CN111881944A - Method, electronic device and computer readable medium for image authentication - Google Patents
Method, electronic device and computer readable medium for image authentication Download PDFInfo
- Publication number
- CN111881944A CN111881944A CN202010651813.2A CN202010651813A CN111881944A CN 111881944 A CN111881944 A CN 111881944A CN 202010651813 A CN202010651813 A CN 202010651813A CN 111881944 A CN111881944 A CN 111881944A
- Authority
- CN
- China
- Prior art keywords
- target image
- trained
- image
- inputting
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000013145 classification model Methods 0.000 claims abstract description 26
- 230000008569 process Effects 0.000 claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 23
- 238000013528 artificial neural network Methods 0.000 claims description 77
- 238000012549 training Methods 0.000 claims description 42
- 230000004044 response Effects 0.000 claims description 15
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 7
- 230000006870 function Effects 0.000 description 20
- 238000010586 diagram Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 8
- 230000004913 activation Effects 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 239000000969 carrier Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
Embodiments of the present disclosure disclose methods, electronic devices, and computer-readable media for image authentication. One embodiment of the method comprises: acquiring a first target image; inputting the first target image into a pre-trained detection model to generate a second target image; inputting the second target image into a pre-trained classification model to generate an identification result set of the second target image; based on the set of authentication results, a category of the first target image is determined. The method utilizes the pre-trained detection model to generate the second target characteristic, does not need manual intervention, and automatically acquires the effective image target area. And the identification result set is automatically generated by utilizing the pre-trained classification model, and the category of the first target image is automatically determined according to the identification result set, so that the automation degree and the convenience of the image identification process are improved.
Description
Technical Field
The disclosed embodiments relate to the field of artificial intelligence, and in particular, to a method, an electronic device, and a computer-readable medium for image recognition.
Background
Image recognition is an important field of artificial intelligence, and refers to a technology for processing, analyzing and understanding images by using a computer to recognize various different patterns of targets and objects. Different from the methods of identification through biochemical components and identification based on near-infrared hyperspectral images, the image identification method is convenient and quick, and does not need professional equipment for assistance. The traditional image identification method needs a manual method to design and extract the features in the image, the process of feature extraction is complex and difficult to popularize in other images, and the identification accuracy is low. The deep learning algorithm is applied in the field of image recognition, the features can be extracted and classified into a whole, and the features are not required to be designed manually, so that the identification of a plurality of types of images can be realized at a high accuracy, and the method can be conveniently popularized to the identification application of other types of images.
Disclosure of Invention
The embodiment of the disclosure provides an image identification method.
In a first aspect, an embodiment of the present disclosure provides a method for image authentication, where the method includes: acquiring a first target image; inputting the first target image into a pre-trained detection model to generate a second target image; inputting the second target image into a pre-trained classification model to generate an identification result set of the second target image; based on the set of authentication results, a category of the first target image is determined.
In some embodiments, the method further comprises: and sending the category of the first target image to the display supporting equipment, and controlling the equipment to display the category.
In some embodiments, inputting the first target image into a pre-trained detection model, generating the second target image, comprises: inputting a first target image into a pre-trained detection model to generate a process image; and cutting the process image to generate a second target image.
In some embodiments, the pre-trained detection model includes a convolutional layer, a region proposal layer, a matching layer, a full convolutional layer, and an output layer; and inputting the first target image into a pre-trained detection model to generate a process image, comprising: inputting the first target image into the convolutional layer to generate a first feature map; inputting the first feature map into a region suggestion layer to generate a candidate region map; inputting the first feature map and the candidate region map into a matching layer to generate a second feature map; inputting the second feature map into the full convolution layer to generate a third feature map; and inputting the third feature map into an output layer to generate a process image.
In some embodiments, the pre-trained classification model includes a first number of pre-trained neural networks, wherein the pre-trained neural networks are residual networks, the residual networks being comprised of a second number of residual modules, the residual modules generating an output using the following equation: y ═ F (x, { W)iX is the input of the residual block, y is the output of the residual block, F () is the residual function, W is the weight matrix, i is the layer count in the residual block, WiWeight matrix representing i-th layer, { WiDenotes the set of weight matrices for all layers in the residual block.
In some embodiments, wherein the first number of pre-trained neural networks corresponds to the first number of predetermined classes.
In some embodiments, the pre-trained neural network is obtained by: determining a network structure of an initial neural network and initializing network parameters of the initial neural network; acquiring a training sample set, wherein the training samples comprise sample images and sample categories corresponding to the sample images; selecting samples from the sample set, and performing the following training steps: inputting a sample image of the selected sample into an initial neural network to obtain the category of the selected sample; comparing the selected sample category with the corresponding sample category; determining whether the initial neural network reaches a preset optimization target according to the comparison result; in response to determining that the initial neural network reaches the optimization goal, taking the initial neural network as a pre-trained neural network after training is completed; in response to determining that the initial neural network is not trained, adjusting relevant parameters in the initial neural network, and re-selecting samples from the sample set, using the adjusted initial neural network as the initial neural network, and performing the training step again.
In some embodiments, inputting the second target image into a pre-trained classification model, and generating the set of discrimination results for the second target image comprises: inputting the second target image into a pre-trained classification model to obtain an output result set; and determining an output result set of the pre-trained classification model as an identification result set of the second target image, wherein the output result set of the pre-trained classification model is a set of output results of a first number of pre-trained neural networks, the identification result is an output result of the pre-trained neural networks, and the identification result set comprises the first number of identification results.
In some embodiments, determining the category of the first target image based on the set of authentication results comprises: in response to all values in the set of authentication results being negative values, determining that the category of the first target image is null; and in response to the values in the identification result set not being all negative values, determining the category corresponding to the maximum value in the identification result set as the category of the first target image.
In a second aspect, an embodiment of the present disclosure provides a terminal device, where the terminal device includes: one or more processors; a storage device for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method as described in any implementation manner of the first aspect.
The disclosed embodiments provide a method, an electronic device and a computer readable medium for image authentication. One embodiment of the method comprises: acquiring a first target image; inputting the first target image into a pre-trained detection model to generate a second target image; inputting the second target image into a pre-trained classification model to generate an identification result set of the second target image; based on the set of authentication results, a category of the first target image is determined.
One of the above-described various embodiments of the present disclosure has the following advantageous effects: based on the first target image, the second target image is automatically obtained by utilizing the pre-trained detection model without manually determining the key target area in the first target image. And classifying the second target image by using a pre-trained classification model to obtain an identification result set of the second target image. Based on the authentication set, a category of the first target image is automatically generated. The embodiment of the disclosure generates the second target feature by using the pre-trained detection model, and automatically acquires the effective image target area without manual intervention. And the identification result set is automatically generated by utilizing the pre-trained classification model, and the category of the first target image is automatically determined according to the identification result set, so that the automation degree and the convenience of the image identification process are improved.
Drawings
Other features, objects and advantages of the disclosure will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an architectural diagram of an exemplary system in which some embodiments of the present disclosure may be applied;
FIG. 2 is a flow diagram of some embodiments of a method of image authentication according to the present disclosure;
FIG. 3 is a flow chart of training steps for training a neural network according to the present disclosure;
fig. 4 is a schematic block diagram of a terminal device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 illustrates an exemplary system architecture 100 to which embodiments of the disclosed method of image authentication may be applied.
As shown in fig. 1, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as an image recognition application, a data analysis application, a natural language processing application, and the like.
The terminal apparatuses 101, 102, and 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various terminal devices having a display screen, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the above-listed terminal apparatuses. Which may be implemented as multiple software or software modules (e.g., to provide image input, text input, etc.), or as a single software or software module. And is not particularly limited herein.
The server 105 may be a server that provides various services, such as a server that performs processing such as recognition of images input by the terminal apparatuses 101, 102, 103. The server may perform processing such as recognition on the received image and feed back a processing result (e.g., a result of the recognition) to the terminal device.
It should be noted that the method for image authentication provided by the embodiment of the present disclosure is generally performed by the server 105, and accordingly, the device for displaying is generally disposed in the server 105.
It should be noted that the local area of the server 105 may also directly store the image, and the server 105 may directly extract the local image to obtain the recognition result through the recognition method, in this case, the exemplary system architecture 100 may not include the terminal devices 101, 102, 103 and the network 104.
It should be noted that the terminal devices 101, 102, and 103 may also be installed with an image recognition application, and in this case, the method of image authentication may also be executed by the terminal devices 101, 102, and 103. At this point, the exemplary system architecture 100 may also not include the server 105 and the network 104.
The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server is software, it may be implemented as a plurality of software or software modules (for example, a service for providing image authentication), or may be implemented as a single software or software module. And is not particularly limited herein.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to fig. 2, a flow 200 of some embodiments of a method of image authentication in accordance with the present disclosure is shown. The image identification method comprises the following steps:
In some embodiments, the subject of the method of image authentication (e.g., the terminal device shown in fig. 1) may acquire a first target image. Among them, images are a kind of similarity, vivid description or portrayal of objective objects, and are the most commonly used information carriers in human social activities. The image is all pictures with visual effect. In particular, the first target image may be an image of an apple.
In some embodiments, the performing agent inputs the first target image into a pre-trained detection model to generate a process image. The pre-trained detection model includes a convolutional layer, a region proposal layer, a matching layer, a full convolutional layer, and an output layer.
In some optional implementations of some embodiments, the executing subject inputs the first target image into a pre-trained detection model, and an output of the pre-trained detection model is used as the process image. The process of generating a process image from a pre-trained detection model may include the steps of:
first, a first target image is input into the convolutional layer to generate a first feature map.
And secondly, inputting the first feature map into the region suggestion layer to generate a candidate region map.
Specifically, the region suggestion layer performs sliding window in the first feature map through windows or anchor points with different multiples and length-width ratios to generate a candidate region map. Specifically, 3 windows may be defined. The size of the first window may be 16 pixels, including 3 windows respectively representing length-width ratios of 1:1, 1:2, and 2: 1. The size of the second window may be 8 pixels, including 3 windows respectively representing length-width ratios of 1:1, 1:2, and 2: 1. The size of the third window can be 32 pixel points, including 3 windows respectively representing the length-width ratios of 1:1, 1:2 and 2: 1. The region suggestion layer performs sliding window on the first feature map by using the 3 windows, and calculates the intersection ratio by using the following formula respectively:
wherein IoU represents the cross-over ratio, A represents the window generated by the region suggestion layer, B represents the correct window in the sample database used for pre-training, S represents the areaA∩BDenotes the area of overlap of A and B, SA∪BThe union area after merging a and B is shown. In response to the value of IoU being greater than "0.5", the region a is included in the candidate region to obtain a candidate region map.
And thirdly, inputting the first feature map and the candidate region map into a matching layer to generate a second feature map.
Specifically, the matching layer realizes pooling of the candidate region maps, so that the candidate region maps with different sizes are pooled to obtain the second feature map with a fixed size. Optionally, the pooling operation may use a bilinear interpolation algorithm to obtain the interpolated second feature map. And marking the part which is not subjected to interpolation processing in the second feature map as a candidate region.
And fourthly, inputting the second characteristic diagram into the full convolution layer to generate a third characteristic diagram.
And fifthly, inputting the third feature diagram into the output layer to generate a process image.
In some optional implementations of some embodiments, the performing the subject cutting procedure image generates a second target image. The outermost edges of the candidate areas of the mark form a bounding box in the process image. The outermost edge may be defined according to the abscissa minimum and maximum values and the ordinate minimum and maximum values of all pixels inside the candidate region of the mark. The outermost edges form a rectangle. The candidate regions are cut out of the process image using a photo-processing toolkit based on the rectangular box. The width of the rectangular frame is set to a uniform pixel size. Specifically, the width may be 300 pixels. And the height of the rectangular frame is correspondingly transformed according to the aspect ratio of the candidate region picture so as to generate a second target image.
In some embodiments, the performing subject inputs the second target image into a pre-trained classification model. Optionally, the pre-trained classification model comprises a first number of pre-trained neural networks. The first number of pre-trained neural networks corresponds to a first number of pre-determined image classes.
Optionally, the pre-trained neural network is a residual error network. The residual network is composed of a second number of residual modules. Wherein each residual module generates an output using the following equation:
y＝F(x,{Wi})+x，
wherein x is the input of the residual module, y is the output of the residual module, F () is the residual function, W is the weight matrix, i is the layer count in the residual module, W is the layer count in the residual moduleiWeight matrix representing i-th layer, { WiDenotes the set of weight matrices for all layers in the residual block. Specifically, the residual function F () is expressed as the following equation:
F(x)＝W2σ(W1x)，
wherein x is the input of the residual module, W is a weight matrix, W1Weight matrix, W, representing layer 12The weight matrix representing layer 2, σ represents the activation function. In particular, the activation function may be a function that runs on a neuron of the artificial neural network, responsible for mapping the input of the neuron to the output. Specifically, the activation function may be a ReLu function, expressed as:
σ(x)＝max(0,x)
where σ denotes an activation function, x denotes an arbitrary integer input, and max () is a process of finding the maximum value.
In some optional implementations of some embodiments, the executing subject inputs the second target image into a pre-trained classification model, and obtains an output result set. The pre-trained classification model includes a first number of pre-trained neural networks. The execution subject inputs the second target image into a first number of pre-trained neural networks to obtain a first number of output results. The output result set includes a first number of output results. And determining an output result set of the pre-trained classification model as an identification result set of the second target image. Wherein the set of output results of the pre-trained classification model is a set of output results of a first number of pre-trained neural networks. The discrimination result is an output result of a pre-trained neural network, and the discrimination result set includes a first number of discrimination results.
In some embodiments, the executing entity determines the category of the first target image based on the set of authentication results.
In response to all of the values in the set of authentication results being negative, determining that the category of the first target image is null. Specifically, the category of the first target image does not belong to a predetermined image category. And in response to the values in the identification result set not being all negative values, determining the category corresponding to the maximum value in the identification result set as the category of the first target image.
Optionally, the execution subject sends the category of the first target image to a device supporting display, and controls the device to display the category. The display-supporting device may be a device that is in communication connection with the execution subject, and may display an image category according to the received information. For example, the device displays category information of "apple of the first kind", wherein the first kind may indicate that the origin of the apple is "Shandong province". For another example, the device displays category information of "apple of the second category", wherein the second category may indicate that the origin of the apple is "Hebei province". The automatic display mode emphasizes the category condition of the first target image, thereby being beneficial to improving the accuracy and convenience of the judgment and decision of the user about the first target image.
One embodiment presented in fig. 2 has the following beneficial effects: based on the first target image, the second target image is automatically obtained by utilizing the pre-trained detection model without manually determining the key target area in the first target image. And classifying the second target image by using a pre-trained classification model to obtain an identification result set of the second target image. Based on the authentication set, a category of the first target image is automatically generated. The embodiment of the disclosure generates the second target feature by using the pre-trained detection model, and automatically acquires the effective image target area without manual intervention. And the identification result set is automatically generated by utilizing the pre-trained classification model, and the category of the first target image is automatically determined according to the identification result set, so that the automation degree and the convenience of the image identification process are improved.
With continued reference to FIG. 3, a flow 300 of one embodiment of the training step of pre-training a neural network is shown, in accordance with the present disclosure. The training step may include the steps of:
In this embodiment, the execution subject of the training step may be the same as or different from the execution subject of the method of image authentication (e.g., the terminal device shown in fig. 1). If the network structure information is the same as the network parameter information, the main body of the training step can store the trained network structure information and the parameter values of the network parameters after the neural network is obtained through training. If the difference is not the same, the executive body of the training step can send the trained network structure information and the parameter values of the network parameters to the executive body of the image identification method after the neural network is trained.
In this embodiment, the executing agent of the training step may first determine the network structure of the initial neural network. For example, it is necessary to determine which layers the initial neural network includes, the connection order relationship between layers, and which neurons each layer includes, the weight (weight) and bias term (bias) corresponding to each neuron, the activation function of each layer, and so on. Optionally, the neural network may comprise a second number of residual modules.
The executing agent of this training step may then initialize the network parameters of the initial neural network. In practice, the network parameters (e.g., weight parameters and bias parameters) of the initial neural network may be initialized with some different small random numbers. The small random number is used for ensuring that the network does not enter a saturation state due to overlarge weight value, so that training fails, and the different random numbers are used for ensuring that the network can normally learn.
In this embodiment, the executing entity of the training step may obtain the training sample set from other terminal devices connected to the executing entity through a network, locally or remotely. Wherein the training samples include sample images and sample classes corresponding to the sample images.
In this embodiment, the main body for performing the training step may perform the first step of training the neural network.
Step one, a neural network training process.
Firstly, sample images included in training samples in a selected training sample set are input to an initial neural network, and the category of the selected samples is obtained.
Second, the category of the selected sample is compared with the corresponding sample category. Specifically, the difference between the category of the selected sample and the corresponding sample category may be first calculated using a preset loss function. For example, the difference between the class of the selected sample and the corresponding sample class can be calculated by using a cross entropy loss function, and the problem of the reduction of the machine learning rate can be avoided when the gradient is reduced by using a sigmoid function in the cross entropy loss function.
Thirdly, in response to determining that the initial neural network reaches the optimization goal, the training is ended with the initial neural network as a pre-trained neural network after the training is completed. Specifically, the preset optimization objectives may include, but are not limited to, at least one of the following: the training time exceeds the preset time; the training times exceed the preset times; the calculated difference is less than a preset difference threshold.
In this embodiment, the main body of the training step adjusts the relevant parameters in the initial neural network in response to determining that the initial neural network is not trained, specifically, in response to the initial neural network not reaching the optimization goal. In particular, various implementations may be employed to adjust network parameters of the initial neural network based on differences between the categories of the selected samples and the corresponding sample categories. For example, Adam, BP (Back Propagation) algorithm or SGD (Stochastic Gradient Descent) algorithm may be used to adjust the network parameters of the initial neural network.
Optionally, the executing entity reselects the sample from the sample set. And taking the sample image included in the sample as input, taking the corresponding pre-obtained sample class corresponding to the sample image as expected output, using the adjusted initial neural network as the initial neural network, executing the first step, and training the neural network again.
In this embodiment, the executing subject of the training step determines the initial neural network obtained by training as a neural network trained in advance.
One embodiment presented in fig. 3 has the following beneficial effects: a neural network is trained based on the sample images and sample classes corresponding to the sample images. The neural network can be directly applied to determine the probability that the input image corresponds to the category. The first target image is directly input into the neural network without manual intervention or extraction of the characteristics of the image, and the probability of the first target image corresponding to the category can be automatically obtained.
Referring now to FIG. 4, a block diagram of a computer system 400 suitable for use in implementing a server of an embodiment of the present disclosure is shown. The server shown in fig. 4 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present disclosure.
As shown in fig. 4, the computer system 400 includes a Central Processing Unit (CPU)401 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 402 or a program loaded from a storage section 408 into a Random Access Memory (RAM) 403. In the RAM 403, various programs and data necessary for the operation of the system 400 are also stored. The CPU 401, ROM402, and RAM 403 are connected to each other via a bus 404. An Input/Output (I/O) interface 405 is also connected to the bus 404.
The following components are connected to the I/O interface 405: a storage section 406 including a hard disk and the like; and a communication section 407 including a Network interface card such as a LAN (Local Area Network) card, a modem, or the like. The communication section 407 performs communication processing via a network such as the internet. A drive 408 is also connected to the I/O interface 405 as needed. A removable medium 409 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted as necessary on the drive 408, so that a computer program read out therefrom is mounted as necessary in the storage section 406.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 407 and/or installed from the removable medium 409. The above-described functions defined in the method of the present disclosure are performed when the computer program is executed by a Central Processing Unit (CPU) 401. It should be noted that the computer readable medium in the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the C language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is possible without departing from the inventive concept as defined above. For example, the above features and (but not limited to) the features disclosed in this disclosure having similar functions are replaced with each other to form the technical solution.
Claims (10)
1. A method of image authentication, comprising:
acquiring a first target image;
inputting the first target image into a pre-trained detection model to generate a second target image;
inputting the second target image into a pre-trained classification model to generate an identification result set of the second target image;
determining a category of the first target image based on the set of authentication results.
2. The method of claim 1, wherein the method further comprises:
and sending the category of the first target image to a device supporting display, and controlling the device to display the category.
3. The method of claim 1, wherein the inputting the first target image into a pre-trained detection model, generating a second target image, comprises:
inputting the first target image into a pre-trained detection model to generate a process image;
and cutting the process image to generate the second target image.
4. The method of claim 3, wherein the pre-trained detection model comprises a convolutional layer, a region proposal layer, a matching layer, a full convolutional layer, and an output layer; and
inputting the first target image into a pre-trained detection model to generate a process image, wherein the process image comprises:
inputting the first target image into the convolutional layer to generate a first feature map;
inputting the first feature map into a region suggestion layer to generate a candidate region map;
inputting the first feature map and the candidate region map into the matching layer to generate a second feature map;
inputting the second feature map into the full convolution layer to generate a third feature map;
and inputting the third feature map into the output layer to generate the process image.
5. The method of claim 4, wherein the pre-trained classification model comprises a first number of pre-trained neural networks, wherein the pre-trained neural networks are residual networks comprised of a second number of residual modules that generate an output using the equation: y ═ F (x, { W)iX is the input of the residual block, y is the output of the residual block, F () is the residual function, W is the weight matrix, i is the layer count in the residual block, WiWeight matrix representing i-th layer, { WiDenotes the set of weight matrices for all layers in the residual block.
6. The method of claim 5, wherein the first number of pre-trained neural networks corresponds to a first number of predetermined classes.
7. The method of claim 6, wherein the pre-trained neural network is obtained by:
determining a network structure of an initial neural network and initializing network parameters of the initial neural network;
acquiring a training sample set, wherein training samples comprise sample images and sample classes corresponding to the sample images;
selecting samples from the sample set, and performing the following training steps:
inputting a sample image of a selected sample into an initial neural network to obtain the category of the selected sample;
comparing the selected sample category with the corresponding sample category;
determining whether the initial neural network reaches a preset optimization target according to the comparison result;
in response to determining that the initial neural network meets the optimization goal, treating the initial neural network as the pre-trained neural network for which training is complete;
in response to determining that the initial neural network is not trained, adjusting relevant parameters in the initial neural network, and reselecting samples from the sample set, the training step is performed again using the adjusted initial neural network as the initial neural network.
8. The method of claim 7, wherein the inputting the second target image into a pre-trained classification model to generate the set of discrimination results for the second target image comprises:
inputting the second target image into a pre-trained classification model to obtain an output result set;
determining an output result set of the pre-trained classification model as an identification result set of the second target image, wherein the output result set of the pre-trained classification model is a set of output results of the first number of pre-trained neural networks, the identification result is an output result of the pre-trained neural networks, and the identification result set includes the first number of identification results.
9. The method of claim 8, wherein said determining a category of the first target image based on the set of authentication results comprises:
determining that the category of the first target image is null in response to all values in the set of authentication results being negative values;
in response to the values in the set of identification results not being all negative values, determining the category corresponding to the maximum value in the set of identification results as the category of the first target image.
10. A first terminal device comprising:
one or more processors;
a storage device having one or more programs stored thereon;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010651813.2A CN111881944B (en) | 2020-07-08 | 2020-07-08 | Image authentication method, electronic device, and computer-readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010651813.2A CN111881944B (en) | 2020-07-08 | 2020-07-08 | Image authentication method, electronic device, and computer-readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111881944A true CN111881944A (en) | 2020-11-03 |
| CN111881944B CN111881944B (en) | 2024-09-17 |
Family
ID=73151184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010651813.2A Active CN111881944B (en) | 2020-07-08 | 2020-07-08 | Image authentication method, electronic device, and computer-readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111881944B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112270377A (en) * | 2020-11-11 | 2021-01-26 | 北京百度网讯科技有限公司 | Target image extraction method, neural network training method and device |
| CN112766285A (en) * | 2021-01-26 | 2021-05-07 | 北京有竹居网络技术有限公司 | Image sample generation method and device and electronic equipment |
| CN113240027A (en) * | 2021-05-24 | 2021-08-10 | 北京有竹居网络技术有限公司 | Image classification method and device, readable medium and electronic equipment |
| CN113408661A (en) * | 2021-07-16 | 2021-09-17 | 北京百度网讯科技有限公司 | Method, apparatus, device and medium for determining mismatching |
| WO2022037452A1 (en) * | 2020-08-19 | 2022-02-24 | 北京字节跳动网络技术有限公司 | Information generation method and apparatus, electronic device, and computer readable medium |
| CN115600131A (en) * | 2022-11-28 | 2023-01-13 | 西安弘捷电子技术有限公司（Cn） | Automatic test system based on graphical test platform |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016155371A1 (en) * | 2015-03-31 | 2016-10-06 | 百度在线网络技术（北京）有限公司 | Method and device for recognizing traffic signs |
| CN107609598A (en) * | 2017-09-27 | 2018-01-19 | 武汉斗鱼网络科技有限公司 | Image authentication model training method, device and readable storage medium storing program for executing |
| WO2019051941A1 (en) * | 2017-09-15 | 2019-03-21 | 平安科技（深圳）有限公司 | Method, apparatus and device for identifying vehicle type, and computer-readable storage medium |
| US20190102605A1 (en) * | 2017-09-29 | 2019-04-04 | Baidu Online Network Technology (Beijing) Co.,Ltd. | Method and apparatus for generating information |
| CN109871730A (en) * | 2017-12-05 | 2019-06-11 | 杭州海康威视数字技术股份有限公司 | A kind of target identification method, device and monitoring device |
| CN110110652A (en) * | 2019-05-05 | 2019-08-09 | 达闼科技（北京）有限公司 | A kind of object detection method, electronic equipment and storage medium |
| CN110378420A (en) * | 2019-07-19 | 2019-10-25 | Oppo广东移动通信有限公司 | A kind of image detecting method, device and computer readable storage medium |
| CN110826504A (en) * | 2019-11-07 | 2020-02-21 | 深圳市微埃智能科技有限公司 | Visual identification method and device combined with fine-grained classification and computer equipment |
-
2020
- 2020-07-08 CN CN202010651813.2A patent/CN111881944B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016155371A1 (en) * | 2015-03-31 | 2016-10-06 | 百度在线网络技术（北京）有限公司 | Method and device for recognizing traffic signs |
| WO2019051941A1 (en) * | 2017-09-15 | 2019-03-21 | 平安科技（深圳）有限公司 | Method, apparatus and device for identifying vehicle type, and computer-readable storage medium |
| CN107609598A (en) * | 2017-09-27 | 2018-01-19 | 武汉斗鱼网络科技有限公司 | Image authentication model training method, device and readable storage medium storing program for executing |
| US20190102605A1 (en) * | 2017-09-29 | 2019-04-04 | Baidu Online Network Technology (Beijing) Co.,Ltd. | Method and apparatus for generating information |
| CN109871730A (en) * | 2017-12-05 | 2019-06-11 | 杭州海康威视数字技术股份有限公司 | A kind of target identification method, device and monitoring device |
| CN110110652A (en) * | 2019-05-05 | 2019-08-09 | 达闼科技（北京）有限公司 | A kind of object detection method, electronic equipment and storage medium |
| CN110378420A (en) * | 2019-07-19 | 2019-10-25 | Oppo广东移动通信有限公司 | A kind of image detecting method, device and computer readable storage medium |
| CN110826504A (en) * | 2019-11-07 | 2020-02-21 | 深圳市微埃智能科技有限公司 | Visual identification method and device combined with fine-grained classification and computer equipment |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022037452A1 (en) * | 2020-08-19 | 2022-02-24 | 北京字节跳动网络技术有限公司 | Information generation method and apparatus, electronic device, and computer readable medium |
| CN112270377A (en) * | 2020-11-11 | 2021-01-26 | 北京百度网讯科技有限公司 | Target image extraction method, neural network training method and device |
| CN112270377B (en) * | 2020-11-11 | 2024-03-15 | 北京百度网讯科技有限公司 | Target image extraction method, neural network training method and device |
| CN112766285A (en) * | 2021-01-26 | 2021-05-07 | 北京有竹居网络技术有限公司 | Image sample generation method and device and electronic equipment |
| CN112766285B (en) * | 2021-01-26 | 2024-03-19 | 北京有竹居网络技术有限公司 | Image sample generation method and device and electronic equipment |
| CN113240027A (en) * | 2021-05-24 | 2021-08-10 | 北京有竹居网络技术有限公司 | Image classification method and device, readable medium and electronic equipment |
| CN113408661A (en) * | 2021-07-16 | 2021-09-17 | 北京百度网讯科技有限公司 | Method, apparatus, device and medium for determining mismatching |
| CN115600131A (en) * | 2022-11-28 | 2023-01-13 | 西安弘捷电子技术有限公司（Cn） | Automatic test system based on graphical test platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111881944B (en) | 2024-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111881944B (en) | Image authentication method, electronic device, and computer-readable medium | |
| US10902245B2 (en) | Method and apparatus for facial recognition | |
| CN111539942B (en) | Method for detecting face depth tampered image based on multi-scale depth feature fusion | |
| CN108038880B (en) | Method and apparatus for processing image | |
| CN108898186B (en) | Method and device for extracting image | |
| US10635979B2 (en) | Category learning neural networks | |
| US11978245B2 (en) | Method and apparatus for generating image | |
| CN108171203B (en) | Method and device for identifying vehicle | |
| CN108197652B (en) | Method and apparatus for generating information | |
| CN108197618B (en) | Method and device for generating human face detection model | |
| WO2018109505A1 (en) | Transforming source domain images into target domain images | |
| CN109472264B (en) | Method and apparatus for generating an object detection model | |
| CN107609506B (en) | Method and apparatus for generating image | |
| CN110929780A (en) | Video classification model construction method, video classification device, video classification equipment and media | |
| CN107507153B (en) | Image denoising method and device | |
| EP3745309A1 (en) | Training a generative adversarial network | |
| CN109902763B (en) | Method and device for generating feature map | |
| CN109948700B (en) | Method and device for generating feature map | |
| CN109389096B (en) | Detection method and device | |
| CN109377508B (en) | Image processing method and device | |
| CN109712164A (en) | Image intelligent cut-out method, system, equipment and storage medium | |
| CN112215831B (en) | Method and system for evaluating quality of face image | |
| CN112766284A (en) | Image recognition method and device, storage medium and electronic equipment | |
| CN113837965B (en) | Image definition identification method and device, electronic equipment and storage medium | |
| CN108921792B (en) | Method and device for processing pictures |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |