Image detection method and device, equipment, storage medium and product

Abstract

The invention discloses an image detection method and device, equipment, a storage medium and a product, and relates to the technical field of image detection, and the image detection method comprises the steps: determining the image detection number of a detection person according to historical detection information; distributing a to-be-detected image to the detection person based on the image detection number, and obtaining a detection result fed back by the detection person based on the to-be-detected image; and performing iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds, and obtaining an image detection result. Since the to-be-detected image is allocated to the detector according to the historical detection information and then the image detection is performed, and the image detection result is generated when the number of detection rounds reaches the preset number of detection rounds, compared with an existing mode of sequentially distributing the images for detection according to the table sequence of the detector, the detection efficiency is improved; according to the method, the image detection efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the field of image detection technology, and in particular to image detection methods, devices, equipment, storage media and products. Background Art

[0002] In the scenario of digital human (also known as digital intelligent human) intelligent customer service or business assistant, the appearance of digital human can significantly improve the sense of warmth in interaction with users. Behind the sense of warmth is the high cost of producing digital human. Currently, there are mainly 2D digital human and 3D digital human on the market. Taking 2D digital human as an example, the fastest is generally 4 to 6 weeks, and the minimum cost of a digital human is 250,000. The production cost and cycle of 3D digital human are more and longer. With the rapid development of text-generated image and image-generated image technology, generative AI can generate images such as human actions and expressions. Therefore, the production of digital human has been accelerated and the cost has been reduced. Only one real person image is needed to use generative AI to complete the generation of digital human actions and expressions corresponding to the real person. However, generative action, expression and other images need to be manually detected to determine the applicability. At present, it is distributed manually, which is highly arbitrary and has poor quality control. Therefore, how to improve the efficiency of image detection has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The main purpose of this application is to provide an image detection method, device, equipment, storage medium and product, aiming to solve the technical problem of low efficiency of existing image detection.

[0004] To achieve the above objectives, the present application proposes an image detection method, which includes:

[0005] Determine the number of images to be tested for a person based on historical test information;

[0006] Allocating images to be detected to the detector based on the number of image detections, and obtaining detection results fed back by the detector based on the images to be detected;

[0007] Iterative detection is performed based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain an image detection result.

[0008] Optionally, the step of determining the number of images of the detected person according to the historical detection information includes:

[0009] Determine the historical test results of each tester based on the historical test information;

[0010] Determining the testing quality and testing efficiency of the tester according to the historical testing results;

[0011] The number of images to be detected of the detected person is determined based on the detection quality, the detection efficiency and the number of images to be detected.

[0012] Optionally, the detection person information, the image to be detected and the detection result in the image detection method are all stored on a blockchain, the blockchain includes a main chain and a two-dimensional chain group, the detection person information, the image to be detected and the address of the two-dimensional chain group are stored on the main chain, the detection result is stored on the two-dimensional chain group, and the two-dimensional chain group stores the detection results of the detection person on each image to be detected through a one-way linked list.

[0013] Optionally, after the step of performing iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain the image detection result, the step further includes:

[0014] Traversing the two-dimensional chain group to determine the current chain list traversed;

[0015] The first non-empty element in the current linked list is used as the head element of the current linked list, and subsequent non-empty elements are sequentially mounted behind the head element, and the empty elements in the current linked list are deleted;

[0016] Return to the step of traversing the two-dimensional chain group until the traversal of the two-dimensional chain group is completed.

[0017] Optionally, before the step of performing iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds and obtaining the image detection result, the step further includes:

[0018] Obtaining information on the number of images to be detected and a preset detection quantity threshold;

[0019] Determine the range of the number of testing rounds according to the quantity information, the preset detection quantity threshold and the number of testers;

[0020] A preset number of detection rounds is determined based on the range of detection rounds.

[0021] Optionally, the step of performing iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain the image detection result includes:

[0022] Determine whether the current number of detection rounds reaches the preset number of detection rounds;

[0023] If the current number of detection rounds does not reach the preset number of detection rounds, the detection result is used as historical detection information, and the process returns to the step of determining the number of images of the detected person to be detected based on the historical detection information until the number of detection rounds reaches the preset number of detection rounds.

[0024] In addition, to achieve the above-mentioned purpose, the present application also proposes an image detection device, which includes:

[0025] A determination module, used to determine the number of images of the detected person according to historical detection information;

[0026] A detection module, used to allocate images to be detected to the detector based on the number of image detections, and obtain detection results fed back by the detector based on the images to be detected;

[0027] The iterative detection module is used to perform iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain an image detection result.

[0028] In addition, to achieve the above-mentioned purpose, the present application also proposes an image detection device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the image detection method described above.

[0029] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the image detection method described above are implemented.

[0030] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the image detection method described above are implemented.

[0031] The present application determines the number of images to be detected for the person to be detected based on historical detection information; based on the number of image detections, the image to be detected is assigned to the person to be detected, and the detection result fed back by the person to be detected based on the image to be detected is obtained; based on the detection result, iterative detection is performed until the number of detection rounds reaches a preset number of detection rounds, and the image detection result is obtained. Since the present application assigns images to be detected to the person to be detected based on historical detection information and then performs image detection, and generates image detection results when the number of detection rounds reaches a preset number of detection rounds, compared to the existing method of distributing images for detection in sequence according to the table order of the person to be detected, the above method of the present application can improve the efficiency of image detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0033] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0034] Figure 1 A schematic diagram of a process flow provided for the first embodiment of the image detection method of the present application;

[0035] Figure 2 A schematic diagram of a storage structure provided for the second embodiment of the image detection method of the present application;

[0036] Figure 3 A schematic diagram of a flow chart provided for the second embodiment of the image detection method of the present application;

[0037] Figure 4 This is a schematic diagram of the module structure of the image detection device according to an embodiment of the present application;

[0038] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the image detection method in the embodiment of the present application.

[0039] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0040] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0041] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0042] The main solution of the embodiment of the present application is: determine the number of images to be detected for the tester based on historical detection information; assign images to be detected to the tester based on the number of image detections, and obtain the detection results fed back by the tester based on the images to be detected; perform iterative detection based on the detection results until the number of detection rounds reaches a preset number of detection rounds, and obtain image detection results. Since the present application assigns images to be detected to the tester based on historical detection information and then performs image detection, and generates image detection results when the number of detection rounds reaches a preset number of detection rounds, compared to the existing method of distributing images for detection in sequence according to the table order of the tester, the above method of the present application can improve the efficiency of image detection.

[0043] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, an image detection device, etc. The following takes the image detection device as an example to illustrate this embodiment and the following embodiments.

[0044] Based on this, the present application embodiment provides an image detection method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the image detection method of the present application.

[0045] In this embodiment, the image detection method includes steps S10 to S30:

[0046] Step S10, determining the number of images of the detected person according to the historical detection information;

[0047] It should be noted that the historical detection information may include the detection result information of the image to be detected by the detector in the previous round or historical detection, such as whether the detection result is that the image passes or fails, the number of images detected, and the corresponding detection time. The detector may be a user who detects the image to be detected or a computer node with the function of detecting images. The number of image detections may be the number of images to be detected assigned to the detector in this round of detection.

[0048] Step S20, allocating images to be detected to the detector based on the number of images detected, and obtaining detection results fed back by the detector based on the images to be detected;

[0049] It should be noted that the allocation of images to be detected to the detector based on the number of image detections may be to select the number of images to be detected from all the images to be detected and send them to the detector, so that the detector performs the detection and feeds back the detection result, which includes information such as whether the image to be detected is qualified, the number of images detected by the detector and the corresponding detection time. 1 may be used to indicate that the image to be detected is qualified, that is, the detection passes, and 0 may be used to indicate that the image to be detected is unqualified, that is, the detection fails.

[0050] Step S30, performing iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain an image detection result.

[0051] It should be noted that the iterative detection based on the detection results can be that when the number of detection rounds does not reach the preset number of detection rounds, the detection quality and detection efficiency of each detection person are determined according to the detection results, and the images to be detected are re-assigned to each detection person according to the detection quality and the detection efficiency for the next round of image detection to obtain the detection results until the number of detection rounds reaches the preset number of detection rounds. The preset number of detection rounds can be the number of detection rounds pre-set according to the empirical value, or the number of detection rounds generated randomly. The detection quality and detection efficiency of each detection person determined according to the detection results can be determined according to the detection results The variance of the detection result of the current detection person and the average detection result of other detection people is used as the detection quality of the current detection person. The number of images detected by the current detection person and the detection time when the number of images is detected is determined, and the detection efficiency of the current detection person is the number of detected images / the detection time when the number of images is detected. When the number of detection rounds reaches the preset number of detection rounds, the image detection result can be the average value of the detection results of each round. For example, the detection results of image 1 in each round are 1, 0, 1, 0, 1, 1, respectively, and the average value is 0.66. After rounding, the image detection result of image 1 is passed. In each round, the same image can be assigned to multiple inspectors for inspection at the same time. In the same round, the inspection results of the same image may be multiple. The inspection result of the inspector with the highest inspection quality can be used as the basis, or the average value of each inspector can be used as the basis. The settings can be customized according to the specific usage scenario, and this embodiment is not limited here.

[0052] Further, in this embodiment, the step of determining the preset number of detection rounds may include: obtaining quantity information of images to be detected and a preset detection quantity threshold;

[0053] Determine the range of the number of testing rounds according to the quantity information, the preset detection quantity threshold and the number of testers;

[0054] A preset number of detection rounds is determined based on the range of detection rounds.

[0055] It should be noted that the preset detection quantity threshold may include the upper and lower limits of the detection images of each detection person, such as the minimum number of detections per detection person per round is K1, and the maximum number of detections per detection person per round is K2. The detection round number range is determined based on the quantity information, the preset detection quantity threshold, and the number of detection persons, and the detection round number range can be determined based on the following formula:

[0056]

[0057] Among them, m is used to represent the total number of images to be detected, and n is used to represent the number of detected people.

[0058] Determining the preset number of detection rounds based on the range of detection rounds may be randomly selecting an integer value within the range of detection rounds to obtain the preset number of detection rounds.

[0059] Further, in order to improve the image detection efficiency, the step S30 may include: determining whether the current number of detection rounds reaches a preset number of detection rounds;

[0060] If the current number of detection rounds does not reach the preset number of detection rounds, the detection result is used as historical detection information, and the process returns to the step of determining the number of images of the detected person to be detected based on the historical detection information until the number of detection rounds reaches the preset number of detection rounds.

[0061] It should be noted that each time a test is completed, the counter for calculating the number of test rounds is incremented by 1, and then compared with the preset number of test rounds. When the current number of test rounds does not reach the preset number of test rounds, the test result is used as historical test information, and the step of determining the number of images to be tested based on the historical test information is returned until the number of test rounds reaches the preset number of test rounds. When the current number of test rounds reaches the preset number of test rounds, the test results of each image in each round are obtained, and then the average of each image in each round of test results is calculated, and the result is rounded off as the final test result of the image.

[0062] Furthermore, in order to prevent data from being tampered with and improve the efficiency of image detection, the detection person information, the image to be detected and the detection result in the image detection method are all stored on the blockchain. The blockchain includes a main chain and a two-dimensional chain group. The detection person information, the image to be detected and the address of the two-dimensional chain group are stored on the main chain, and the detection result is stored on the two-dimensional chain group. The two-dimensional chain group stores the detection results of the detection person on each image to be detected through a one-way linked list.

[0063] It should be noted that when implementing the image detection method based on blockchain, it is necessary to first upload the information of the detector, the smart contract, the image to be detected and other information to the chain. The smart contract is an algorithm for calculating the number of detection rounds and the number of images detected by each detector in each round. The detector information includes the number of detectors, identification and other information. The image to be detected includes the total number of images to be detected, grouping information, image identification and other information.

[0064] It should be noted that the data stored in the blockchain includes information about the person being tested, smart contracts, image information such as the facial expressions and movements of the generated digital human to be tested, and information such as the test results of the person testing the image. The storage mode of the blockchain is the main chain + two-dimensional chain group storage mode. The main chain is built around the information of a person, a smart contract or a group of graphs, and the address of a two-dimensional chain group is mounted. This storage mode helps to quickly recycle data storage space when some information (such as image detection data of a person) is not needed, saving storage space and economic costs. For details, please refer to Figure 2 , Figure 2 A schematic diagram of a storage structure provided in the second embodiment of the image detection method of the present application; Figure 2 As shown, the information of people, smart contracts or a group of graphs is encapsulated in the main chain. The storage mode is as follows: Each block of the main chain consists of four types of blocks, and the data structure of the block body contains two key designs, as shown below:

[0065] 1. Content: This part stores the content on the chain.

[0066] 2. address: This part is used for the address of the two-dimensional chain group, so as to realize the main chain block mounting the two-dimensional chain group.

[0067] The core contents of content are the creation block content, the detection person information, the smart contract content, and the generated image group. In this embodiment, the smart contract and the detection person information are stored in a separate block. The main details of the storage of the generated image group stored in this embodiment are as follows:

[0068] 1. Different from the traditional mode of one image per block, in order to save storage space and facilitate subsequent recycling, a group of uploaded images (i.e., images of generative digital human expressions and actions, referred to as generative image groups here, indicating that the images are a group rather than a single image) are packaged into one block. It should be pointed out that if the number of images on the chain is too large or the volume is too large to exceed the limit of one block, the group of images per block described in this embodiment also includes splitting the group of images on the chain into multiple groups and encapsulating them into independent blocks respectively, and then sequentially mounting them on the main chain.

[0069] 2. In addition to the core information such as people, smart contracts or a group of graphs, the main chain block also carries a two-dimensional chain group address. In this embodiment, the definition of the two-dimensional chain group is:

[0070] The two-dimensional chain group is composed of multiple (the number of "individuals" is the same as the number of detected persons) one-way linked lists from backward elements to forward elements, and each linked list is connected up and down through the first element of the linked list, that is, the first element of the second linked list points to the first element of the first linked list, and so on for other linked lists. (In this embodiment, the length of the linked list is the same as the number of images on the chain of the group) This two-dimensional linked list has the advantage of a clear mapping relationship between the rows and the vertical axes in the two-dimensional array, and is also convenient for data space recovery after the detection of the chain image is completed.

[0071] Different from conventional linked list elements, the core fields of the data structure of the "element" in the two-dimensional linked list described in this embodiment are as follows:

[0072] 1. Sequence number of int type: in this embodiment, it represents the sequence number of the detected generated digital human expression action image; from 1 to m, where m is the number of images mounted on the current main chain block.

[0073] 2. Long type number: This number is composed of two groups of numbers. The first group of numbers indicates the milliseconds corresponding to the detection time of sequence number j by detector i. The second group of numbers indicates the detection result. 0 indicates no, i.e., failure; 1 indicates yes, i.e., pass.

[0074] It should be noted that the main scenario of the main chain + two-dimensional chain group in the blockchain involves data chaining and data recovery. The chaining steps of the generative digital human expression and action image (i.e., the image to be detected) include: packing and compressing the generative digital human expression and action image, calling the chaining interface to chain the data; go to step 2; step 2: after receiving the chaining request in step 1, a certain node A of the blockchain decompresses the data and identifies whether the chained data is an image and is in the agreed format. If not, it returns the content of the data format error of the interface caller so that the image can be uploaded in the agreed format in step 1; if it meets the regulations, the compressed package received locally is packed into the block, and the block is published to the blockchain. After consensus by the consensus algorithm, each node of the blockchain saves a copy of the compressed package chained data. Go to step 3; step 3: each node performs the following actions locally: create a main chain block; create a two-dimensional chain group according to the number of images to be detected and the number of detected people in the chained data; mount the address of the two-dimensional chain group on the main chain block; mount the main chain block at the end of the chain of the local blockchain.

[0075] After each block is locally chained, the smart contract starts working. (The smart contract includes an algorithm for calculating the number of detection rounds and the number of images detected by each detector in each round, that is, the above-mentioned determination of the number of image detections and the determination of the preset number of detection rounds). According to the number of image detections distributed to each detector, the smart contract randomly selects the corresponding number of images that have not been detected by the corresponding detector from the images to be detected on the chain and sends them to the corresponding detector. After the detector detects the received images to be detected, the detector number, the main chain block number of the image to be detected, the image number, the detection time and the detection result are chained. The specific chaining step can be: after the detector completes the detection, click the submit button, the image detection device assembles the data, and calls the chaining interface for chaining. Go to step 2; Step 2: Receive a blockchain node A that receives the chaining request in step 1, detect the main chain block number of the image in the chaining data, the correctness of the image number, check whether the main chain block has the number, and check whether the image with the corresponding number exists in the image data of the corresponding main chain block. If one of the two fields is wrong, it means that it is invalid data, and the chaining is rejected, and the information of the error field is returned to the interface caller. If all the fields are correct, the node will package them into blocks and publish the blocks to the blockchain. After consensus by the consensus algorithm, each node of the blockchain will save a copy of the on-chain detection data. Go to step three; Step three: Each node performs the following actions locally: find the corresponding main chain block according to the main chain block number to which the image belongs; find the jth element in the i-th linked list (i.e. the detector number is the i-th) in the two-dimensional chain group mounted on the main chain block according to the detector number and image number (i.e. the image number is the sequence number of the image in the main chain block is the jth), convert the detection time into a millisecond digital string A, and convert the detection result into a result B of 0 or 1. Store A×10+B as the detection data in the long type digital field of the j-th element in the i-th linked list (the sequence number of the int type in the element is written into the corresponding sequence number j when the element is created).

[0076] Furthermore, in order to save storage space, after step S30, the method further includes: traversing the two-dimensional chain group to determine the current chain list traversed;

[0077] The first non-empty element in the current linked list is used as the head element of the current linked list, and subsequent non-empty elements are sequentially mounted behind the head element, and the empty elements in the current linked list are deleted;

[0078] Return to the step of traversing the two-dimensional chain group until the traversal of the two-dimensional chain group is completed.

[0079] It should be noted that after the image detection is completed, there will be some vacant elements in the two-dimensional chain group, that is, some elements have no data, that is, the linked list corresponding to the detector will have some images that have not been assigned for detection and therefore have no detection results. At this time, the two-dimensional chain group can be compressed to save storage space. Specifically, step 1: start traversing from the first linked list in the two-dimensional chain group, save the first element of the linked list in a temporary variable, hereinafter referred to as temp, traverse to the first non-empty element, and use it as the first element of the linked list (since the element has its own image number, the order will not be messed up due to deleting the empty elements at this time);

[0080] Step 2: Continue to traverse the first linked list, and mount subsequent non-empty elements at the back of the linked list in sequence. In this process, blank elements are deleted from the linked list. If the first linked list is traversed, find the first element of the second linked list according to the temporary variable temp, copy it to the temporary variable temp, and continue with step 2 until all linked lists are traversed.

[0081] Step 3: Delete the separated and empty elements in the two-dimensional chain group, and realize the partial data recovery of the two-dimensional chain group. In addition, when the administrator triggers the data recovery of a certain main chain block or a certain main chain block in the blockchain, after each blockchain node receives the request, the smart contract can automatically delete the two-dimensional chain group of the corresponding main chain block to save storage space.

[0082] In a specific implementation, when the image detection method is implemented based on blockchain, the image information (i.e., the image to be detected) such as the detection person information, smart contracts, and generative digital intelligent person expressions and actions are first put on the chain. The blockchain smart contract calculates the number of detection rounds based on the number of detection persons in the detection person information and the total number of images to be detected, and then determines the detection quality and detection efficiency of each detection person based on the historical detection information of the detection person, and calculates the number of images detected by each detection person in each round based on the detection quality and detection efficiency, and then distributes the images to be detected to each detection person based on the number of images detected by each detection person in each round. Each detection person receives the image to be detected, and after detecting the image to be detected distributed to each person, the result is fed back, and the detection result is uploaded to the blockchain synchronously and stored in the two-dimensional chain group on the blockchain. The blockchain smart contract calculates and refreshes the detection quality and efficiency of the detection person based on the recovered detection results, and performs iterative detection.

[0083] This embodiment determines the number of images to be detected for the detected person based on historical detection information; based on the number of image detections, the detected person is assigned images to be detected, and the detection results fed back by the detected person based on the images to be detected are obtained; based on the detection results, iterative detection is performed until the number of detection rounds reaches a preset number of detection rounds, and the image detection results are obtained. Since this embodiment assigns images to be detected to the detected person based on historical detection information and then performs image detection, and generates image detection results when the number of detection rounds reaches the preset number of detection rounds, compared with the existing method of distributing images for detection in sequence according to the table order of the detected person, the above method of this embodiment can improve the efficiency of image detection.

[0084] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 3 , Figure 3 The flowchart of the second embodiment of the image detection method of the present application is provided, wherein the step S10 further includes the following steps:

[0085] Step S101: determining the historical test results of each tester according to the historical test information;

[0086] It should be noted that the historical detection results may include the detection results of each detector on the image to be detected, and 1 may be used to indicate a passed detection, and 0 may be used to indicate a failed detection.

[0087] Step S102: Determine the detection quality and detection efficiency of the detection person according to the historical detection results;

[0088] It should be noted that the determination of the detection quality of the detection person according to the historical detection results may be performed by using the following formula:

[0089]

[0090] Among them, Q i It is used to characterize the detection quality of the i-th detector, and E is used to characterize the average of the images detected by the detector i in the historical detection results of other detectors. i，j It is used to represent the detection result of the i-th detector on the j-th image to be detected. num is used to represent the number of images to be detected by the detector.

[0091] Determining the detection efficiency of the detection person according to the historical detection results may be determining the detection efficiency of the detection person by the following formula:

[0092]

[0093] Among them, T iIt is used to characterize the detection efficiency of the i-th detector, num is used to characterize the number of images to be detected by the detector, and time is used to characterize the average detection time spent by the detector i to detect num images to be detected. The detection average time is determined based on the historical average time and the current average time. If the difference between the historical average time and the current average time is within the threshold k, the two are averaged; if the difference is outside the threshold k, the current average time is used as the basis. The threshold k can be a pre-defined threshold.

[0094] Step S103: Determine the number of images of the person to be detected based on the detection quality, the detection efficiency and the number of images to be detected.

[0095] It should be noted that the determination of the number of images of the detected person to be detected based on the detection quality, the detection efficiency and the number of images to be detected may be performed by determining the number of images of the detected person to be detected using the following formula:

[0096]

[0097] Among them, num i is used to represent the number of images detected by the i-th detection person, round is used to represent the preset number of detection rounds, and m is used to represent the number of images to be detected, that is, the total number of images to be detected. In order to avoid a large difference in the number of images detected by each detection person, this embodiment also sets the minimum number of detections per round for each detection person to be K1, and the maximum number of detections per round for each detection person to be K2. i After calculation, num i <K1, then num i =K1; if num i After calculation, num i >K2, then num i =K2.

[0098] This embodiment determines the historical detection results of each detector based on historical detection information; determines the detection quality and detection efficiency of the detector based on the historical detection results; and determines the number of image detections of the detector based on the detection quality, the detection efficiency, and the number of images to be detected. This embodiment automatically and intelligently calculates the number of image detections based on the historical detection quality and efficiency of the detector. This realizes intelligent distribution detection based on the quality and efficiency of the detector, and improves the intelligence, automation, and controllability of detection.

[0099] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the image detection method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0100] This application also provides an image detection device, please refer to Figure 4 , the image detection device comprises:

[0101] A determination module 10, used to determine the number of images of the detected person according to the historical detection information;

[0102] The detection module 20 is used to allocate images to be detected to the detector based on the number of image detections, and obtain the detection results fed back by the detector based on the images to be detected;

[0103] The iterative detection module 30 is used to perform iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain an image detection result.

[0104] This embodiment determines the number of images to be detected for the detected person based on historical detection information; based on the number of image detections, the detected person is assigned images to be detected, and the detection results fed back by the detected person based on the images to be detected are obtained; based on the detection results, iterative detection is performed until the number of detection rounds reaches a preset number of detection rounds, and the image detection results are obtained. Since this embodiment assigns images to be detected to the detected person based on historical detection information and then performs image detection, and generates image detection results when the number of detection rounds reaches the preset number of detection rounds, compared with the existing method of distributing images for detection in sequence according to the table order of the detected person, the above method of this embodiment can improve the efficiency of image detection.

[0105] The image detection device provided by the present application adopts the image detection method in the above embodiment, which can solve the technical problem of low efficiency of existing image detection. Compared with the prior art, the beneficial effects of the image detection device provided by the present application are the same as the beneficial effects of the image detection method provided by the above embodiment, and other technical features in the image detection device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0106] The present application provides an image detection device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the image detection method in the above-mentioned embodiment one.

[0107] Reference below Figure 5, which shows a schematic diagram of the structure of an image detection device suitable for implementing the embodiment of the present application. The image detection device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The image detection device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0108] like Figure 5 As shown, the image detection device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the image detection device are also stored. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the image detection device to communicate with other devices wirelessly or by wire to exchange data. Although the image detection device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided alternatively.

[0109] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0110] The image detection device provided by the present application adopts the image detection method in the above embodiment, which can solve the technical problem of low efficiency of existing image detection. Compared with the prior art, the beneficial effects of the image detection device provided by the present application are the same as the beneficial effects of the image detection method provided by the above embodiment, and other technical features in the image detection device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0111] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0112] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0113] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the image detection method in the above-mentioned embodiment.

[0114] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0115] The computer-readable storage medium may be included in the image detection device; or may exist independently without being assembled into the image detection device.

[0116] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the image detection device, the image detection device executes the image detection method.

[0117] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0118] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0119] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0120] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned image detection method, and can solve the technical problem of low efficiency of existing image detection. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the image detection method provided in the above-mentioned embodiment, and will not be described in detail here.

[0121] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned image detection method when executed by a processor.

[0122] The computer program product provided by this application can solve the technical problem of low efficiency of existing image detection. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the image detection method provided by the above embodiment, which will not be repeated here.

[0123] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. An image detection method, characterized in that: The image detection method comprises the following steps: Determine the number of images to be tested for a person based on historical test information; Allocating images to be detected to the detector based on the number of image detections, and obtaining detection results fed back by the detector based on the images to be detected; Iterative detection is performed based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain an image detection result.

2. The image detection method according to claim 1, characterized in that: The step of determining the number of images of the detected person according to the historical detection information comprises: Determine the historical test results of each tester based on the historical test information; Determining the testing quality and testing efficiency of the tester according to the historical testing results; The number of images to be detected of the detected person is determined based on the detection quality, the detection efficiency and the number of images to be detected.

3. The image detection method according to claim 1, characterized in that: The information of the detector, the image to be detected and the detection result in the image detection method are all stored on the blockchain. The blockchain includes a main chain and a two-dimensional chain group. The information of the detector, the image to be detected and the address of the two-dimensional chain group are stored on the main chain. The detection result is stored on the two-dimensional chain group. The two-dimensional chain group stores the detection results of the detector on each image to be detected through a one-way linked list.

4. The image detection method according to claim 3, characterized in that: After the step of performing iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain the image detection result, the method further includes: Traversing the two-dimensional chain group to determine the current chain list traversed; The first non-empty element in the current linked list is used as the head element of the current linked list, and subsequent non-empty elements are sequentially mounted behind the head element, and the empty elements in the current linked list are deleted; Return to the step of traversing the two-dimensional chain group until the traversal of the two-dimensional chain group is completed.

5. The image detection method according to any one of claims 1 to 4, characterized in that: Before the step of performing iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain the image detection result, the step further includes: Obtaining information on the number of images to be detected and a preset detection quantity threshold; Determine the range of the number of testing rounds according to the quantity information, the preset detection quantity threshold and the number of testers; A preset number of detection rounds is determined based on the range of detection rounds.

6. The image detection method according to any one of claims 1 to 4, characterized in that: The step of performing iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain the image detection result includes: Determine whether the current number of detection rounds reaches the preset number of detection rounds; If the current number of detection rounds does not reach the preset number of detection rounds, the detection result is used as historical detection information, and the process returns to the step of determining the number of images of the detected person to be detected based on the historical detection information until the number of detection rounds reaches the preset number of detection rounds.

7. An image detection device, characterized in that: The image detection device comprises: A determination module, used to determine the number of images of the detected person according to historical detection information; A detection module, used to allocate images to be detected to the detector based on the number of image detections, and obtain detection results fed back by the detector based on the images to be detected; The iterative detection module is used to perform iterative detection based on the detection result until the number of detection rounds reaches a preset number of detection rounds to obtain an image detection result.

8. An image detection device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the image detection method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the image detection method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the image detection method according to any one of claims 1 to 6 are implemented.

Images