] The memory is used to store programs;

[0045] The processor is used to execute the program to implement the various steps of the method for assisting blind people in verification as described above.

[0046] A readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method for assisting blind verification.

[0047] As can be seen from the above technical solutions, the method, apparatus, device, and readable storage medium provided in this application for assisting blind people in verification involves acquiring a reference image to be matched and a moving image, performing adaptive threshold calculation and binarization processing on the reference image to generate a binarized reference image, determining the missing area in the binarized reference image that matches the contour of the moving image through template matching, determining in real time the direction and distance that the moving image needs to move to the missing area, and converting the direction and distance to be moved into speech form for broadcast.

[0048] The moving image described in this application is obtained by extracting a sub-image from the original verification image. The reference image is the remaining part after the sub-image from the original verification image has been extracted. Therefore, the outline of the moving image should match the extracted empty area on the reference image. By adaptively thresholding and binarizing the reference image, a black and white image that can display the empty area can be generated. Using template matching, the empty area that matches the outline of the moving image can be determined. The direction and distance that the moving image needs to move to the empty area are the directions and distances that a blind person needs to control. The blind person can control the moving image to move to the empty area according to the direction and distance announced by voice to complete the image verification, overcoming the problem that blind people cannot browse web pages normally because they cannot pass the image verification. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0050] Figure 1 This is a schematic diagram of an image verification image, which serves as the background technology of this application.

[0051] Figure 2 This application discloses a flowchart of a method for assisting blind people in verification.

[0052] Figure 3 This is a schematic diagram of an original verification image as an example of this application;

[0053] Figure 4 A schematic diagram of a reference image as an example of this application;

[0054] Figure 5 This is a schematic diagram illustrating a moving image as an example of this application;

[0055] Figure 6 This is a schematic diagram of a binarized reference image as an example of this application;

[0056] Figure 7 This is a schematic diagram of a binarized image verification image as an example of this application;

[0057] Figure 8 This is a schematic diagram illustrating the target point and matching point in this application.

[0058] Figure 9 This is a structural block diagram of a device for assisting blind people in verification, as disclosed in this application;

[0059] Figure 10 This is a hardware structure block diagram of a device for assisting blind people in verification, as disclosed in this application. Detailed Implementation

[0060] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0061] The following section introduces the solution proposed in this application. The technical solution is as follows, and details are provided below.

[0062] Figure 1This is a flowchart of a method for assisting blind people in verification, as disclosed in an embodiment of this application. Figure 1 As shown, the method may include:

[0063] Step S1: Obtain the baseline image and the moving image to be matched.

[0064] Specifically, in general, the common method for generating images for image verification is as follows: randomly select a sub-image from the original verification image and extract it; then overlay the moving image onto the base image at any position except for the empty area after extraction; finally combine the base image and the moving image to obtain the image used for image verification.

[0065] First, a base image and a moving image need to be obtained for matching. The moving image is obtained by extracting a sub-image from the original verification image. The base image is the remaining part after the sub-image from the original verification image has been extracted. The user needs to move the moving image to the corresponding empty area in the base image to complete the image verification.

[0066] For example, Figure 3 To constitute Figure 1 The original verification image shown can be used to extract a sub-image from the original verification image to obtain the moving image. In this example, the extracted moving image is... Figure 5 Simultaneously, the remaining portion of the sub-image extracted from the original verification image is used as the reference image. In this example, the reference image of the extracted remaining portion is... Figure 4 Baseline image Figure 4 The image contains a cutout area of ​​the moving image.

[0067] It is understood that the types of moving images and reference images include, but are not limited to, the types in the examples above. The example images above are merely one optional type for ease of understanding.

[0068] Step S2: Perform adaptive threshold calculation and binarization on the reference image to generate a binarized reference image.

[0069] Specifically, adaptive threshold calculation of the reference image determines a suitable binarization threshold for processing the reference image. Simultaneously, the binarization threshold obtained through adaptive threshold calculation can display the missing areas in the reference image after binarization processing. After binarization, areas in the reference image with pixel values ​​greater than the binarization threshold appear black, and areas with pixel values ​​less than the binarization threshold appear white; that is, after binarization processing, a black and white binarized reference image is obtained. Figure 6 The image shown is the baseline image after binarization, where the missing areas are clearly visible. After generating the binarized baseline image, restoring it to the image verification process will yield... Figure 7 The image shown is the verification result after restoration.

[0070] Step S3: Determine the missing regions in the binarized reference image that match the contour of the moving image through template matching.

[0071] Specifically, in practical applications, after binarizing the reference image, the area with a pixel value of 0 is taken as the empty area. Then, there will generally be multiple empty areas in the binarized reference image. The shapes of the empty areas are different. The empty area that matches the contour of the moving image can be determined by the template matching algorithm. This area is the target position that needs to be manually controlled to move the moving image to.

[0072] like Figure 7 As shown, there are multiple missing regions in the binarized reference image. Through the template matching algorithm, the missing region that matches the contour of the moving image A can be determined as region B. That is, in the image verification, it is necessary to manually control the moving image A to move to region B.

[0073] Step S4: Determine in real time the direction and distance that the currently moving image needs to move to the empty area.

[0074] Specifically, since the position of the moving image can be any location within the empty area of ​​the base image (excluding the extracted sub-image), the direction of the empty area to which the moving image needs to be moved relative to the moving image can vary. The empty area and the moving image can be on the same horizontal line, or... Figure 7 As shown, the empty area and the moving image are not on the same horizontal line. Using the moving image as a reference, the direction and distance the moving image needs to move to the empty area are determined in real time. In other words, for the user to complete image verification, they need to control the direction and distance the moving image moves.

[0075] Step S5: Convert the required direction and distance of movement into voice format and broadcast it.

[0076] Specifically, after determining the direction and distance that the current moving image needs to move to the empty area, the direction and distance that the current moving image needs to move to the empty area are converted into speech and broadcast to assist the blind person in controlling the moving image to move to the empty area according to the required direction and distance, so as to complete the image verification.

[0077] Understandably, this method can be continuously implemented during the process of a blind person controlling the movement of a moving image. It continuously analyzes and determines the direction and distance of the empty area relative to the moving image based on the current position of the moving image, and continuously provides voice prompts on the direction and distance to be moved until the moving image is controlled to move to the empty area, thus completing the image verification.

[0078] As can be seen from the above technical solutions, the method for assisting blind people in verification provided in this application involves acquiring a reference image to be matched and a moving image, performing adaptive threshold calculation and binarization processing on the reference image to generate a binarized reference image, determining the missing area in the binarized reference image that matches the contour of the moving image through template matching, determining in real time the direction and distance that the moving image needs to move to the missing area, and converting the direction and distance to be moved into speech form for broadcast.

[0079] The moving image described in this application is obtained by extracting a sub-image from the original verification image. The reference image is the remaining part after the sub-image from the original verification image has been extracted. Therefore, the outline of the moving image should match the extracted empty area on the reference image. By adaptively thresholding and binarizing the reference image, a black and white image that can display the empty area can be generated. Using template matching, the empty area that matches the outline of the moving image can be determined. The direction and distance that the moving image needs to move to the empty area are the directions and distances that a blind person needs to control. The blind person can control the moving image to move to the empty area according to the direction and distance announced by voice to complete the image verification, overcoming the problem that blind people cannot browse web pages normally because they cannot pass the image verification.

[0080] Optionally, step S1, the process of obtaining the baseline image and the moving image to be matched, may specifically include:

[0081] Step S11: Download the baseline image and the moving image to be matched to the local machine.

[0082] Step S12: Convert the baseline image and the moving image to be matched into Mat data format.

[0083] Specifically, to obtain the baseline image and moving image to be matched, it is first necessary to download the baseline image and moving image to be matched to the local machine and process the baseline image and moving image, specifically by converting the baseline image and moving image into Mat data format.

[0084] In some embodiments of this application, the process of step S2, performing adaptive threshold calculation and binarization on the reference image to generate a binarized reference image, is described, and may specifically include:

[0085] Step S21: Divide the reference image into multiple sub-images.

[0086] Step S22: Perform adaptive threshold calculation on each sub-image to obtain the binarization threshold of each sub-image.

[0087] Specifically, adaptive threshold calculation is based on image features and automatically calculates the binarization threshold. The specific logic is to perform histogram statistics on each sub-image that makes up the reference image and calculate the average pixel value of each sub-image. This average pixel value is the binarization threshold of each sub-image.

[0088] Step S23: Perform binarization processing on each sub-image according to the binarization threshold of each sub-image.

[0089] Specifically, based on the binarization threshold of each sub-image, each sub-image constituting the reference image is binarized to generate a black and white sub-image after binarization.

[0090] Step S24: Generate a binarized reference image based on each sub-image after binarization processing.

[0091] Specifically, all binarized sub-images are restored back to the base image to obtain the binarized base image.

[0092] In some embodiments of this application, the process of step S4, determining in real time the direction and distance that the currently moving image needs to move to the vacant area, is described, and may specifically include:

[0093] Step S41: Determine any point in the moving image as the target point.

[0094] Specifically, a point is randomly selected from the moving image as the target point. This target point can be a point on the edge of the moving image or a point inside the moving image. For example... Figure 8 As shown, a point a on the edge of the moving image A was determined as the target point.

[0095] Step S42: Determine the matching point in the missing region that corresponds to the target point.

[0096] Specifically, after determining the target point, a matching point is identified within the empty area corresponding to the moving image. The target point and the matching point have a unique correspondence. For example... Figure 8 As shown, the matching point corresponding to target point a in the empty region B is point b.

[0097] Step S43: Determine the direction and distance that the current target point needs to move to the matching point, and use this as the direction and distance that the current moving image needs to move to the empty area.

[0098] Specifically, since the moving image matches the empty area, the direction and distance between each point on the moving image and its matching point in the empty area are the same, and this direction and distance are also what the user needs to control the direction and distance of the moving image's movement. Therefore, by determining the direction and distance of the matching point relative to the target point, the direction and distance of the empty area relative to the moving image can be determined, i.e., the direction and distance the target point needs to move to the matching point, and this direction and distance are used as the direction and distance the moving image needs to move to the empty area.

[0099] like Figure 8 In the case shown, after determining the target point a and the matching point b, the direction and distance of point b relative to point a can be further determined. This direction and distance are the direction and distance that the moving image A needs to move to the empty area B.

[0100] In some embodiments of this application, considering practical situations, in order to make the moving image more prominent and facilitate users to observe and confirm the position of the moving image, fixed pixel value processing is often performed on the edge of the moving image. That is, the moving image is obtained by extracting a sub-image from the original verification image and performing fixed pixel value processing on the edge of the extracted sub-image.

[0101] In the above case, before step S3, which determines the missing region in the binarized reference image that matches the contour of the moving image through template matching, the following may also be included:

[0102] Step S6: Binarize the moving image based on the fixed pixel values.

[0103] Specifically, the edges of the moving image are processed with fixed pixel values, meaning the pixel values ​​of its edge regions are uniformly set to fixed pixel values. After binarizing the moving image based on these fixed pixel values, the edge shape of the moving image will be displayed in black, making the outline of the moving image clearer and facilitating more accurate template matching in the subsequent process.

[0104] The apparatus for assisting blind people in verification provided in the embodiments of this application will be described below. The apparatus for assisting blind people in verification described below can be referred to in correspondence with the method for assisting blind people in verification described above.

[0105] See Figure 9 , Figure 9 This is a schematic diagram of a device for assisting blind people in verification, as disclosed in an embodiment of this application.

[0106] like Figure 9 As shown, the device may include:

[0107] The acquisition unit 110 is used to acquire a base image and a moving image to be matched, wherein the moving image is obtained by extracting a sub-image from the original verification image, and the base image is the remaining part after extracting the sub-image from the original verification image;

[0108] The reference processing unit 120 is used to perform adaptive threshold calculation and binarization processing on the reference image to generate a binarized reference image;

[0109] Template matching unit 130 is used to determine the missing region in the binarized reference image that matches the contour of the moving image through template matching;

[0110] The determining unit 140 is used to determine in real time the direction and distance that the currently moving image needs to move to the vacant area;

[0111] The voice broadcasting unit 150 is used to convert the direction and distance to be moved into voice form and broadcast it to assist the blind person in controlling the moving image to move to the empty area according to the direction and distance to be moved, so as to complete the image verification.

[0112] As can be seen from the above technical solution, the device for assisting blind verification provided in this application obtains a reference image to be matched and a moving image, performs adaptive threshold calculation and binarization processing on the reference image to generate a binarized reference image, determines the missing area in the binarized reference image that matches the contour of the moving image through template matching, determines in real time the direction and distance that the moving image needs to move to the missing area, and converts the direction and distance to be moved into voice form for broadcast.

[0113] The moving image described in this application is obtained by extracting a sub-image from the original verification image. The reference image is the remaining part after the sub-image from the original verification image has been extracted. Therefore, the outline of the moving image should match the extracted empty area on the reference image. By adaptively thresholding and binarizing the reference image, a black and white image that can display the empty area can be generated. Using template matching, the empty area that matches the outline of the moving image can be determined. The direction and distance that the moving image needs to move to the empty area are the directions and distances that a blind person needs to control. The blind person can control the moving image to move to the empty area according to the direction and distance announced by voice to complete the image verification, overcoming the problem that blind people cannot browse web pages normally because they cannot pass the image verification.

[0114] Optionally, the aforementioned reference processing unit may include:

[0115] A segmentation unit is used to segment the reference image into multiple sub-images;

[0116] The calculation unit is used to perform adaptive threshold calculation on each sub-image to obtain the binarization threshold of each sub-image.

[0117] The sub-image processing unit is used to perform binarization processing on each sub-image according to the binarization threshold of each sub-image;

[0118] The generation unit is used to generate a binary reference image based on each sub-image after binarization processing.

[0119] Optionally, the aforementioned determining unit may include:

[0120] The target point determination unit is used to determine any point in the current binary moving image as a target point;

[0121] A matching point determination unit is used to determine the matching point corresponding to the target point in the empty region that matches the binarized moving image;

[0122] The distance and direction determination unit is used to determine the direction and distance that the current target point needs to move to the matching point, and to determine the direction and distance that the current binary moving image needs to move to the empty area that matches the binary moving image.

[0123] Optionally, the aforementioned acquisition unit may include:

[0124] The download unit is used to download the baseline image and the moving image to be matched to the local machine;

[0125] The format conversion unit is used to convert the reference image and the moving image to be matched into Mat data format.

[0126] Optionally, the moving image can be obtained by extracting a sub-image from the original verification image and processing the edges of the extracted sub-image with fixed pixel values;

[0127] The aforementioned device for assisting blind people in verification may further include:

[0128] The motion processing unit is configured to perform binarization processing on the moving image based on the fixed pixel values ​​before determining the missing region in the binarized reference image that matches the contour of the moving image through template matching, so as to preserve the contour of the moving image.

[0129] The device for assisting blind people in verification provided in this application can be applied to devices that assist blind people in verification, such as PC terminals, cloud platforms, servers, and server clusters. Optionally, Figure 10 The hardware structure block diagram of the device for assisting blind people in verification is shown. (Refer to...) Figure 10The hardware structure of a device for assisting blind people in verification may include: at least one processor 1, at least one communication interface 2, at least one memory 3, and at least one communication bus 4;

[0130] In this embodiment of the application, the number of processor 1, communication interface 2, memory 3, and communication bus 4 is at least one, and processor 1, communication interface 2, and memory 3 communicate with each other through communication bus 4;

[0131] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

[0132] Memory 3 may include high-speed RAM, and may also include non-volatile memory, such as at least one disk storage device;

[0133] The memory stores a program, which the processor can call. The program is used for:

[0134] Obtain the baseline image and the moving image to be matched, wherein the moving image is obtained by extracting a sub-image from the original verification image, and the baseline image is the remaining part after extracting the sub-image from the original verification image;

[0135] The reference image is subjected to adaptive threshold calculation and binarization processing to generate a binarized reference image;

[0136] The missing regions in the binarized reference image that match the contour of the moving image are determined by template matching;

[0137] The direction and distance that the currently moving image needs to move to the vacant area can be determined in real time.

[0138] The required direction and distance of movement are converted into speech and broadcast to assist blind people in controlling the moving image to the empty area according to the required direction and distance, so as to complete the image verification.

[0139] Optionally, the refined and extended functions of the program can be referred to the above description.

[0140] This application embodiment also provides a readable storage medium that can store a program suitable for execution by a processor, the program being used for:

[0141] Obtain the baseline image and the moving image to be matched, wherein the moving image is obtained by extracting a sub-image from the original verification image, and the baseline image is the remaining part after extracting the sub-image from the original verification image;

[0142] The reference image is subjected to adaptive threshold calculation and binarization processing to generate a binarized reference image;

[0143] The missing regions in the binarized reference image that match the contour of the moving image are determined by template matching;

[0144] The direction and distance that the currently moving image needs to move to the vacant area can be determined in real time.

[0145] The required direction and distance of movement are converted into speech and broadcast to assist blind people in controlling the moving image to the empty area according to the required direction and distance, so as to complete the image verification.

[0146] Optionally, the refined and extended functions of the program can be referred to the above description.

[0147] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0148] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0149] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of assisting blind people in authentication, characterized by, The method comprises the following steps: obtaining a reference picture and a moving picture to be matched, wherein the moving picture is obtained by cutting out one sub-picture in an original verification picture and performing fixed pixel value processing on the edges of the cut-out sub-picture, and the reference picture is the remaining part after cutting out the sub-picture in the original verification picture; performing adaptive threshold calculation and binarization processing on the reference picture to generate a binarized reference picture; performing binarization processing on the moving picture according to the fixed pixel value to retain the outline of the moving picture; determining a vacancy area in the binarized reference picture that matches the outline of the moving picture through template matching; determining the direction and distance that the current moving picture needs to move to the vacancy area in real time; converting the direction and distance that the moving picture needs to move into a voice form for broadcasting, so as to assist the blind person to control the moving picture to move to the vacancy area according to the direction and distance that the moving picture needs to move, and complete the picture verification.

2. The method of claim 1, wherein, The adaptive threshold calculation and binarization processing on the reference picture to generate a binarized reference picture comprises the following steps: segmenting the reference picture into multiple sub-pictures; performing adaptive threshold calculation on each sub-picture to obtain a binarization threshold value of each sub-picture; performing binarization processing on each sub-picture according to the binarization threshold value of each sub-picture; generating a binarized reference picture according to each sub-picture after binarization processing.

3. The method of claim 1, wherein, The real-time determination of the direction and distance that the current moving picture needs to move to the vacancy area comprises the following steps: determining any point in the current moving picture as a target point; determining a matching point in the vacancy area corresponding to the target point; determining the direction and distance that the current target point needs to move to the matching point as the direction and distance that the current moving picture needs to move to the vacancy area.

4. The method of claim 1, wherein, The obtaining of the reference picture and the moving picture to be matched comprises the following steps: downloading the reference picture and the moving picture to be matched to the local; converting the reference picture and the moving picture to be matched into Mat data format.

5. An apparatus for assisting blind authentication, characterized by, The method comprises the following steps: an obtaining unit is configured to obtain a reference picture and a moving picture to be matched, wherein the moving picture is obtained by cutting out one sub-picture in an original verification picture and performing fixed pixel value processing on the edges of the cut-out sub-picture, and the reference picture is the remaining part after cutting out the sub-picture in the original verification picture; a reference processing unit is configured to perform adaptive threshold calculation and binarization processing on the reference picture to generate a binarized reference picture, and perform binarization processing on the moving picture according to the fixed pixel value to retain the outline of the moving picture; a template matching unit is configured to determine a vacancy area in the binarized reference picture that matches the outline of the moving picture through template matching; a determining unit is configured to determine the direction and distance that the current moving picture needs to move to the vacancy area in real time; The voice broadcast unit is configured to convert the direction and distance of movement into voice and broadcast the direction and distance of movement to assist the blind person to control the moving picture to move to the empty area according to the direction and distance of movement, so as to complete the picture verification.

6. The apparatus of claim 5, wherein, The reference processing comprises: The dividing unit is configured to divide the reference picture into a plurality of sub-pictures; The calculating unit is configured to perform adaptive threshold calculation on each sub-picture to obtain a binarization threshold of each sub-picture; The sub-picture processing unit is configured to perform binarization processing on each sub-picture according to the binarization threshold of each sub-picture; The generating unit is configured to generate a binarization reference picture according to each sub-picture after the binarization processing.

7. The apparatus of claim 5, wherein, The determining unit comprises: The target point determining unit is configured to determine any point in the current binarization moving picture as a target point; The matching point determining unit is configured to determine a matching point corresponding to the target point in the empty area matched with the binarization moving picture; The direction and distance determining unit is configured to determine the direction and distance of movement of the current target point to the matching point, and take the direction and distance of movement as the direction and distance of movement of the current binarization moving picture to the empty area matched with the binarization moving picture.

8. An apparatus for assisting blind authentication, characterized by, The computer program comprises a memory and a processor; The memory is configured to store a program; The processor is configured to execute the program to implement each step of the method for assisting the blind person to verify.

9. A readable storage medium, having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement each step of the method for assisting the blind person to verify.

Images