Image verification processing method and device

Abstract

The application provides an image verification processing method and device, relates to the technical field of image processing, and can be applied to the financial field or other technical fields. The method comprises the following steps: acquiring a first picture containing object contour information and a second picture containing artistic information; if it is determined that the number of the second picture is 1, performing image processing on the first picture and the second picture, and acquiring at least two noise pictures in the image processing process; simultaneously displaying the at least two noise pictures, the first picture and a verification code image obtained through image processing in a first verification interface in a random order; in response to a sorting action on the pictures in the first verification interface, comparing the arrangement order of the sorting action with a preset arrangement order, and if it is determined that the comparison result is consistent, determining that the image verification is passed. The device executes the above method. The method and device provided in the embodiment of the application can guarantee information security.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and more specifically to an image verification processing method and apparatus. Background Technology

[0002] In today's rapidly developing internet age, image verification via CAPTCHA is frequently required to protect information security.

[0003] There are two main types of existing image CAPTCHAs. One common type consists of randomly generated numbers, English letters, or Chinese characters. These CAPTCHAs prevent machine recognition by adding interference lines, noise, rotating characters, or altering their adhesion. Users identify the characters in the image and then input their own for verification. Many advanced recognition models exist to crack these character-based CAPTCHAs, leading to security vulnerabilities on online platforms. The other type of image CAPTCHA can also contain objects, such as fire hydrants, zebra crossings, or cars. Multiple images are displayed, and users click on all images containing the specific object to complete the verification. For object-based CAPTCHAs, recognition models often use features like color and patterns for identification, and well-trained models can crack these types of CAPTCHAs. Summary of the Invention

[0004] To address the problems in the prior art, embodiments of the present invention provide an image verification processing method and apparatus, which can at least partially solve the problems existing in the prior art.

[0005] On one hand, the present invention proposes an image verification processing method, comprising:

[0006] Acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern.

[0007] If the number of the second image is determined to be 1, then image processing is performed on the first image and the second image, and at least two noisy images are obtained during the image processing process;

[0008] The at least two noisy images, the first image, and the CAPTCHA image obtained from image processing are simultaneously displayed on the first verification interface in a random order.

[0009] In response to the sorting action of the image in the first verification interface, the sorting order is compared with the preset sorting order. If the order comparison result is consistent, the image verification is confirmed to be successful.

[0010] The image verification processing method further includes:

[0011] The timer is started when the step of simultaneously displaying the at least two noise images, the first image, and the verification code image obtained from image processing in the first verification interface in a random order is completed, and the number of times the sorting processing action is executed is monitored.

[0012] If it is determined that the number of executions exceeds a preset execution threshold within a preset time period, an operation error message is generated.

[0013] The image verification processing method further includes:

[0014] At the moment when the step of simultaneously displaying the at least two noisy images, the first image, and the CAPTCHA image obtained from image processing in a random order on the first verification interface is completed, an instruction message prompting the user to sort the images is generated.

[0015] The image verification processing method further includes:

[0016] If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images;

[0017] Randomly select one target second image from each second image, and display the target second image and at least two verification code images in the second verification interface;

[0018] In response to the selection and processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively;

[0019] If the selected CAPTCHA image has the highest similarity comparison result value, then the image verification is considered successful.

[0020] The image verification processing method further includes:

[0021] If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images;

[0022] Randomly select one target CAPTCHA image from all CAPTCHA images, and display the target CAPTCHA image and at least two second images in the third verification interface;

[0023] In response to the selection processing action of the at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image respectively;

[0024] If the selected second image has the highest similarity comparison result value, then the image verification is considered successful.

[0025] The image verification processing method further includes:

[0026] If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images;

[0027] Randomly select one target second image from each second image, and display the target second image and at least two verification code images in the second verification interface;

[0028] In response to the selection and processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively;

[0029] If the selected verification code image is determined to have the highest similarity comparison result value, then a target verification code image is randomly selected from all the verification code images, and the target verification code image and at least two second images are displayed in the third verification interface.

[0030] In response to the selection processing action of the at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image respectively;

[0031] If the selected second image has the highest similarity comparison result value, then the image verification is considered successful.

[0032] The image verification processing method further includes:

[0033] If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images;

[0034] Randomly select one target CAPTCHA image from all CAPTCHA images, and display the target CAPTCHA image and at least two second images in the third verification interface;

[0035] In response to the selection processing action of the at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image respectively;

[0036] If the selected second image is determined to have the highest similarity comparison result value, then a target second image is randomly selected from each second image, and the target second image and at least two verification code images are displayed in the second verification interface.

[0037] In response to the selection and processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively;

[0038] If the selected CAPTCHA image has the highest similarity comparison result value, then the image verification is considered successful.

[0039] On one hand, the present invention proposes an image verification processing apparatus, comprising:

[0040] An acquisition unit is used to acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern.

[0041] The determining unit is configured to, if the number of the second image is determined to be 1, perform image processing on the first image and the second image, and obtain at least two noisy images during the image processing;

[0042] The display unit is used to simultaneously display the at least two noise images, the first image, and the verification code image obtained by image processing in the first verification interface in a random order.

[0043] The verification unit is used to respond to the sorting action of the image in the first verification interface, and compare the sorting order with the preset sorting order. If the order comparison result is consistent, the image verification is determined to be successful.

[0044] In another aspect, embodiments of the present invention provide an electronic device, including: a processor, a memory, and a bus, wherein,

[0045] The processor and the memory communicate with each other via the bus;

[0046] The memory stores program instructions that can be executed by the processor, and the processor can execute the following methods by calling the program instructions:

[0047] Acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern.

[0048] If the number of the second image is determined to be 1, then image processing is performed on the first image and the second image, and at least two noisy images are obtained during the image processing process;

[0049] The at least two noisy images, the first image, and the CAPTCHA image obtained from image processing are simultaneously displayed on the first verification interface in a random order.

[0050] In response to the sorting action of the image in the first verification interface, the sorting order is compared with the preset sorting order. If the order comparison result is consistent, the image verification is confirmed to be successful.

[0051] This invention provides a non-transitory computer-readable storage medium, comprising:

[0052] The non-transitory computer-readable storage medium stores computer instructions that cause the computer to perform the following methods:

[0053] Acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern.

[0054] If the number of the second image is determined to be 1, then image processing is performed on the first image and the second image, and at least two noisy images are obtained during the image processing process;

[0055] The at least two noisy images, the first image, and the CAPTCHA image obtained from image processing are simultaneously displayed on the first verification interface in a random order.

[0056] In response to the sorting action of the image in the first verification interface, the sorting order is compared with the preset sorting order. If the order comparison result is consistent, the image verification is confirmed to be successful.

[0057] The image verification processing method and apparatus provided in this invention acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern; if the number of the second image is determined to be 1, image processing is performed on the first image and the second image, and at least two noise images are acquired during the image processing; the at least two noise images, the first image, and the verification code image obtained from the image processing are simultaneously displayed in a first verification interface in a random order; in response to the sorting action of the images in the first verification interface, the sorting order is compared with a preset sorting order, and if the order comparison result is consistent, the image verification is determined to be successful, thus ensuring information security. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of the present invention 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 some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0059] Figure 1 This is a schematic flowchart of an image verification processing method provided in an embodiment of the present invention.

[0060] Figure 2 This is a schematic diagram of the structure of an image verification processing device provided in an embodiment of the present invention.

[0061] Figure 3 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments and descriptions of the present invention are used to explain the present invention, but are not intended to limit the present invention. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other.

[0063] Figure 1 This is a flowchart illustrating an image verification processing method according to an embodiment of the present invention, as shown below. Figure 1 As shown, the image verification processing method provided in this embodiment of the invention includes:

[0064] Step S1: Obtain a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern.

[0065] Step S2: If the number of the second image is determined to be 1, then perform image processing on the first image and the second image, and obtain at least two noisy images during the image processing.

[0066] Step S3: Display the at least two noisy images, the first image, and the verification code image obtained from image processing simultaneously in the first verification interface in a random order.

[0067] Step S4: In response to the sorting action of the image in the first verification interface, compare the sorting order with the preset sorting order. If the order comparison result is consistent, the image verification is confirmed to be successful.

[0068] In step S1 above, the device acquires a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern. The device can be a computer device that performs the method, for example, it may include a server. It should be noted that the acquisition and analysis of data involved in this embodiment of the invention are authorized by the user. The object can be any object with a solid shape, such as fruit, equipment, and tools, and the corresponding object outline information includes the shape of the fruit, the outline of the equipment, and the outline of the tool, etc. In the field of image processing technology, the image that provides outline information for the final verification code image is denoted as the content image, and the image that provides color and / or pattern information is denoted as the refer image. That is, the first image is the content image and the second image is the refer image.

[0069] In step S2 above, if the device determines that the number of the second image is 1, it performs image processing on the first image and the second image, and obtains at least two noisy images during the image processing. The image processing model VGG19 can be used for image processing.

[0070] In step S3 above, the device simultaneously displays the at least two noise images, the first image, and the CAPTCHA image obtained from image processing on the first verification interface in a random order. Taking two noise images as an example, the first verification interface displays four images from left to right: two noise images, the first image, and the CAPTCHA image. The order of the four images is shuffled, and the user needs to identify the process of color and pattern feature changes in the images. That is, the order in which the color and pattern features gradually approach the second image is the preset arrangement order, namely, the first image, noise image1 (which is not close to the second image relative to noise image2), noise image2 (which is close to the second image relative to noise image1), and the CAPTCHA image.

[0071] The first verification interface displays at least two noisy images, the first image, and a verification code image obtained through image processing.

[0072] It should be noted that, in order to guide users to perform the correct sorting operation, at the moment when the step of simultaneously displaying the at least two noisy images, the first image and the CAPTCHA image obtained from image processing in the first verification interface in a random order is completed, an operation instruction message prompting the user to sort the images can be generated.

[0073] The above instructions guide the user to drag the images in the preset order. Users can judge the order based on their senses, noting how colors and patterns gradually approach the second image. To complete the image dragging and sorting, the user needs to select the image, drag it, and release the mouse at the appropriate location.

[0074] To prevent machine programs from using brute force to drag and sort images, a timer can be started at the moment when the step of simultaneously displaying the at least two noisy images, the first image, and the CAPTCHA image obtained from image processing in a random order on the first verification interface is completed, and the number of times the sorting processing action is executed can be monitored.

[0075] If the number of executions exceeds a preset threshold within a preset time period, an operation error message is generated. The preset time period and the preset execution threshold can be set independently according to actual conditions. If an operation error message is generated, it indicates that a machine program is using an exhaustive method to drag the image.

[0076] In step S4 above, the device responds to the image sorting action in the first verification interface by comparing the sorting order with a preset sorting order. If the sorting comparison result is consistent, the image verification is confirmed to be successful. If the sorting order executed by the user is completely consistent with the first image, noise image1, noise image2, and verification code image, the sorting comparison result is confirmed to be consistent, and the image verification is confirmed to be successful.

[0077] If the order in which the user arranges the images is not exactly the same as the first image, noise image1, noise image2, and CAPTCHA image, the user can be prompted to rearrange them.

[0078] The image verification processing method provided in this embodiment of the invention acquires a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern; if the number of the second image is determined to be 1, image processing is performed on the first image and the second image, and at least two noise images are acquired during the image processing; the at least two noise images, the first image, and the verification code image obtained from the image processing are simultaneously displayed in a first verification interface in a random order; in response to the sorting action of the images in the first verification interface, the sorting order is compared with a preset sorting order, and if the order comparison result is consistent, the image verification is determined to be successful, thus ensuring information security.

[0079] Furthermore, the image verification processing method further includes:

[0080] The timing is started when the step of simultaneously displaying the at least two noise images, the first image, and the CAPTCHA image obtained from image processing in a random order on the first verification interface is completed, and the number of times the sorting processing action is executed is monitored; the above description is provided and will not be repeated here.

[0081] If it is determined that the number of executions exceeds a preset execution threshold within a preset time period, an operation error message will be generated. Please refer to the above explanation; further details are omitted.

[0082] The image verification processing method provided in this embodiment of the invention can further ensure information security.

[0083] Furthermore, the image verification processing method further includes:

[0084] At the moment when the step of simultaneously displaying the at least two noisy images, the first image, and the CAPTCHA image obtained from image processing in a random order on the first verification interface is completed, an instruction message prompting the user to sort the images is generated. This can be referred to the above description and will not be repeated here.

[0085] The image verification processing method provided in this embodiment of the invention facilitates sorting operations for users.

[0086] Furthermore, the image verification processing method further includes:

[0087] If it is determined that the number of the second images is greater than 1, then the first image and each of the second images are processed to obtain a number of verification code images equal to the number of the second images; taking the number of second images as 2 as an example, the two second images are denoted as r1 and r2 respectively, and the obtained verification code images are denoted as c1 and c2 respectively.

[0088] Randomly select one target second image from each of the second images, and display the target second image and at least two verification code images in the second verification interface; select r1 as the target second image, and display r1, c1 and c2 in the second verification interface.

[0089] The second verification interface displays a target second image and at least two verification code images.

[0090] In response to the selection of at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image. The user can be prompted to select the image most similar to r1 from c1 and c2. If the user selects c1, a similarity comparison is performed between r1 and c1, and between r1 and c2. The similarity comparison method can be a conventional image similarity comparison method.

[0091] If the selected CAPTCHA image has the highest similarity comparison result value, the image verification is confirmed to be successful. If the similarity comparison result between r1 and c1 is greater than the similarity comparison result between r1 and c2, it means that the user's selection of c1 is correct, and the image verification is confirmed to be successful.

[0092] If the similarity comparison result between r1 and c1 is less than the similarity comparison result between r1 and c2, it means that the user's selection of c1 is incorrect, and the image verification fails.

[0093] The image verification processing method provided in this embodiment of the invention can further ensure information security.

[0094] Furthermore, the image verification processing method further includes:

[0095] If it is determined that the number of the second images is greater than 1, then the first image and each of the second images are processed to obtain a number of verification code images equal to the number of the second images; taking the number of second images as 2 as an example, the two second images are denoted as r1 and r2 respectively, and the obtained verification code images are denoted as c1 and c2 respectively.

[0096] Randomly select one target CAPTCHA image from among the CAPTCHA images, and display the target CAPTCHA image and at least two second images on the third verification interface; select c1 as the target CAPTCHA image, and display c1, r1 and r2 on the third verification interface.

[0097] The third verification interface displays a target verification code image and at least two secondary images.

[0098] In response to the selection of at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image. The user can be prompted to select the image most similar to c1 from r1 and r2. If the user selects r1, a similarity comparison is performed between r1 and c1, and between r2 and c1. The similarity comparison method can be a conventional image similarity comparison method.

[0099] If the selected second image has the highest similarity comparison result value, the image verification is considered successful. If the similarity comparison result between r1 and c1 is greater than that between r2 and c1, it indicates that the user's selection of r1 is correct, and the image verification is considered successful.

[0100] If the similarity comparison results for r1 and c1 are less than those for r2 and c1, it indicates that the user's selection of r1 is incorrect, and the image verification fails.

[0101] The image verification processing method provided in this embodiment of the invention can further ensure information security.

[0102] Furthermore, the image verification processing method further includes:

[0103] If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images;

[0104] Randomly select one target second image from each second image, and display the target second image and at least two verification code images in the second verification interface;

[0105] In response to the selection and processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively;

[0106] If the selected verification code image is determined to have the highest similarity comparison result value, then a target verification code image is randomly selected from each verification code image, and the target verification code image and at least two second images are displayed in the third verification interface.

[0107] In response to the selection processing action of the at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image respectively;

[0108] If the selected second image has the highest similarity comparison result value, the image verification is considered successful. This means the image verification steps can be combined: first, image verification is performed on the target second image in the second verification interface, and then image verification is performed on the target CAPTCHA image in the third verification interface.

[0109] The image verification processing method provided in this embodiment of the invention can further ensure information security.

[0110] Furthermore, the image verification processing method further includes:

[0111] If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images;

[0112] Randomly select one target CAPTCHA image from all CAPTCHA images, and display the target CAPTCHA image and at least two second images in the third verification interface;

[0113] In response to the selection processing action of the at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image respectively;

[0114] If the selected second image is determined to have the highest similarity comparison result value, then a target second image is randomly selected from each second image, and the target second image and at least two verification code images are displayed in the second verification interface.

[0115] In response to the selection and processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively;

[0116] If the selected CAPTCHA image has the highest similarity comparison result value, then the image verification is successful. This means the image verification steps can be combined: first, image verification is performed on the target CAPTCHA image in the third verification interface, and then image verification is performed on the target second image in the second verification interface.

[0117] The image verification processing method provided in this embodiment of the invention can further ensure information security.

[0118] Image verification processing methods also include:

[0119] Acquire multiple first images containing object outline information and one second image containing artistic information;

[0120] Each of the first and second images is processed to obtain a number of verification code images equal to the number of the first images;

[0121] The system responds to the user's selection of a verification code image from the verification code images based on text prompts, and compares the selected verification code image with the object corresponding to the text prompts; the text prompts include the name of the object that guides the user to select.

[0122] If the comparison results are consistent, the image verification is deemed successful. If the comparison results are inconsistent, the first and second images are updated to re-execute the image verification process.

[0123] It should be noted that, to prevent the machine from automatically recognizing the images, the speed of the selected CAPTCHA image can be monitored. If the monitored speed is determined to be greater than a preset speed threshold, the first and second images are updated to re-execute the image verification process. The preset speed threshold can be set independently according to actual conditions.

[0124] The embodiments of the present invention can use VGG19 for image processing. VGG19 is described as follows:

[0125] VGG19 is a convolutional neural network commonly used for classification problems. VGG19 has 19 weight layers, divided into 16 convolutional layers (5 blocks, each containing multiple structurally identical convolutional layers, all of which undergo maxpooling after passing through the block), and 3 fully connected layers. Given a 224×224×3 RGB image as input, the first block performs two convolutions with 64 [3×3] kernels each, followed by a ReLU activation function after each convolution. The second block performs two convolutions with 128 [3×3] kernels each, the third block performs four convolutions with 256 [3×3] kernels each, the fourth block performs four convolutions with 512 [3×3] kernels each, and the fifth block performs four convolutions with 512 [3×3] kernels each. Finally, it passes through three fully connected layers with 4096, 4096, and 1000 nodes respectively.

[0126] The image processing model of this invention uses 16 convolutional layers of VGG19 instead of the last three fully connected layers. This is because fully connected layers act as classifiers in convolutional neural networks, and this invention does not address classification issues. Furthermore, the parameters of fully connected layers can account for about 80% of the total network parameters, and removing them simplifies the model considerably.

[0127] The workflow of the image processing model is described below:

[0128] 1. The image providing the contour information for the final CAPTCHA image is called the content image, and the image providing the color and pattern information is called the refer image. Both images are used for feature extraction via VGG19. Shallower convolutional layers extract detailed features, while deeper convolutional layers summarize the overall features. The outputs of the refer images in blocks 1 to 5 are used as detail references, and the outputs of the content images in blocks 4 and 5 are used as overall references.

[0129] 2. Generate a noise image 0 randomly based on the content image.

[0130] 3. Input noise image 0 into VGG19 and save its output in blocks 1 to 5 respectively.

[0131] 4. Following the block order (specifically, the convolutional layers within a block) in VGG19, calculate the content loss for noise image 0 and content image at this layer, as well as the referential loss for noise image 0 and referential image at this layer. Based on the content loss and referential loss, the total loss can be obtained.

[0132] 5. In the direction of the total loss gradient descent, noise image 1 is generated from noise image 0.

[0133] 6. Using noise image 1 as the new input, repeat steps 3, 4, and 5 until the iteration termination condition is met.

[0134] 7. After multiple iterations, the output noisy images become very similar. An iteration termination condition can be added using the SSIM (Structural Similarity) between adjacent images. The iteration will terminate when SSIM > 0.995.

[0135] 8. Use the generated noisy image as the final CAPTCHA image.

[0136] The loss function is explained as follows:

[0137] (1) The formula for calculating the content loss of layer l is:

[0138]

[0139] Represents content image. P represents a noise image. l F represents the output of the content image at layer l. l This represents the output of the noise image at layer l. This represents the output of the i-th convolutional kernel in layer l at position j.

[0140] (2) The matrix formed by the inner product of k vectors α1, α2, ..., αk is called the Gram matrix of the k vectors α1, α2, ..., αk, as follows:

[0141]

[0142] The Gram matrix, composed of Nl features generated from the output of layer l, reflects the correlation between pairs of features, and the diagonal elements of the Gram matrix also reflect the quantity of each feature in the image. To measure the style difference between the noise image and the refer image, it is only necessary to compare their Gram matrices.

[0143] The formula for calculating the refer loss of layer l is:

[0144]

[0145] The formula for calculating the total refer loss is:

[0146]

[0147] Represents referrer image. Represents a noise image, A l G represents the Gram matrix of the output of the refer image at layer l. l This represents the Gram matrix of the noise image output at layer l. Let the l-th layer have Nl convolutional kernels, producing Nl features, with feature size Ml. ω l It is a weighting factor for the contribution of each layer to the total refer loss.

[0148] (3) In summary, the formula for calculating total loss is:

[0149]

[0150] Where α and β are the weighting factors of content and style in image reconstruction, respectively, and satisfy:

[0151] α+β=1.

[0152] It should be noted that the image verification processing method provided in this embodiment of the invention can be used in the financial field, or in any technical field other than the financial field. This embodiment of the invention does not limit the application field of the image verification processing method.

[0153] Figure 2 This is a schematic diagram of the structure of an image verification processing device provided in an embodiment of the present invention, as shown below. Figure 2 As shown, the image verification processing apparatus provided in this embodiment of the invention includes an acquisition unit 201, a determination unit 202, a display unit 203, and a verification unit 204, wherein:

[0154] The acquisition unit 201 is used to acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern; the determination unit 202 is used to perform image processing on the first image and the second image if the number of the second image is determined to be 1, and to acquire at least two noise images during the image processing process; the display unit 203 is used to simultaneously display the at least two noise images, the first image and the verification code image obtained from the image processing in a random order on the first verification interface; the verification unit 204 is used to respond to the sorting action of the images in the first verification interface, compare the sorting action order with the preset sorting order, and if the order comparison result is consistent, determine that the image verification is passed.

[0155] Specifically, the acquisition unit 201 in the device is used to acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern; the determination unit 202 is used to perform image processing on the first image and the second image if the number of the second image is determined to be 1, and to acquire at least two noise images during the image processing; the display unit 203 is used to simultaneously display the at least two noise images, the first image, and the verification code image obtained from the image processing in a random order on the first verification interface; the verification unit 204 is used to respond to the sorting action of the images in the first verification interface, and to compare the sorting order with the preset sorting order. If the order comparison result is consistent, the image verification is determined to be successful.

[0156] The image verification processing apparatus provided in this embodiment of the invention acquires a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern; if the number of the second image is determined to be 1, image processing is performed on the first image and the second image, and at least two noise images are acquired during the image processing; the at least two noise images, the first image, and the verification code image obtained from the image processing are simultaneously displayed in a first verification interface in a random order; in response to the sorting action of the images in the first verification interface, the sorting order is compared with a preset sorting order, and if the order comparison result is consistent, the image verification is determined to be successful, thus ensuring information security.

[0157] Furthermore, the image verification processing device is also used for:

[0158] The timer is started when the step of simultaneously displaying the at least two noise images, the first image, and the verification code image obtained from image processing in the first verification interface in a random order is completed, and the number of times the sorting processing action is executed is monitored.

[0159] If it is determined that the number of executions exceeds a preset execution threshold within a preset time period, an operation error message is generated.

[0160] The image verification processing device provided in this embodiment of the invention further ensures information security.

[0161] Furthermore, the image verification processing device is also used for:

[0162] At the moment when the step of simultaneously displaying the at least two noisy images, the first image, and the CAPTCHA image obtained from image processing in a random order on the first verification interface is completed, an instruction message prompting the user to sort the images is generated.

[0163] The image verification processing device provided in this embodiment of the invention facilitates sorting operations for users.

[0164] Furthermore, the image verification processing device is also used for:

[0165] If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images;

[0166] Randomly select one target second image from each second image, and display the target second image and at least two verification code images in the second verification interface;

[0167] In response to the selection and processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively;

[0168] If the selected CAPTCHA image has the highest similarity comparison result value, then the image verification is considered successful.

[0169] The image verification processing device provided in this embodiment of the invention further ensures information security.

[0170] Furthermore, the image verification processing device is also used for:

[0171] If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images;

[0172] Randomly select one target CAPTCHA image from all CAPTCHA images, and display the target CAPTCHA image and at least two second images in the third verification interface;

[0173] In response to the selection processing action of the at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image respectively;

[0174] If the selected second image has the highest similarity comparison result value, then the image verification is considered successful.

[0175] The image verification processing device provided in this embodiment of the invention further ensures information security.

[0176] Furthermore, the image verification processing device is also used for:

[0177] If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images;

[0178] Randomly select one target second image from each second image, and display the target second image and at least two verification code images in the second verification interface;

[0179] In response to the selection and processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively;

[0180] If the selected verification code image is determined to have the highest similarity comparison result value, then a target verification code image is randomly selected from each verification code image, and the target verification code image and at least two second images are displayed in the third verification interface.

[0181] In response to the selection processing action of the at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image respectively;

[0182] If the selected second image has the highest similarity comparison result value, then the image verification is considered successful.

[0183] The image verification processing device provided in this embodiment of the invention further ensures information security.

[0184] Furthermore, the image verification processing device is also used for:

[0185] If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images;

[0186] Randomly select one target CAPTCHA image from all CAPTCHA images, and display the target CAPTCHA image and at least two second images in the third verification interface;

[0187] In response to the selection processing action of the at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image respectively;

[0188] If the selected second image is determined to have the highest similarity comparison result value, then a target second image is randomly selected from each second image, and the target second image and at least two verification code images are displayed in the second verification interface.

[0189] In response to the selection and processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively;

[0190] If the selected CAPTCHA image has the highest similarity comparison result value, then the image verification is considered successful.

[0191] The image verification processing device provided in this embodiment of the invention further ensures information security.

[0192] The embodiments of the image verification processing apparatus provided in this invention can be used to execute the processing flow of the above-described method embodiments. Its functions will not be repeated here, but can be referred to the detailed description of the above-described method embodiments.

[0193] Figure 3 This is a schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as... Figure 3 As shown, the electronic device includes: a processor 301, a memory 302, and a bus 303;

[0194] The processor 301 and the memory 302 communicate with each other via the bus 303.

[0195] The processor 301 is used to call program instructions in the memory 302 to execute the methods provided in the above-described method embodiments, including, for example:

[0196] Acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern.

[0197] If the number of the second image is determined to be 1, then image processing is performed on the first image and the second image, and at least two noisy images are obtained during the image processing process;

[0198] The at least two noisy images, the first image, and the CAPTCHA image obtained from image processing are simultaneously displayed on the first verification interface in a random order.

[0199] In response to the sorting action of the image in the first verification interface, the sorting order is compared with the preset sorting order. If the order comparison result is consistent, the image verification is confirmed to be successful.

[0200] This embodiment discloses a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, and when the program instructions are executed by a computer, the computer can perform the methods provided in the above-described method embodiments, such as:

[0201] Acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern.

[0202] If the number of the second image is determined to be 1, then image processing is performed on the first image and the second image, and at least two noisy images are obtained during the image processing process;

[0203] The at least two noisy images, the first image, and the CAPTCHA image obtained from image processing are simultaneously displayed on the first verification interface in a random order.

[0204] In response to the sorting action of the image in the first verification interface, the sorting order is compared with the preset sorting order. If the order comparison result is consistent, the image verification is confirmed to be successful.

[0205] This embodiment provides a computer-readable storage medium storing a computer program that causes the computer to execute the methods provided in the above-described method embodiments, including, for example:

[0206] Acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern.

[0207] If the number of the second image is determined to be 1, then image processing is performed on the first image and the second image, and at least two noisy images are obtained during the image processing process;

[0208] The at least two noisy images, the first image, and the CAPTCHA image obtained from image processing are simultaneously displayed on the first verification interface in a random order.

[0209] In response to the sorting action of the image in the first verification interface, the sorting order is compared with the preset sorting order. If the order comparison result is consistent, the image verification is confirmed to be successful.

[0210] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0211] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0212] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0213] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0214] In the description of this specification, the references to terms such as "an embodiment," "a specific embodiment," "some embodiments," "for example," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0215] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An image verification processing method, characterized in that, include: Acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern. If the number of the second image is determined to be 1, then image processing is performed on the first image and the second image, and at least two noisy images are obtained during the image processing process; the at least two noisy images, the first image, and the verification code image obtained from the image processing are simultaneously displayed in the first verification interface in a random order; in response to the sorting action of the images in the first verification interface, the sorting order is compared with the preset sorting order, and if the order comparison result is consistent, then the image verification is determined to be successful; If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images; a target second image is randomly selected from each of the second images, and the target second image and at least two verification code images are displayed in the second verification interface; in response to the selection processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively; If the selected CAPTCHA image has the highest similarity comparison result value, then the image verification is considered successful.

2. The image verification processing method according to claim 1, characterized in that, The image verification processing method further includes: The timer is started when the step of simultaneously displaying the at least two noise images, the first image, and the verification code image obtained from image processing in the first verification interface in a random order is completed, and the number of times the sorting processing action is executed is monitored. If it is determined that the number of executions exceeds a preset execution threshold within a preset time period, an operation error message is generated.

3. The image verification processing method according to claim 1, characterized in that, The image verification processing method further includes: At the moment when the step of simultaneously displaying the at least two noisy images, the first image, and the CAPTCHA image obtained from image processing in a random order on the first verification interface is completed, an instruction message prompting the user to sort the images is generated.

4. The image verification processing method according to any one of claims 1 to 3, characterized in that, The image verification processing method further includes: If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images; Randomly select one target CAPTCHA image from all CAPTCHA images, and display the target CAPTCHA image and at least two second images in the third verification interface; In response to the selection of at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image. If the selected second image has the highest similarity comparison result value, then the image verification is considered successful.

5. The image verification processing method according to any one of claims 1 to 3, characterized in that, The image verification processing method further includes: If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images; Randomly select one target second image from each second image, and display the target second image and at least two verification code images in the second verification interface; In response to the selection and processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively; If the selected verification code image is determined to have the highest similarity comparison result value, then a target verification code image is randomly selected from each verification code image, and the target verification code image and at least two second images are displayed in the third verification interface. In response to the selection of at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image. If the selected second image has the highest similarity comparison result value, then the image verification is considered successful.

6. The image verification processing method according to any one of claims 1 to 3, characterized in that, The image verification processing method further includes: If it is determined that the number of the second images is greater than 1, then image processing is performed on the first image and each of the second images to obtain a number of verification code images equal to the number of the second images; Randomly select one target CAPTCHA image from all CAPTCHA images, and display the target CAPTCHA image and at least two second images in the third verification interface; In response to the selection of at least two second images in the third verification interface, a similarity comparison is performed between the at least two second images and the target verification code image. If the selected second image is determined to have the highest similarity comparison result value, then a target second image is randomly selected from each second image, and the target second image and at least two verification code images are displayed in the second verification interface. In response to the selection and processing action of the at least two verification code images in the second verification interface, a similarity comparison is performed between the at least two verification code images and the target second image respectively; If the selected CAPTCHA image has the highest similarity comparison result value, then the image verification is considered successful.

7. An image verification processing device, characterized in that, include: An acquisition unit is used to acquire a first image containing object outline information and a second image containing artistic information; the artistic information includes color and / or pattern. The determining unit is configured to, if the number of the second image is determined to be 1, perform image processing on the first image and the second image, and obtain at least two noisy images during the image processing; The display unit is used to simultaneously display the at least two noise images, the first image, and the verification code image obtained by image processing in the first verification interface in a random order. The verification unit is used to respond to the sorting action of the image in the first verification interface, and compare the sorting order with the preset sorting order. If the order comparison result is consistent, the image verification is determined to be successful. The determining unit is further configured to, if the number of the second images is determined to be greater than 1, perform image processing on the first image and each of the second images respectively to obtain a number of verification code images equal to the number of the second images; the display unit is further configured to, randomly select a target second image from each of the second images, and display the target second image and at least two verification code images in the second verification interface; The verification unit is also configured to respond to the selection processing action of the at least two verification code images in the second verification interface, and to perform similarity comparison between the at least two verification code images and the target second image respectively; If the selected CAPTCHA image has the highest similarity comparison result value, then the image verification is considered successful.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images