WO2020258667A1

WO2020258667A1 - Image recognition method and apparatus, and non-volatile readable storage medium and computer device

Info

Publication number: WO2020258667A1
Application number: PCT/CN2019/118187
Authority: WO
Inventors: 王健宗; 赵峰
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-06-26
Filing date: 2019-11-13
Publication date: 2020-12-30
Also published as: CN110458185A

Abstract

Disclosed are an image recognition method and an apparatus, and a non-volatile readable storage medium and a computer device, relating to the technical field of image recognition and able to improve the accuracy of image recognition. The method comprises: using a trained generative network model in a deep convolutional generative adversarial network model to generate counterfeit images on the basis of tampering data; using an image determination sample set formed from the generated counterfeit images and preset real images to train a trained determination network model in the convolutional generative adversarial network model in order to obtain a final determination network model; and using the final determination network model to perform recognition on a target image, and determine whether the target image is a counterfeit image or a real image. The present application is suitable for providing higher reliability in image evidence collection in governmental departments such as public security and courts.

Description

Image recognition method and device, non-volatile readable storage medium, and computer equipment

This application claims the priority of a Chinese patent application filed on June 26, 2019 with the Chinese Patent Office, the application number is 2019105590703, and the application name is "Methods and devices for identifying text data types, storage media, and computer equipment", and the entire content Incorporated in the application by reference.

Technical field

This application relates to the field of image recognition technology, in particular to image recognition methods and devices, non-volatile readable storage media and computer equipment.

Background technique

With the rapid development of computer technology, computer software can produce or splice forged images with vivid details and distinct levels, which are very similar to real images captured by digital cameras and are difficult to distinguish with the naked eye. Forged images are gradually appearing in the political, military, news and other fields of society, bringing great harm to society. Therefore, the forensic research on the authenticity of images is very important.

In the traditional image forensics technology, the active forensics technology needs to add verification information to the image in advance, and the images obtained for most application scenarios do not contain a priori information, so the active forensics technology has great limitations; the existing The passive blind forensics technology mainly relies on image statistical characteristics or shallow feature information, such as gray value, gray change, etc. The existing passive blind forensics technology is very dependent on the selection of shallow features, and the quality of shallow features affects the image The accuracy of the recognition result has a great influence. In addition, because the passive blind forensics technology requires a large number of forged samples, the establishment of the forged sample set generally needs to be completed manually, which consumes a lot of time and energy, and the labor cost is high.

Summary of the invention

In view of this, this application provides an image recognition method and device, a non-volatile readable storage medium, and computer equipment. The main purpose is to solve the existing passive blind forensics technology that relies too much on image statistical characteristics or shallow feature information, and the result of image recognition The technical problems of low accuracy and high labor cost for constructing corresponding forged sample sets.

According to an aspect of the present application, there is provided an image recognition method, which includes:

Use deep convolution to fight against the generative network model trained in the generative network model to generate fake images based on the tampered data;

Use the image discrimination sample set composed of the generated fake image and the preset real image to train the discriminant network model trained in the deep convolutional confrontation generation network model to obtain the final discriminant network model;

The final discriminant network model is used to identify the target image, and it is determined that the target image is a fake image or a real image.

According to another aspect of the present application, there is provided an image recognition device, which includes:

The generation module is used to use the generated network model trained in the deep convolution against the generated network model to generate fake images according to the tampered data;

The training module is used to train the discriminant network model trained in the deep convolutional confrontation generation network model by using the image discrimination sample set composed of the generated fake image and the preset real image to obtain the final discriminant network model;

The recognition module is used to recognize the target image using the final discriminant network model, and determine whether the target image is a fake image or a real image.

According to another aspect of the present application, there is provided a non-volatile readable storage medium having computer readable instructions stored thereon, and the program is executed by a processor to realize the above-mentioned image recognition method.

According to another aspect of the present application, a computer device is provided, including a non-volatile readable storage medium, a processor, and computer readable instructions stored on the non-volatile readable storage medium and running on the processor , When the processor executes the program, the foregoing image recognition method is implemented.

With the above technical solutions, the image recognition method and device, non-volatile readable storage medium, and computer equipment provided in this application are compared with the existing technical solutions based on active forensics technology and passive blind forensics technology to identify the authenticity of images. This application uses the trained generative network model in the deep convolution against the generative network model to generate forged images based on the tampered data, and uses the image discriminant sample set composed of the generated forged images and preset real images to generate deep convolution against The trained discriminant network model in the network model is trained to obtain the final discriminant network model, so that the final discriminant network model can be used to identify the target image and determine whether the target image is a fake image or a real image. It can be seen that the trained generation network model is used to generate forged images that conform to the distribution of image discrimination samples, so that a large number of forged images can be generated from a small number of forged images, which can better solve the technical problem of high labor costs for establishing a forged sample set; in addition, use The final discriminative network model in the deep convolutional confrontation generation network model recognizes the target image, which can better solve the technical problems of passive blind forensics technology, such as excessive reliance on the shallow feature information of the image and the poor robustness of the network model, and effectively ensure the final The accuracy of the discriminant network model to identify the authenticity of the image and the robustness of the final discriminant network model.

The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented in accordance with the content of the specification, and to make the above and other purposes, features and advantages of this application more obvious and understandable. , The following specifically cite the specific implementation of this application.

Description of the drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The exemplary embodiments and descriptions of the application are used to explain the application and do not constitute an improper limitation of the application. In the attached picture:

FIG. 1 shows a schematic flowchart of an image recognition method provided by an embodiment of the present application;

FIG. 2 shows a schematic flowchart of another image recognition method provided by an embodiment of the present application;

Fig. 3 shows a schematic structural diagram of an image recognition device provided by an embodiment of the present application.

Detailed ways

Hereinafter, the application will be described in detail with reference to the drawings and in conjunction with embodiments. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other if there is no conflict.

In the current process of identifying the authenticity of images based on active forensic technology and passive blind forensics technology, the active forensics technology has the limitation that the acquired images do not contain prior information, and the passive blind forensics technology relies too much on image statistical characteristics or shallow Layer feature information has a greater impact on the accuracy of the image recognition result, and the technical problem of high labor cost for constructing the corresponding forged sample set. This embodiment provides an image recognition method, which can effectively avoid the technical problems of low accuracy of image recognition results caused by the existing passive blind forensics technology in the process of recognizing images, and the high labor cost of constructing a corresponding forged sample set. , Thereby effectively improving the accuracy of image recognition. As shown in Figure 1, the method includes:

101. Use the generative network model trained in the deep convolution against the generative network model to generate forged images according to the tampered data.

Deep Convolutional Generative Adversarial Networks (DCGAN: Deep Convolutional Generative Adversarial Networks) includes generative network model and discriminative network model, and training the generative network model and discriminant network model at the same time. On the one hand, the generative network model generates fake and real images through training The gap between them is as small as possible to deceive the discriminative network model; on the other hand, the discriminant network model is trained to make it as accurate as possible to determine the authenticity of the input target image.

In this embodiment, the generation network model in the deep convolutional confrontation generation network DCGAN is a reverse convolutional neural network model, which has 5 layers, specifically:

1) The first layer is the input layer, in order to obey the normal distribution, the number of input layer nodes is consistent with the input data dimension. For example, the input data is 100-dimensional data, and the number of input layer nodes is also 100.

2) The second layer is the deconvolution layer, and its input data is the output result of the first layer. Set the convolution kernel size to 4*4 and the filter to 64*8. After batch regularization, input to the activation In the function, the activation function is the ReLU function.

3) The third layer is the deconvolution layer, and the input data is the output result of the second layer. Set the convolution kernel size to 4*4, the step size to 2*2, and the filter to 64*4. After batch regularization, it is input into the activation function, which is the ReLU function.

4) The fourth layer is the deconvolution layer, and its input data is the output result of the third layer. Set its convolution kernel size to 4*4, step size to 2*2, and 64 filters to perform batch regularization After conversion, it is input into the activation function, which is the ReLU function.

5) The fifth layer is the deconvolution layer. The output result is used to construct the image discriminant sample set of the discriminant network model. Set the convolution kernel size to 4*4, the step size to 2*2, and the filter to 64 , Input into the activation function, which is the Tanh function.

102. Use the image discrimination sample set composed of the generated fake images and preset real images to train the discriminant network model trained in the deep convolutional confrontation generation network model to obtain a final discriminant network model.

In this embodiment, the discriminant network model in the deep convolutional confrontation generation network DCGAN is a convolutional neural network model, with a total of 5 layers, specifically:

1) The first layer is the input layer, and the matrix specification of the input data vector is set to 64*64*3, the size of the convolution kernel is 4*4, and the activation function is LeakyReLU. Among them, the calculation formula of the activation function LeakyReLU is specifically:

Among them, x _i is the input data vector, y _i is the processed data vector obtained after the activation function is calculated and output, and a _i is a fixed parameter in the interval (1, +∞).

2) The second layer is a convolutional layer, and its input data is the output result of the first layer. Set its convolution kernel size to 4*4 and filter to 64*2. After batch normalization, input into the activation function , The activation function is LeakyReLU.

3) The third layer is a convolutional layer, and its input data is the output result of the second layer. Set its convolution kernel size to 4*4, step size to 2*2, filter to 64*4, batch After normalization, it is input into the activation function, which is LeakyReLU.

4) The fourth layer is a convolutional layer, and its input data is the output result of the third layer. Set its convolution kernel size to 4*4, step size to 2*2, filter to 64*8, batch After normalization, it is input into the activation function, which is LeakyReLU.

5) The fifth layer is a convolutional layer, and the size of the convolution kernel is set to 4*4, and the filter is one, and the output result is obtained after smoothing operation.

103. Use the final discriminant network model to recognize the target image, and determine whether the target image is a fake image or a real image.

In this embodiment, the target image is input into the final discriminant network model. If the output result is infinitely close to 0, the target image is determined to be a fake image; if the output result is infinitely close to 1, the target image is determined to be a real image. In the actual application scenario, set the forgery discrimination value to a. If the output result is in the range of (0, a], the target image is determined to be a forged image; if the output result is in the range of [b, 1), then the target image is determined The target image is a real image, and the forgery discriminant value and the true discriminant value are not specifically limited here.

For this embodiment, according to the above scheme, the deep convolution against the generative network model trained in the generative network model can be used to generate a forged image based on the tampered data, and an image discrimination sample composed of the generated forged image and a preset real image can be used Set to train the discriminant network model trained in the deep convolutional confrontation generation network model to obtain the final discriminant network model, so that the final discriminant network model can be used to identify the target image and determine whether the target image is a fake image or a real image Compared with the existing technical solutions based on active forensics technology and passive blind forensics technology to identify the authenticity of images, this embodiment enables the discriminant network model to have better discriminative ability through the early learning and training, and the generation of the network model remains unchanged In the case of, the discriminant network model can still be trained separately, so that the discriminant network model can adaptively learn its internal statistical laws from the image discriminant sample set, thereby improving the generalization ability of the final discriminant network model.

Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully explain the specific implementation process of this embodiment, another image recognition method is provided. As shown in FIG. 2, the method includes:

201. Use the first discriminant sample set composed of noise variables and real images to train the initial discriminant network model in the deep convolutional confrontation generation network model to obtain the first discriminant network model.

In this embodiment, the initial discriminant network model is trained to obtain the first discriminant network model, which specifically includes: using noise variables and real images as the input data of the initial discriminant network model, and using the obtained output result as the logistic regression output function Further, use the first loss function to obtain the loss value d_loss_real of the real image, and use the gradient ascent algorithm to train the initial network parameters θ _d so that the output result is infinitely close to 1, thereby obtaining the first discriminant network model.

Among them, the first loss function is:

Wherein, x ⁱ and z ⁱ are the real image and the noise variance, m is the number of samples of the first judgment, D (x ⁱ⁾ is the initial network model is ^{determined, D (G (z i)} ) to generate an initial network model.

The calculation formula of using the gradient ascent algorithm to train the initial network parameters θ _d is:

When the output result is infinitely close to 1, the optimized initial network parameter is used as the first network parameter.

202. Train the first discriminant network model by using a second discriminant sample set composed of noise variables and fake images to obtain a second discriminant network model.

In this embodiment, the initialization of the discriminant network model is trained to obtain the first discriminant network model, which specifically includes: using noise variables and fake images as the input data of the first discriminant network model, and using the output result as the logistic regression output function Input data; further, use the second loss function to obtain the loss value d_loss_fake of the fake image, and use the gradient descent algorithm to train the first network parameter θ _d so that the output result is infinitely close to 0, thereby determining the second discriminant network model The second network parameter θ _d , and the second discriminant network model.

Among them, the second loss function is:

Wherein, y ⁱ forged image, m is the number of samples of the second judgment, D (x ⁱ⁾ is determined as a first network ^{model, D (G (z i)} ) to generate an initial network model.

The calculation formula for training the first network parameter θ _d using the gradient descent algorithm is:

In practical application scenarios, the obtained second discriminant network model can be used as a trained discriminant network model, so as to use the fake image generated by the trained generation network model and the preset real image to form an image discriminant sample set for this training The good discriminant network model is further trained to obtain the final discriminant network model to realize the recognition of fake images and real images.

203. Use a third discriminant sample set composed of noise variables and real images to train the second discriminant network model to obtain a third discriminant network model.

204. Use a fourth discriminant sample set composed of noise variables and fake images to train the third discriminant network model to obtain a trained discriminant network model.

In this embodiment, the third discriminant sample set can be the same as the first discriminant sample set, or it can be adjusted accordingly according to actual application needs; accordingly, the fourth discriminant sample set and the second discriminant sample set can be the same, or Adjust accordingly according to actual application needs, and the number of first discriminant samples, the number of second discriminant samples, the number of third discriminant samples, and the number of fourth discriminant samples can also be adjusted according to the needs of actual applications. The discriminant sample set and the first discriminant sample set, and the fourth discriminant sample set and the second discriminant sample set, and the number of the first discriminant sample, the second discriminant sample number, the third discriminant sample number, and the fourth discriminant sample number are specifically limited .

205. Use the first generated sample set composed of noise variables to train the initial generation network model in the deep convolutional confrontation generation network model to obtain a trained generation network model.

In this embodiment, training the initial generation network model to obtain a trained network model specifically includes: using the noise variable used for training the generation network model as the input data of the initial generation network model, for example, the noise variable is 100 Dimensional data, and use the output result as the input data of the logistic regression output function; further, use the loss function of the generated network model to obtain the forged image loss value d_loss, and use the gradient descent algorithm to minimize the loss of the initial generated network model Value g_loss, the network parameters θ _{g of the} trained generative network model are trained, so that the output fake image is input to the trained discriminant network model, and the output result is infinitely close to 1, so that the trained generative network model is obtained. To reduce the discriminative ability of the trained discriminant network model.

Among them, the loss function of the generated network model is:

The formula for training network parameters θ _g using the gradient descent algorithm is:

206. Use the deep convolution against the generative network model trained in the generative network model to generate a forged image according to the tampered data.

In actual application scenarios, in order to achieve better results for the discriminative ability of the discriminant network model, the trained generative network model can be further optimized. For example, use tampering data to further optimize the training of the trained generative network model to obtain an optimized generative network model, so as to further generate fake images based on the tampered data, and construct image discriminant sample sets to realize the deep convolutional confrontation generation network Further optimization of the discriminative network model trained in the model.

207. Use the image discrimination sample set composed of the generated fake images and preset real images to train the discriminant network model trained in the deep convolutional confrontation generation network model to obtain a final discriminant network model.

In this embodiment, the fake image generated by the trained generation network model or the optimized generation network model and the acquired real image are used to construct an image discrimination sample set. Use the constructed image discriminant sample set to train the trained discriminant network model. By minimizing the loss value d_loss of the trained discriminant network model, the network parameter θ _{d of the} final discriminant network model is obtained, thereby obtaining the final discriminant network model.

208. Recognize and intercept the acquired target feature in the image to be recognized to obtain a target image corresponding to the target feature.

209. Acquire image deep features of the target image.

In this embodiment, the acquired image to be recognized is preprocessed, specifically, the target feature in the image to be recognized is recognized, the recognized target feature is intercepted, and the intercepted image is sized according to a certain ratio Adjust to obtain the target image used to characterize the target feature. Among them, according to the needs of actual application scenarios, the deep image features of the target image can be contour, texture, brightness, color, and combinations thereof, as well as corresponding high-level semantics and combinations thereof.

210. Recognize the target image according to the acquired deep image features, and determine that the target image is a forged image or a real image.

In order to illustrate the specific implementation of step 210, as a preferred embodiment, step 210 may specifically include: if the tampering data is copy-and-paste type image data, fuzzy retouch type image data, or computer-generated type image data, correspondingly, The final discriminant network model is used to identify the target image, and it is determined that the target image is a forged image, and the corresponding forged image types are copy and paste type images, fuzzy retouch type images, or computer-generated type images.

In this embodiment, if the noise variable used to train the discriminant network model does not set the data type, only the trained generation network model or the tampered data input by the optimized generation network model is set to the copy and paste type, Either the fuzzy retouching type or the computer-generated type, the final discriminant network model is used to determine the target image is a fake image or a real image, and the image types used to determine the target image to be a forged image are copy and paste type image and fuzzy retouch type respectively Image, or computer-generated type image.

According to the needs of actual application scenarios, the data type of the noise variable used to train the discriminant network model can also be set to copy and paste type, or fuzzy retouch type, or computer-generated type, so as to make the final discriminant network model more stable , Quickly determine the authenticity of the target image, and provide higher reliability for the image collection of public security, courts and other departments.

In addition, because copy-and-paste type images, fuzzy retouch type images, or computer-generated type images have common deep image features, they are used to train and discriminate the type of noise variable of the network model, and the trained generation network model or the optimized generation The tampered data input by the network model does not need to set the data type. The final discriminating network model can also be used to determine whether the target image is a forged image or a real image, and the image types used to determine the target image as a forged image are copy and paste types. Image, blur retouch type image, or computer generated type image. There is no specific limitation here.

By applying the technical solution of this embodiment, using the deep convolution against the generative network model trained in the generative network model, generating a forged image based on the tampered data, and using the image discrimination sample composed of the generated forged image and the preset real image Set to train the discriminant network model trained in the deep convolutional confrontation generation network model to obtain the final discriminant network model, so that the final discriminant network model can be used to identify the target image and determine whether the target image is a fake image or a real image . Compared with the existing technical solutions based on active forensics technology and passive blind forensics technology to identify the authenticity of images, this embodiment generates a large number of forged images through a small amount of forged images, which better solves the high labor cost of establishing a forged sample set. The problem, as well as the use of the final discriminant network model in the deep convolutional generation network model to identify the target image, can effectively ensure the accuracy of the final discriminant network model to identify the authenticity of the image and the robustness of the final discriminant network model.

Further, as a specific implementation of the method in FIG. 1, an embodiment of the present application provides an image recognition device. As shown in FIG. 3, the device includes: a generation module 35, a training module 36, and a recognition module 37.

The generation module 35 can be used to use the generated network model trained in the deep convolution against the generation network model to generate fake images based on the tampered data; the generation module 35 is a basic module for the device to recognize whether the image to be recognized is a fake image or a real image .

The training module 36 can be used to train the discriminant network model trained in the deep convolutional confrontation generation network model by using the image discrimination sample set composed of the generated fake image and the preset real image to obtain the final discriminant network model The training module 36 is the main functional module for the device to recognize that the image to be recognized is a fake image or a real image, and is also a core functional module of the device.

The recognition module 37 can be used to recognize the target image using the final discriminant network model, and determine that the target image is a forged image or a real image; the recognition module 37 is the main part of the device to recognize that the image to be recognized is a forged image or a real image. The functional module is also the core functional module of the device.

In a specific application scenario, it also includes a first discriminant training module 31 or a second discriminant training module 32. The first discriminant training module 31 can be used to use the first discriminant sample set composed of noise variables and real images to convolve the depth Training against the initial discriminant network model in the generative network model to obtain a first discriminant network model; and, using a second discriminant sample set composed of noise variables and fake images to train the first discriminant network model, and obtain the training The discriminative network model.

The second discriminant training module 32 can be used to train the initial discriminant network model in the deep convolutional confrontation generation network model by using the first discriminant sample set composed of noise variables and real images to obtain the first discriminant network model; and, Use the second discriminant sample set composed of noise variables and fake images to train the first discriminant network model to obtain the second discriminant network model; and use the third discriminant sample set composed of noise variables and real images to compare the results The second discriminant network model is trained to obtain a third discriminant network model; and the third discriminant network model is trained using a fourth discriminant sample set composed of noise variables and fake images to obtain a trained discriminant network model .

In specific application scenarios, it also includes a first generation training module 33, which can be used to train the initial generation network model in the deep convolutional confrontation generation network model by using the first generation sample set composed of noise variables, and get well trained The generative network model.

In a specific application scenario, a preprocessing module 34 is also included, which can be used to identify and intercept the target feature in the acquired image to be recognized, to obtain a target image corresponding to the target feature.

In a specific application scenario, if the tampering data is copy and paste type image data, fuzzy retouch type image data, or computer-generated type image data, correspondingly, the final discriminant network model is used to identify the target image to determine the The target image is a forged image, and the corresponding forged image types are copy and paste type images, fuzzy retouch type images, or computer-generated type images.

In a specific application scenario, the recognition module 37 can be specifically used to obtain the deep image features of the target image; recognize the target image according to the acquired deep image features, and determine whether the target image is a fake image or a real image. image.

It should be noted that, for other corresponding descriptions of the functional units involved in the image recognition device provided in the embodiment of the present application, reference may be made to the corresponding descriptions in FIG. 1 and FIG. 2, and details are not repeated here.

Based on the above-mentioned method shown in Figure 1 and Figure 2, correspondingly, an embodiment of the present application also provides a non-volatile readable storage medium on which computer readable instructions are stored, and the program is executed when the processor is executed. The image recognition method shown in Figure 1 and Figure 2 described above.

Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, and the software product can be stored in a non-volatile non-volatile readable storage medium (can be CD-ROM, U disk, mobile hard disk) Etc.), including several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in each implementation scenario of this application.

Based on the methods shown in Figures 1 and 2 and the virtual device embodiment shown in Figure 3, in order to achieve the above objectives, the embodiments of the present application also provide a computer device, which can be a personal computer, a server, or a network. The physical device includes a non-volatile readable storage medium and a processor; the non-volatile readable storage medium is used to store computer readable instructions; and the processor is used to execute computer readable instructions to achieve the above Figure 1 and Figure 2 show the image recognition method.

Optionally, the computer device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a Wi-Fi module, and so on. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, and the like. The network interface can optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.

Those skilled in the art can understand that the structure of a computer device provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or arrange different components.

The non-volatile readable storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of computer equipment, and supports the operation of information processing programs and other software and/or programs. The network communication module is used to implement communication between various components in the non-volatile readable storage medium and communication with other hardware and software in the physical device.

Through the description of the foregoing implementation manners, those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary general hardware platform, or by hardware. By applying the technical solution of the present application, compared with the existing technical solutions based on active forensics technology and passive blind forensics technology to identify the authenticity of images, this embodiment can generate a large number of forged images from a small amount of forged images; and, use depth volume The final discriminant network model in the product confrontation generation network model recognizes the target image, which can effectively ensure the accuracy of the final discriminant network model to recognize the authenticity of the image and the robustness of the final discriminant network model.

Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of preferred implementation scenarios, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing this application. Those skilled in the art can understand that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the description of the implementation scenario, or can be changed to be located in one or more devices different from the implementation scenario. The modules of the above implementation scenarios can be combined into one module or further divided into multiple sub-modules.

The above serial number of this application is only for description, and does not represent the merits of implementation scenarios. The above disclosures are only a few specific implementation scenarios of the application, but the application is not limited to these, and any changes that can be thought of by those skilled in the art should fall into the protection scope of the application.

Claims

An image recognition method, characterized in that it comprises:

Use deep convolution to fight against the generative network model trained in the generative network model to generate fake images based on the tampered data;

Use the image discrimination sample set composed of the generated fake image and the preset real image to train the discriminant network model trained in the deep convolutional confrontation generation network model to obtain the final discriminant network model;

The final discriminant network model is used to identify the target image, and it is determined that the target image is a fake image or a real image.
The method according to claim 1, characterized in that, before the generating network model trained in the deep convolution confrontation generating network model is used to generate the forged image according to the tampered data, the method specifically further comprises:

Use the first discriminant sample set composed of noise variables and real images to train the initial discriminant network model in the deep convolutional confrontation generation network model to obtain the first discriminant network model;

The first discriminant network model is trained by using a second discriminant sample set composed of noise variables and fake images to obtain a trained discriminant network model.
The method according to claim 1, characterized in that, before the generating network model trained in the deep convolution confrontation generating network model is used to generate the forged image according to the tampered data, the method specifically further comprises:

Use the first discriminant sample set composed of noise variables and real images to train the initial discriminant network model in the deep convolutional confrontation generation network model to obtain the first discriminant network model;

Training the first discriminant network model by using a second discriminant sample set composed of noise variables and fake images to obtain a second discriminant network model;

Training the second discriminant network model by using a third discriminant sample set composed of noise variables and real images to obtain a third discriminant network model;

The third discriminant network model is trained by using a fourth discriminant sample set composed of noise variables and fake images to obtain a trained discriminant network model.
The method according to claim 1, characterized in that, before the generating network model trained in the deep convolution confrontation generating network model is used to generate the forged image according to the tampered data, the method specifically further comprises:

The first generation sample set composed of noise variables is used to train the initial generation network model in the deep convolutional confrontation generation network model to obtain the trained generation network model.
The method according to claim 1, wherein the step of using the final discriminant network model to identify the target image, and before determining that the target image is a forged image or a real image, specifically further comprises:

The target feature in the acquired image to be recognized is recognized and intercepted to obtain a target image corresponding to the target feature.
The method according to claim 1, wherein if the tampering data is copy and paste type image data, fuzzy retouch type image data, or computer-generated type image data, correspondingly, use the final discriminant network model to compare the target image Recognition is performed, and it is determined that the target image is a forged image, and the corresponding forged image types are copy and paste type images, fuzzy retouch type images, or computer-generated type images.
The method according to any one of claims 1 to 6, wherein said using the final discriminant network model to recognize the target image and determine whether the target image is a fake image or a real image specifically comprises:

Acquiring image deep features of the target image;

The target image is identified according to the acquired deep image features, and it is determined that the target image is a fake image or a real image.
An image recognition device, characterized by comprising:

The generation module is used to use the generated network model trained in the deep convolution against the generated network model to generate fake images according to the tampered data;

The training module is used to train the discriminant network model trained in the deep convolutional confrontation generation network model by using the image discrimination sample set composed of the generated fake image and the preset real image to obtain the final discriminant network model;

The recognition module is used to recognize the target image using the final discriminant network model, and determine whether the target image is a fake image or a real image.
The device according to claim 8, further comprising a first discriminant training module, which specifically comprises:

Use the first discriminant sample set composed of noise variables and real images to train the initial discriminant network model in the deep convolutional confrontation generation network model to obtain the first discriminant network model;

The first discriminant network model is trained by using a second discriminant sample set composed of noise variables and fake images to obtain a trained discriminant network model.
The device according to claim 8, further comprising a second discriminant training module, specifically comprising:

Use the first discriminant sample set composed of noise variables and real images to train the initial discriminant network model in the deep convolutional confrontation generation network model to obtain the first discriminant network model;

Training the first discriminant network model by using a second discriminant sample set composed of noise variables and fake images to obtain a second discriminant network model;

Training the second discriminant network model by using a third discriminant sample set composed of noise variables and real images to obtain a third discriminant network model;

The third discriminant network model is trained by using a fourth discriminant sample set composed of noise variables and fake images to obtain a trained discriminant network model.
The device according to claim 8, further comprising a first generating training module, which specifically comprises:

The first generation sample set composed of noise variables is used to train the initial generation network model in the deep convolutional confrontation generation network model to obtain the trained generation network model.
The device according to claim 8, further comprising a pre-processing module, specifically comprising:

The target feature in the acquired image to be recognized is recognized and intercepted to obtain a target image corresponding to the target feature.
The device according to claim 8, wherein if the tampering data is copy and paste type image data, fuzzy retouch type image data, or computer-generated type image data, correspondingly, the final discriminant network model is used to compare the target image Recognition is performed, and it is determined that the target image is a forged image, and the corresponding forged image types are copy and paste type images, fuzzy retouch type images, or computer-generated type images.
The device according to any one of claims 8-13, wherein the identification module specifically comprises:

Acquiring image deep features of the target image;

The target image is identified according to the acquired deep image features, and it is determined that the target image is a fake image or a real image.
A non-volatile readable storage medium, on which computer readable instructions are stored, characterized in that, when the program is executed by a processor, an image recognition method is realized, including:

Use deep convolution to fight against the generative network model trained in the generative network model to generate fake images based on the tampered data;

Use the image discrimination sample set composed of the generated fake image and the preset real image to train the discriminant network model trained in the deep convolutional confrontation generation network model to obtain the final discriminant network model;

The final discriminant network model is used to identify the target image, and it is determined that the target image is a fake image or a real image.
The non-volatile readable storage medium according to claim 15, characterized in that, before the generating network model trained in the generating network model using the deep convolution confrontation, before generating the forged image according to the tampered data, it specifically further comprises:

Use the first discriminant sample set composed of noise variables and real images to train the initial discriminant network model in the deep convolutional confrontation generation network model to obtain the first discriminant network model;

Training the first discriminant network model by using a second discriminant sample set composed of noise variables and fake images to obtain a second discriminant network model;

Training the second discriminant network model by using a third discriminant sample set composed of noise variables and real images to obtain a third discriminant network model;

The third discriminant network model is trained by using a fourth discriminant sample set composed of noise variables and fake images to obtain a trained discriminant network model.
The non-volatile readable storage medium according to claim 15, wherein if the tampering data is copy and paste type image data, blur retouch type image data, or computer-generated type image data, correspondingly, use the final The discriminant network model of, recognizes the target image, and determines that the target image is a forged image, and the corresponding forged image types are copy and paste type images, fuzzy retouch type images, or computer-generated type images.
A computer device, including a non-volatile readable storage medium, a processor, and computer readable instructions stored on the non-volatile readable storage medium and running on the processor, characterized in that the processor The method for realizing image recognition when executing the program includes:

Use deep convolution to fight against the generative network model trained in the generative network model to generate fake images based on the tampered data;

Use the image discrimination sample set composed of the generated fake images and preset real images to train the discriminant network model trained in the deep convolutional confrontation generation network model to obtain the final discriminant network model;

The final discriminant network model is used to identify the target image, and it is determined that the target image is a fake image or a real image.
18. The computer device according to claim 18, wherein the generating network model trained in the deep convolution confrontation generating network model, before generating the forged image according to the tampered data, specifically further comprises:

Use the first discriminant sample set composed of noise variables and real images to train the initial discriminant network model in the deep convolutional confrontation generation network model to obtain the first discriminant network model;

Training the first discriminant network model by using a second discriminant sample set composed of noise variables and fake images to obtain a second discriminant network model;

Training the second discriminant network model by using a third discriminant sample set composed of noise variables and real images to obtain a third discriminant network model;

The third discriminant network model is trained by using a fourth discriminant sample set composed of noise variables and fake images to obtain a trained discriminant network model.
The computer device according to claim 18, wherein if the tampering data is copy-and-paste type image data, fuzzy retouch type image data, or computer-generated type image data, correspondingly, the final discriminating network model is used to target the target The image is recognized, and it is determined that the target image is a forged image, and the corresponding forged image type is a copy and paste type image, a fuzzy retouch type image, or a computer-generated type image.