Infringement Detection Method and Apparatus, Storage Method and Apparatus, Electronic Device

Abstract

The present disclosure discloses an infringement detection method and device, a storage method and device, and an electronic device. The infringement detection method is applied to the technical field of copyright protection. The method includes: determining N suspected homologous images corresponding to the image to be detected; respectively performing similar region segmentation on the image to be detected and each of the N suspected homologous images; if it is determined, based on the similar region segmentation results of the N suspected homologous images, that there is an image that meets the infringement conditions among the N suspected homologous images, then determining that the image to be detected is infringing, and determining the similar region between the image to be detected and the image that meets the infringement conditions as the infringement region. Since the method of similar region segmentation has the characteristics of low running burden, high robustness, and high segmentation accuracy, by using the method of similar region segmentation, not only can the infringement detection result of the image to be detected be obtained quickly and accurately, but also the infringement region can be determined by segmentation, thereby providing evidence for subsequent rights protection.

Description

Technical Field

[0001] The present disclosure relates to the technical field of copyright protection, and particularly to an infringement detection method and apparatus, a storage method and apparatus, and an electronic device. Background Art

[0002] With the rapid development of image-related technologies (such as image processing technologies), the importance of copyright protection for images has become increasingly prominent. Currently, traditional infringement detection methods are often used to detect images to be protected in order to verify whether there are infringement problems with the images to be protected. However, traditional infringement detection methods usually achieve the detection purpose based on the global feature data of images, and thus there are problems with poor detection effects. Summary of the Invention

[0003] In view of this, the present disclosure provides an infringement detection method and apparatus, a storage method and apparatus, and an electronic device to solve the problem of poor detection effects in infringement detection.

[0004] In a first aspect, an infringement detection method is provided. The method includes: determining N suspected homologous images corresponding to the image to be detected, where N is a positive integer; respectively performing similar region segmentation on the image to be detected and each of the N suspected homologous images; if it is determined, based on the similar region segmentation results of the N suspected homologous images, that there is an image that meets the infringement conditions among the N suspected homologous images, then determining that the image to be detected is infringed, and determining the similar region between the image to be detected and the image that meets the infringement conditions as the infringement region.

[0005] In a second aspect, a storage method is provided. The method includes: receiving a protected image that has passed the detection based on the method of the first aspect; storing the protected image in a blockchain.

[0006] In a third aspect, an infringement detection method is provided. The method includes: in response to a user's infringement detection request, sending the image to be detected to an infringement detection system, where the infringement detection system is configured to perform infringement detection on the image to be detected based on the method of the first aspect; receiving the infringement detection result feedback by the infringement detection system.

[0007] In a fourth aspect, an infringement detection apparatus is provided. The apparatus includes: a first determination module configured to determine N suspected homologous images corresponding to the image to be detected, where N is a positive integer; a similar region segmentation module configured to respectively perform similar region segmentation on the image to be detected and each of the N suspected homologous images; a second determination module configured to, if it is determined, based on the similar region segmentation results of the N suspected homologous images, that there is an image that meets the infringement conditions among the N suspected homologous images, then determining that the image to be detected is infringed, and determining the similar region between the image to be detected and the image that meets the infringement conditions as the infringement region.

[0008] In a fifth aspect, a storage device is provided, which includes: a receiving module configured to receive a to-be-protected image detected and passed by the method according to the first aspect; a storage module configured to store the to-be-protected image into a blockchain.

[0009] In a sixth aspect, an infringement detection device is provided, which includes: a sending module configured to send a to-be-detected image to an infringement detection system in response to a user's infringement detection request, where the infringement detection system is used to perform infringement detection on the to-be-detected image based on the method according to the first aspect; a receiving module configured to receive an infringement detection result fed back by the infringement detection system.

[0010] In a seventh aspect, an electronic device is provided, which includes: a processor and a memory for storing computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method mentioned in any one of the first to third aspects above.

[0011] In an eighth aspect, a computer-readable storage medium is provided, which stores instructions that, when executed, can implement the method mentioned in any one of the first to third aspects above.

[0012] In a ninth aspect, a computer program product is provided, including instructions that, when executed, can implement the method mentioned in any one of the first to third aspects above.

[0013] The infringement detection method provided by the embodiments of the present disclosure realizes the purpose of performing infringement detection on a to-be-detected image by means of segmenting similar regions of the to-be-detected image and N suspected homologous images corresponding to the to-be-detected image. Compared with traditional infringement detection methods, the method of segmenting similar regions has the characteristics of less running burden, high robustness, and high segmentation accuracy, so that the infringement detection result of the to-be-detected image can be obtained quickly and accurately. It can be seen that the embodiments of the present disclosure can improve the speed and accuracy of infringement detection, and further improve the detection effect of infringement detection. In addition, when an infringement region is determined, the infringement region can be determined by means of segmenting similar regions, so as to achieve the purpose of providing evidence for subsequent rights protection to improve the efficiency of rights protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The system architecture diagram of an infringement detection application scenario provided by an embodiment of the present disclosure is shown.

[0015] Figure 2 The flowchart of the infringement detection method provided by an embodiment of the present disclosure is shown.

[0016] Figure 3The figure shows a schematic flowchart of an infringement detection result of a to-be-detected image obtained by performing similar region segmentation based on N suspected homologous images and the to-be-detected image according to an embodiment of the present disclosure.

[0017] Figure 4 The figure shows a schematic flowchart of performing similar region segmentation on each of the to-be-detected image and N suspected homologous images according to an embodiment of the present disclosure.

[0018] Figure 5 The figure shows a schematic presentation diagram of an infringement detection process according to an embodiment of the present disclosure.

[0019] Figure 6 The figure shows a schematic flowchart of a storage method according to an embodiment of the present disclosure.

[0020] Figure 7 The figure shows a schematic flowchart of an infringement detection method according to another embodiment of the present disclosure.

[0021] Figure 8 The figure shows a schematic interaction flowchart of an infringement detection method according to an embodiment of the present disclosure.

[0022] Figure 9 The figure shows a schematic structural diagram of an infringement detection device according to an embodiment of the present disclosure.

[0023] Figure 10 The figure shows a schematic structural diagram of an infringement detection device according to another embodiment of the present disclosure.

[0024] Figure 11 The figure shows a schematic structural diagram of a storage device according to an embodiment of the present disclosure.

[0025] Figure 12 The figure shows a schematic structural diagram of an infringement detection device according to still another embodiment of the present disclosure.

[0026] Figure 13 The figure shows a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. Detailed Embodiments

[0027] Next, the technical solutions in the embodiments of the present disclosure will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments.

[0028] With the rapid development of Internet technology, it has become a trend to publish original image works on the Internet to realize the rapid monetization of intellectual property rights. However, this has led to a chaotic situation in the copyright industry and frequent copyright disputes.

[0029] For example, non-original authors use image editing functions to adapt the original image works of other original authors to obtain non-original image works, and use the non-original image works to pose as original image works, selling copyrights to produce peripheral products to make huge profits, infringing on the rights and interests of original authors and causing copyright disputes. Another example is that relevant websites label non-original image works with exclusive copyright tags for exclusive sale, which not only infringes on the rights and interests of original authors and causes copyright disputes, but also makes the credibility of the website highly questioned and the corporate reputation damaged.

[0030] Due to the increasing number of copyright disputes, copyright protection is urgent. However, in the actual process of protecting rights, there are many problems such as a long rights protection period and difficulty in obtaining evidence. Although there are currently some infringement detection methods that rely on the global feature data of images to assist in rights protection, there are problems with poor detection effects.

[0031] To solve the above problems, the embodiments of the present disclosure provide an infringement detection method, which realizes the purpose of detecting infringement of the image to be detected by means of segmenting similar regions of the image to be detected and N suspected homologous images corresponding to the image to be detected. Compared with the traditional infringement detection method, the method of segmenting similar regions has the characteristics of less running burden, high robustness and high segmentation accuracy, so that the infringement detection result of the image to be detected can be obtained quickly and accurately. It can be seen that the embodiments of the present disclosure can improve the speed and accuracy of infringement detection, and thus can improve the detection effect of infringement detection. In addition, when an infringement area is determined, the infringement area can be determined by means of similar region segmentation, so as to provide evidence for subsequent rights protection to improve the efficiency of rights protection.

[0032] The following combines Figure 1 to give an example of the system architecture of the infringement detection application scenario.

[0033] As Figure 1 shown, the infringement detection application scenario provided by the embodiments of the present disclosure involves a user terminal 110, a server 120 communicatively connected to the user terminal 110, and a blockchain system 130 communicatively connected to the server 120. Among them, an infringement detection system is deployed in the server 120, and the infringement detection system is used to detect infringement of images that need to be detected for infringement. More specifically, the detection steps of the infringement detection system include: respectively segmenting similar regions of each of the image to be detected and the N suspected homologous images; if it is determined based on the similar region segmentation results of the N suspected homologous images that there is an image that meets the infringement conditions among the N suspected homologous images, it is determined that the image to be detected is infringing, and the similar region between the image to be detected and the image that meets the infringement conditions is determined as the infringement region. Among them, the image to be detected includes but is not limited to photographic images, hand-painted images, poster images, etc.

[0034] Exemplarily, the user terminal 110 can be the user terminal of a user with infringement detection requirements. For example, the user terminal can be a mobile phone, a tablet computer, a desktop computer, etc. of a photography enthusiast. The server 120 can be either a physical server or a cloud server. The blockchain system 130 is a blockchain system with a storage function, so as to store the images that have successfully passed the infringement detection, and thus provide a data basis for subsequent operations such as copyright protection. In addition, the blockchain system 130 can maintain one or more blockchains (for example, public blockchains, private blockchains, consortium blockchains, etc.), and includes multiple blockchain nodes for hosting the above one or more blockchains. In some embodiments, the server 120 can also be regarded as a blockchain node of the blockchain system 130.

[0035] Exemplarily, in the actual application process, a user with infringement detection requirements uses the user terminal 110 to put forward an infringement detection requirement. In response to the infringement detection requirement, the user terminal 110 uploads the image to be detected corresponding to the infringement detection requirement to the server 120. The server 120 uses the deployed infringement detection system to perform infringement detection on the image to be detected, obtains the infringement detection result, and feeds back the infringement detection result to the user terminal 110 so that the user can know in time. In addition, if the infringement detection result is determined to be non-infringing, the server 120 sends the image to be detected that has successfully passed the detection (also known as the image to be protected) to the blockchain system 130. Correspondingly, the blockchain system 130 stores the image to be protected.

[0036] Feeding back the infringement detection result to the user terminal 110 enables the user to clearly know the image infringement situation. Further, in some embodiments, if the infringement detection result is determined to be non-infringing, the user terminal 110 can receive an authentication certificate with an authentication timestamp for the user to prove their own rights and interests. If the infringement detection result is determined to be infringing, the user terminal 110 can receive an infringement notice, which will detail the infringement situation (including the infringement area, etc.). If the user is not satisfied with the infringement result, the user can also hold the infringement notice to appeal to the corresponding judicial center.

[0037] A blockchain is a distributed shared ledger and database, which has the characteristics of decentralization, immutability, full traceability, traceability, collective maintenance, and openness and transparency, and is thus widely applied to many fields. In the present disclosure, the method of storing the images that have successfully passed the infringement detection into the blockchain system 130 can avoid the situation where the images to be protected are tampered with. That is to say, the images to be protected (also known as original images) stored in the blockchain system 130 are credible.

[0038] The following will be combined with Figures 2 to 8 to introduce in detail the infringement detection method and storage method mentioned in the embodiments of the present disclosure.

[0039] Figure 2 The following is a schematic flow chart of an infringement detection method provided by an embodiment of the present disclosure. Exemplarily, this infringement detection method can be executed by a server. Further, the entity to which the server belongs can be either an original image library website with an infringement detection requirement or an organization with a copyright authorization function.

[0040] As Figure 2 shown, the infringement detection method provided by the embodiment of the present disclosure includes the following steps.

[0041] Step S210, determine N suspected homologous images corresponding to the image to be detected. Wherein, N is a positive integer.

[0042] The suspected homologous images refer to images that are suspected to be homologous to the image to be detected. That is, images whose similarity degree to the image to be detected exceeds a preset similarity threshold and are suspected of being infringed by the image to be detected. That is to say, the image to be detected may infringe the copyright of the suspected homologous images. The meaning of N being a positive integer is that the suspected homologous images corresponding to the image to be detected can be either one or multiple, and the embodiments of the present disclosure do not make a unified limitation on this. Exemplarily, N is equal to 10.

[0043] In some embodiments, to determine N suspected homologous images corresponding to the image to be detected, it can be executed as: obtain N suspected homologous images corresponding to the image to be detected. That is to say, the N suspected homologous images are not calculated by the server, but are obtained by the server from the outside. Such a setting can not only reduce the computing pressure on the server but also improve the application universality of the infringement detection method mentioned in the embodiments of the present disclosure.

[0044] In some other embodiments, to determine N suspected homologous images corresponding to the image to be detected, it can be executed as: determine N suspected homologous images corresponding to the image to be detected based on the global feature data of the image to be detected. Specifically, perform global feature extraction on the image to be detected to obtain the global feature data (also known as the global feature vector) of the image to be detected, and then calculate the similarity between the global feature data of the image to be detected and the global feature data of each of multiple candidate source images, so as to obtain the similarity value corresponding to each of the multiple candidate source images. Then, arrange the similarity values corresponding to each of the multiple candidate source images in descending order, and use the N candidate source images corresponding to the top N similarity values as the N suspected homologous images. Such a setting can ensure the speed of determining suspected homologous images by means of global feature data, thereby improving the speed of infringement detection.

[0045] Exemplarily, the above-mentioned multiple candidate source images are source images protected by copyright stored in the blockchain. Correspondingly, the global feature data of each of the multiple candidate source images is stored in the source image feature library of the blockchain.

[0046] Step S220: For each of the to-be-detected image and the N suspected homologous images, perform similar region segmentation.

[0047] That is to say, perform similar region segmentation operations on the to-be-detected image and each suspected homologous image respectively, so as to verify whether the suspected homologous image belongs to the infringed image corresponding to the to-be-detected image.

[0048] Exemplarily, the above-mentioned similar region segmentation refers to segmenting out the similar regions existing in the to-be-detected image and each suspected homologous image, so as to achieve the purpose of highlighting the similar regions existing in the to-be-detected image and each suspected homologous image, thereby simplifying the calculation amount of subsequent infringement determination and reflecting the specific infringement regions in the final infringement detection result.

[0049] It should be noted that for each suspected homologous image, if it is determined that there is no similar region based on the similar region detection result, then it is determined that there is no infringement relationship between the suspected homologous image and the to-be-detected image (that is, relative to the suspected homologous image, the to-be-detected image is not infringing).

[0050] In some embodiments, the similar region segmentation mentioned in step S220 can be implemented by means of a pre-trained neural network model (i.e., a similar region segmentation model). That is to say, the similar region segmentation model can perform similar region segmentation on each of the to-be-detected image and the N suspected homologous images. The embodiments of the present disclosure can achieve the end-to-end detection purpose by means of the similar region segmentation model, with a simple process, which can not only improve the speed of infringement detection, but also reduce the system operation pressure. In addition, when it is determined that there is a similar region (also known as an infringement region), the embodiments of the present disclosure determine the infringement region by segmenting the similar region, which can not only improve the detection accuracy, but also enable users to know the specific infringement situation in a timely manner.

[0051] Exemplarily, train an initial neural network model based on a training sample set to obtain the above-mentioned similar region segmentation model. Among them, the model architecture of the initial neural network model includes but is not limited to architectures such as Unet, SegNet, and RefineNet.

[0052] In some embodiments, the implementation manner of determining the N suspected homologous images corresponding to the to-be-detected image can be to perform feature comparison on the global feature data of the to-be-detected image and the global feature data of each of the source images stored in the blockchain to obtain N suspected homologous images. By using the method of global feature comparison, N suspected homologous images are screened out from the large number of source images stored in the blockchain, thereby effectively reducing the pressure on the server for more refined similar region segmentation.

[0053] Step S230: If, based on the segmentation results of the similar regions of each of the N suspected homologous images, it is determined that there is an image among the N suspected homologous images that meets the infringement conditions, then it is determined that the image to be detected is infringing, and the similar region between the image to be detected and the image that meets the infringement conditions is determined as the infringement region.

[0054] That is to say, if, based on the segmentation results of the similar regions of each of the N suspected homologous images, it is determined that there is no image among the N suspected homologous images that meets the infringement conditions, then it is determined that the image to be detected is not infringing.

[0055] The infringement detection method provided by the embodiments of the present disclosure realizes the purpose of detecting infringement of the image to be detected by segmenting the similar regions of the image to be detected and the N suspected homologous images corresponding to the image to be detected. Compared with the traditional infringement detection method, the method of segmenting similar regions has the characteristics of less running burden, high robustness, and high segmentation accuracy, so that the infringement detection result of the image to be detected can be obtained quickly and accurately. It can be seen that the embodiments of the present disclosure can improve the speed and accuracy of infringement detection, and further improve the detection effect of infringement detection. In addition, when determining the existence of an infringement region, the infringement region can be determined by means of similar region segmentation, so as to achieve the purpose of providing evidence for subsequent rights protection to improve the efficiency of rights protection.

[0056] In some embodiments, as Figure 3 shown, the infringement detection method provided by the present disclosure includes the following steps.

[0057] Step S310: Determine the N suspected homologous images corresponding to the image to be detected.

[0058] Step S320: Respectively perform similar region segmentation on the image to be detected and each of the N suspected homologous images among the N suspected homologous images.

[0059] Step S330: Based on the segmentation results of the similar regions of each of the N suspected homologous images, determine whether there is an image among the N suspected homologous images that meets the infringement conditions.

[0060] Exemplarily, in the actual application process, if the judgment result of step S330 is yes, that is, there is an image among the N suspected homologous images that meets the infringement conditions, then perform the following step S340; if the judgment result is no, that is, there is no image among the N suspected homologous images that meets the infringement conditions, then perform the following step S350.

[0061] Step S340: Determine that the image to be detected is infringing, and determine the similar region between the image to be detected and the image that meets the infringement conditions as the infringement region.

[0062] Step S350, determine that the image to be detected is not infringing, and store the image to be detected on the blockchain for evidence preservation.

[0063] Optionally, the implementation manner of storing the image to be detected on the blockchain can be to store the image to be detected, the hash value of the image to be detected, and the global feature vector of the image to be detected on the blockchain.

[0064] That is to say, if it is determined that there is an image that meets the infringement conditions among the N suspected homologous images based on the segmentation results of the similar regions of each of the N suspected homologous images, then it is determined that the image to be detected is infringing, and the similar region between the image to be detected and the image that meets the infringement conditions is determined as the infringement region. If it is determined that there is no image that meets the infringement conditions among the N suspected homologous images based on the segmentation results of the similar regions of each of the N suspected homologous images, then it is determined that the image to be detected is not infringing, and the image to be detected is stored on the blockchain for evidence preservation.

[0065] It can be seen that if it is determined that the image to be detected is infringing, the embodiments of the present disclosure can determine the specific infringement region by means of similar region segmentation, thereby providing a prerequisite for visually presenting the specific infringement region to the user subsequently and improving the user experience satisfaction. In addition, if the image to be detected is not infringing, the embodiments of the present disclosure can store the image to be detected on the blockchain (i.e., the above-mentioned blockchain system) to provide copyright protection for the image to be detected.

[0066] Combined with the above description, it can be known that for each suspected homologous image, the similar region between the suspected homologous image and the image to be detected can be determined by using the similar region segmentation operation. However, even if there is a similar region between the suspected homologous image and the image to be detected, the image to be detected does not necessarily infringe the copyright of the suspected homologous image. For example, if the area ratio of the similar region between the suspected homologous image and the image to be detected is too small (for example, less than the preset area ratio threshold), it can still be determined that the image to be detected does not infringe the copyright of the suspected homologous image. Such a setting can reduce the probability of misjudgment of the image to be detected, and further improve the accuracy of infringement detection.

[0067] Based on this, in some embodiments, it is limited that the ratio of the area of the infringement region in the image that meets the infringement conditions (i.e., the area of the similar region in the image that meets the infringement conditions) to the area of the image that meets the infringement conditions (i.e., the area of the image that meets the infringement conditions), and the ratio of the area of the infringement region in the image to be detected (i.e., the area of the similar region in the image to be detected) to the area of the image to be detected, the larger ratio falls within the preset infringement threshold range. The preset infringement threshold range can be determined according to the actual situation. For example, when the similar region segmentation is implemented by means of a similar region segmentation model, the preset infringement threshold range can be determined according to the specific model structure of the similar region segmentation model.

[0068] That is, in some embodiments, before determining that there is an image meeting the infringement conditions among the N suspected homologous images based on the segmentation results of the similar regions of each of the N suspected homologous images, the method further includes: for each of the N suspected homologous images, if the larger ratio among the ratio of the area of the similar region in the suspected homologous image to the area of the suspected homologous image and the ratio of the area of the similar region in the image to be detected to the area of the image to be detected falls within a preset infringement threshold range, determine that the suspected homologous image is an image meeting the infringement conditions.

[0069] To facilitate the calculation of the similar regions between the suspected homologous images and the image to be detected, the suspected homologous images and the image to be detected can be spliced, and then operations such as similar region segmentation can be performed based on the spliced image. The following combines Figure 4 to give a specific example.

[0070] Figure 4 The following shows a schematic flowchart of performing similar region segmentation on the image to be detected and each of the N suspected homologous images provided by an embodiment of the present disclosure. As Figure 4 shown, in the embodiment of the present disclosure, the steps of performing similar region segmentation on the image to be detected and each of the N suspected homologous images include the following steps.

[0071] Step S410: Splice each of the N suspected homologous images with the image to be detected to obtain N spliced images.

[0072] Step S420: Perform similar region segmentation on the N spliced images respectively.

[0073] Exemplarily, step S420 is implemented based on a similar region segmentation model. The following combines Figure 5 to give an example. Specifically, as Figure 5 shown, input a spliced image (part P1 of the spliced image is the image to be detected, and part P2 is the suspected homologous image) into the similar region segmentation model, and then infringement detection results one and two are obtained.

[0074] Specifically, infringement detection result one labels the infringement region in the form of a rectangular box, and infringement detection result two labels the infringement region in the form of a mask. It can be understood that infringement detection result one and infringement detection result two can either exist simultaneously or one of them can be selected to exist. The embodiments of the present disclosure do not make a unified limitation on this.

[0075] The embodiment of the present disclosure adopts the splicing method to avoid the labeling requirement for the images that need to be compared for similarity, thereby further simplifying the calculation process of the similar regions.

[0076] The following will introduce in detail the storage method mentioned in the embodiments of the present disclosure in conjunction with Figure 6 The storage method mentioned in the embodiments of the present disclosure will be introduced in detail below. This storage method can be executed by any blockchain node in the blockchain system. In some embodiments, the blockchain nodes that execute the storage method mentioned in the embodiments of the present disclosure may include full nodes and light nodes.

[0077] As Figure 6 shown, the storage method provided by the embodiments of the present disclosure includes the following steps.

[0078] Step S610: Receive the image to be protected. Among them, the image to be protected has passed the infringement detection by the infringement detection method mentioned in any of the above embodiments.

[0079] Step S620: Store the image to be protected in the blockchain.

[0080] It can be understood that if the infringement detection result of the image to be detected mentioned in the above embodiment is non-infringement, then the image to be detected can be regarded as the image to be protected that needs to be stored on the chain.

[0081] The storage method provided by the embodiments of the present disclosure can store the image to be protected that has successfully passed the infringement detection in the blockchain system, thereby making full use of the characteristics of the blockchain such as immutability, and achieving the purpose of providing safe and reliable copyright protection for the original author.

[0082] For example, the infringement detection result of the landscape photography image F uploaded by user A is non-infringement. The blockchain receives the successfully detected landscape photography image F at the standard time 2021 / 10 / 25 18:12:32 and stores it. After success, the copyright protection start time feedback to user A is 2021 / 10 / 25 18:12:32. Subsequently, if user A wants to change the copyright protection start time, or user A wants to replace the landscape photography image F with an image S that has not passed the infringement detection, it is not possible. That is to say, due to the immutable characteristic of the blockchain, user A cannot achieve the above behaviors.

[0083] The following will introduce in detail another infringement detection method mentioned in the embodiments of the present disclosure in conjunction with Figure 7 The infringement detection method will be introduced in detail below. This infringement detection method can be executed by the user terminal. As Figure 7 shown, the infringement detection method provided by the embodiments of the present disclosure includes the following steps.

[0084] Step S710: In response to the user's infringement detection request, send the image to be detected to the infringement detection system.

[0085] Exemplarily, the infringement detection system is used to perform infringement detection on the image to be detected based on the infringement detection method mentioned in any of the above embodiments.

[0086] Exemplarily, user Xiaowang uses a mobile phone to take an image X. In order to apply for copyright protection for image X, user Xiaowang uploads image X (i.e., the image to be detected) to the infringement detection software (application, APP) on the mobile phone, so that the infringement detection software uploads image X to the infringement detection system on the server side for infringement detection.

[0087] Step S720, receive the infringement detection result feedback by the infringement detection system.

[0088] Exemplarily, if the image to be detected is not infringing, the mobile terminal receives a certification certificate from the copyright center carrying the current timestamp. If the image to be detected is infringing, the mobile terminal receives infringement prompt information (including specific infringement area marking information) to prompt the user that the image to be detected is not an original work and has infringed the rights of other original authors.

[0089] The infringement detection method provided by the embodiments of the present disclosure achieves the purpose of infringement detection with the help of the infringement detection system. Further, the embodiments of the present disclosure can enable the original authors who have completed the confirmation of rights to have a confirmation certificate, thereby providing safe and reliable copyright protection for the original authors and providing favorable evidence for subsequent rights protection. In addition, the embodiments of the present disclosure can also warn infringing users, thereby effectively reducing the probability of infringing users posing as original images to seek illegal benefits.

[0090] The following combines Figure 8 to further illustrate the interactive process schematic diagram of the actual implementation of infringement detection with examples. As Figure 8 shown, the embodiments of the present disclosure involve a user terminal, an infringement detection system terminal, and a blockchain system terminal.

[0091] For the user terminal, the embodiments of the present disclosure involve the following steps.

[0092] Step S810, in response to the user's infringement detection request, send the image to be detected to the infringement detection system.

[0093] Step S840, receive and present the infringement detection result.

[0094] For the infringement detection system terminal, the embodiments of the present disclosure involve the following steps.

[0095] Step S820, determine N suspected homologous images corresponding to the image to be detected.

[0096] Step S830, based on the N suspected homologous images and the image to be detected, perform similar region segmentation to obtain the infringement detection result of the image to be detected.

[0097] Further, if the image to be detected is not infringing, for the infringement detection system side, the embodiments of the present disclosure further involve the following steps: If the image to be detected is not infringing, send the image to be detected to the blockchain system side.

[0098] For the blockchain system side, the embodiments of the present disclosure involve the following steps.

[0099] Step S832, receive and store the image to be detected.

[0100] Exemplarily, in the actual application process, the user terminal responds to the user's infringement detection request, sends the image to be detected to the infringement detection system. The infringement detection system side receives the image to be detected, determines N suspected homologous images corresponding to the image to be detected, and then performs similar region segmentation based on the N suspected homologous images and the image to be detected to obtain the infringement detection result of the image to be detected. In addition, the infringement detection system side sends the infringement detection result to the user terminal, and the user terminal receives and presents the infringement detection result. Further, if the infringement detection system side determines that the image to be detected is not infringing, the infringement detection system side sends the image to be detected to the blockchain system side, and the blockchain system side receives and stores the image to be detected.

[0101] The embodiments of the present disclosure utilize the characteristics of less operation burden, high robustness, and high segmentation accuracy of similar region segmentation to quickly and accurately obtain the infringement detection result of the image to be detected. It can be seen that the embodiments of the present disclosure can improve the speed and accuracy of infringement detection, and thus can improve the detection effect of infringement detection.

[0102] As described above in conjunction with Figures 2 to 8 , the method embodiments of the present disclosure have been described in detail. Next, in conjunction with Figures 9 to 13 , the apparatus embodiments of the present disclosure will be described in detail. In addition, it should be understood that the descriptions of the method embodiments correspond to those of the apparatus embodiments. Therefore, the parts not described in detail can be referred to the previous method embodiments.

[0103] Figure 9 The following shows a schematic structural diagram of an infringement detection apparatus provided by an embodiment of the present disclosure. As Figure 9As shown in the figure, the infringement detection device 900 provided by an embodiment of the present disclosure includes a first determination module 910, a similar region segmentation module 920, and a second determination module 930. Specifically, the determination module 910 is configured to determine N suspected homologous images corresponding to the image to be detected, where N is a positive integer. The similar region segmentation module 920 is configured to perform similar region segmentation on each of the N suspected homologous images in the image to be detected and the N suspected homologous images respectively. The second determination module is configured to, if it is determined based on the similar region segmentation results of the N suspected homologous images that there is an image that meets the infringement conditions among the N suspected homologous images, determine that the image to be detected is infringing, and determine the similar region between the image to be detected and the image that meets the infringement conditions as the infringement region.

[0104] Figure 10 The following shows a schematic structural diagram of an infringement detection device provided by another embodiment of the present disclosure. Figure 9 Based on the embodiment shown above, Figure 10 the following embodiment is extended. Figure 10 The differences between the embodiment shown below Figure 9 and the embodiment shown above will be mainly described, and the same parts will not be elaborated.

[0105] As Figure 10 shown, the infringement detection device 900 provided by an embodiment of the present disclosure further includes: an infringement condition judgment module 925 and a third determination module 935.

[0106] Specifically, the infringement condition judgment module 925 is configured to, before it is determined based on the similar region segmentation results of the N suspected homologous images that there is an image that meets the infringement conditions among the N suspected homologous images, for each of the N suspected homologous images, if the ratio of the area of the similar region in the suspected homologous image to the area of the suspected homologous image and the ratio of the area of the similar region in the image to be detected to the area of the image to be detected, the larger ratio falls within a preset infringement threshold range, determine that the suspected homologous image is an image that meets the infringement conditions. The third determination module 935 is configured to, after performing similar region segmentation on each of the N suspected homologous images in the image to be detected and the N suspected homologous images respectively, if it is determined based on the similar region segmentation results of the N suspected homologous images that there is no image that meets the infringement conditions among the N suspected homologous images, determine that the image to be detected is not infringing, and store the image to be detected on the blockchain.

[0107] In some embodiments, the similar region segmentation module 920 is further configured to splice each of the N suspected homologous images with the image to be detected respectively to obtain N spliced images; and perform similar region segmentation on the N spliced images respectively.

[0108] In some embodiments, the first determination module 910 is further configured to perform feature comparison on the global feature data of the image to be detected and the global feature data of the source image stored in the blockchain, and obtain N suspected homologous images.

[0109] Figure 11 The following is a schematic structural diagram of a storage device provided by an embodiment of the present disclosure. As Figure 11 shown, the storage device 1100 provided by the embodiment of the present disclosure includes a receiving module 1110 and a storage module 1120. Specifically, the receiving module 1110 is configured to receive the image to be protected that passes the infringement detection based on the infringement detection method mentioned in the above embodiment. The storage module 1120 is configured to store the image to be protected in the blockchain.

[0110] Figure 12 The following is a schematic structural diagram of an infringement detection device provided by another embodiment of the present disclosure. As Figure 12 shown, the infringement detection device 1200 provided by the embodiment of the present disclosure includes a sending module 1212 and a receiving module 1220. Specifically, the sending module 1212 is configured to send the image to be detected to the infringement detection system in response to a user's infringement detection request, where the infringement detection system is used to perform infringement detection on the image to be detected based on the infringement detection method mentioned in the above embodiment. The receiving module 1220 is configured to receive the infringement detection result feedback by the infringement detection system.

[0111] Figure 13 The following is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. Figure 13 The shown electronic device 1300 (the device 1300 may specifically be a computer device) includes a memory 1301, a processor 1302, a communication interface 1303, and a bus 1304. Among them, the memory 1301, the processor 1302, and the communication interface 1303 are communicatively connected to each other through the bus 1304.

[0112] The memory 1301 may be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1301 may store a program. When the program stored in the memory 1301 is executed by the processor 1302, the processor 1302 and the communication interface 1303 are used to execute the various steps of the infringement detection method or the storage method of the embodiment of the present disclosure.

[0113] The processor 1302 may adopt a general - purpose central processing unit (CPU), a microprocessor, an application - specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits to execute relevant programs to implement the functions required to be executed by the units in the infringement detection device of the embodiments of the present disclosure.

[0114] The processor 1302 may also be an integrated circuit chip with the ability to process signals. In the implementation process, each step of the infringement detection method of the present disclosure may be completed by the integrated logic circuit in the hardware of the processor 1302 or the instructions in the form of software. The above - mentioned processor 1302 may also be a general - purpose processor, a digital signal processor (DSP), an application - specific integrated circuit (ASIC), a field - programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present disclosure. The general - purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present disclosure may be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read - only memory, a programmable read - only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 1301, and the processor 1302 reads the information in the memory 1301 and combines its hardware to complete the functions required to be executed by the units included in the infringement detection device of the embodiments of the present disclosure, or execute the infringement detection method of the method embodiments of the present disclosure.

[0115] The communication interface 1303 uses a transceiver device such as, but not limited to, a transceiver to implement the communication between the device 1300 and other devices or communication networks. For example, the image to be detected may be obtained through the communication interface 1303.

[0116] The bus 1304 may include a path for transmitting information between various components of the device 1300 (for example, the memory 1301, the processor 1302, the communication interface 1303).

[0117] It should be understood that the similar region segmentation module 920 in the infringement detection device 900 may be equivalent to the processor 1302.

[0118] It should be noted that although Figure 13 the device 1300 shown only shows a memory, a processor, and a communication interface, in the specific implementation process, those skilled in the art should understand that the device 1300 also includes other devices necessary for normal operation. At the same time, according to specific needs, those skilled in the art should understand that the device 1300 may also include hardware devices for implementing other additional functions. In addition, those skilled in the art should understand that the device 1300 may also only include the devices necessary for implementing the embodiments of the present disclosure, and do not have to include Figure 13 all the devices shown in

[0119] In addition to the above methods, devices, and equipment, the embodiments of the present disclosure may also be a computer program product, which includes computer program instructions that, when run by a processor, cause the processor to execute the steps of the infringement detection method provided in each embodiment of the present disclosure, or execute the steps of the storage method provided in each embodiment of the present disclosure.

[0120] The computer program product can be written in any combination of one or more programming languages for programming code to perform the operations of the embodiments of the present disclosure. The programming languages include object-oriented programming languages such as Java, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as an independent software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0121] In addition, the embodiments of the present disclosure may also be a computer-readable storage medium, on which computer program instructions are stored, and the computer program instructions, when run by a processor, cause the processor to execute the steps of the infringement detection method provided in each embodiment of the present disclosure, or execute the steps of the storage method provided in each embodiment of the present disclosure.

[0122] The computer-readable storage medium may adopt any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the readable storage medium (a non-exhaustive list) include: an electrical connection having one or more wires, a portable 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.

[0123] Those of ordinary skill in the art will realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this disclosure.

[0124] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0125] In several embodiments provided by this disclosure, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the couplings or direct couplings or communication connections shown or discussed with each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0126] The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, the functional units in each embodiment of this disclosure can be integrated in a similar area division unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0128] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present disclosure, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories, random access memories, magnetic disks, or optical discs.

[0129] As described above, the above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of changes or substitutions, which should all be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. An infringement detection method, comprising: Determining N suspected homologous images corresponding to the image to be detected, where N is a positive integer; Performing similar region segmentation on each of the N suspected homologous images in the image to be detected and the N suspected homologous images, where the similar region segmentation based on the N suspected homologous images and the image to be detected is performed by a pre-trained similar region segmentation model; If it is determined, based on the similar region segmentation results of the N suspected homologous images respectively, that there is an image meeting the infringement conditions among the N suspected homologous images, then it is determined that the image to be detected is infringing, and the similar region between the image to be detected and the image meeting the infringement conditions is determined as the infringement region; Wherein, the performing similar region segmentation on each of the N suspected homologous images in the image to be detected and the N suspected homologous images respectively includes: Splicing each of the N suspected homologous images with the image to be detected respectively to obtain N spliced images; Performing similar region segmentation on the N spliced images respectively.

2. The method according to claim 1, before the step of if it is determined, based on the similar region segmentation results of the N suspected homologous images respectively, that there is an image meeting the infringement conditions among the N suspected homologous images, further comprising: For each of the N suspected homologous images, if the ratio of the area of the similar region in the suspected homologous image to the area of the suspected homologous image and the ratio of the area of the similar region in the image to be detected to the area of the image to be detected, the larger ratio falls within a preset infringement threshold range, then it is determined that the suspected homologous image is the image meeting the infringement conditions.

3. The method according to claim 1 or 2, after the step of performing similar region segmentation on each of the N suspected homologous images in the image to be detected and the N suspected homologous images respectively, further comprising: If it is determined, based on the similar region segmentation results of the N suspected homologous images respectively, that there is no image meeting the infringement conditions among the N suspected homologous images, then it is determined that the image to be detected is not infringing, and the image to be detected is stored on the blockchain.

4. The method according to claim 1 or 2, the determining N suspected homologous images corresponding to the image to be detected includes: Performing feature comparison on the global feature data of the image to be detected and the global feature data of the source image stored on the blockchain to obtain the N suspected homologous images.

5. A storage method, comprising: Receiving a protected image detected and passed by the method according to any one of claims 1 to 4; Storing the protected image on the blockchain.

6. An infringement detection method, comprising: In response to a user's infringement detection request, sending the image to be detected to an infringement detection system, where the infringement detection system is used to perform infringement detection on the image to be detected based on the method according to any one of claims 1 to 4; Receiving the infringement detection result fed back by the infringement detection system.

7. An infringement detection device, comprising: The first determination module is configured to determine N suspected homologous images corresponding to the image to be detected, where N is a positive integer; The similar region segmentation module is configured to perform the similar region segmentation on each of the N suspected homologous images in the image to be detected and the N suspected homologous images respectively. The similar region segmentation based on the N suspected homologous images and the image to be detected is performed by a pre-trained similar region segmentation model; The second determination module is configured to, if it is determined that there is an image meeting the infringement conditions among the N suspected homologous images based on the similar region segmentation results of the N suspected homologous images respectively, determine that the image to be detected is infringing, and determine the similar region between the image to be detected and the image meeting the infringement conditions as the infringement region; Among them, the performing the similar region segmentation on each of the N suspected homologous images in the image to be detected and the N suspected homologous images respectively includes: Splicing each of the N suspected homologous images with the image to be detected respectively to obtain N spliced images; Performing the similar region segmentation on the N spliced images respectively.

8. A storage device, comprising: A receiving module configured to receive a protected image detected and passed by the method according to any one of claims 1 to 4; A storage module configured to store the protected image in a blockchain.

9. An infringement detection device, comprising: A sending module configured to send the image to be detected to an infringement detection system in response to a user's infringement detection request, where the infringement detection system is used to perform infringement detection on the image to be detected based on the method according to any one of claims 1 to 4; A receiving module configured to receive the infringement detection result fed back by the infringement detection system.

10. An electronic device, comprising: A processor; And A memory in which computer program instructions are stored, and when the computer program instructions are run by the processor, the processor executes the method according to any one of claims 1 to 6.

Images