CN113283446A - Method and device for identifying target object in image, electronic equipment and storage medium - Google Patents
Method and device for identifying target object in image, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113283446A CN113283446A CN202110581184.5A CN202110581184A CN113283446A CN 113283446 A CN113283446 A CN 113283446A CN 202110581184 A CN202110581184 A CN 202110581184A CN 113283446 A CN113283446 A CN 113283446A
- Authority
- CN
- China
- Prior art keywords
- image
- training set
- target object
- sample
- recognition model
- 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
Images
Classifications
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an image processing technology, and discloses a method for identifying a target object in an image, which comprises the following steps: obtaining a sample image set through image amplification; constructing a first training set and a test set by using the noise images and the sample image set, and training an original recognition model by using the first training set to obtain an initial recognition model; testing an initial recognition model by using a test set, selecting an error test result to construct a second training set so as to generate a first feature vector, and constructing a second feature vector of a sample image; and calculating a loss value between the first characteristic vector and the second characteristic vector to update parameters of the initial recognition model so as to obtain a standard recognition model for recognizing the image to be recognized and obtain a target object recognition result in the image. In addition, the invention also relates to a block chain technology, and the sample image can be stored in a node of the block chain. The invention also provides a device, equipment and medium for identifying the target object in the image. The invention can solve the problem of low accuracy of identifying the target object.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method and an apparatus for identifying an object in an image, an electronic device, and a computer-readable storage medium.
Background
With the rapid development of artificial intelligence technology, it is more and more common in daily life to process an image by using an image recognition model to recognize information of a target object contained in the image, for example, to analyze a disease image by using an image recognition model machine to determine the type of a focus in the image. However, due to the privacy of the medical images, the number of images available for training the model is very small, and the accuracy of the trained model is not high.
In the existing model training aiming at a small amount of samples, an original small amount of samples are often amplified into a plurality of images in an image expansion mode so as to realize the large amount of model training. However, in this method, since the new images generated by image expansion are all obtained based on the features of the original image, the basic features of the images in the new images are not changed, which easily causes situations such as overfitting of the trained model, and further causes low accuracy of the model in identifying the target object.
Disclosure of Invention
The invention provides a method and a device for identifying a target object in an image and a computer-readable storage medium, and mainly aims to solve the problem of low accuracy in identifying the target object.
In order to achieve the above object, the present invention provides a method for identifying an object in an image, comprising:
obtaining a sample image containing a target object, and carrying out image amplification on the sample image to obtain a sample image set;
constructing a first training set and a test set by using the noise images with the same type as the sample images and the sample image set, and training a pre-constructed original recognition model by using the first training set to obtain an initial recognition model;
testing the initial recognition model by using the test set, selecting error results of preset types in test results to construct a second training set, and constructing a third training set by using the sample images;
extracting a first feature vector of the images in the second training set, and extracting a second feature vector of the images in the third training set;
calculating a loss value between the first feature vector and the second feature vector, and updating parameters of the initial identification model according to the loss value to obtain a standard identification model;
and acquiring an image to be recognized, and recognizing the target object of the image to be recognized by using the standard recognition model to obtain a target object recognition result in the image.
Optionally, the performing image amplification on the sample image to obtain a sample image set includes:
performing texture description on the sample image to obtain the image texture of the sample image;
randomly and locally deepening the texture of the image to obtain a texture deepened image;
performing random local desalination on the image file to obtain a texture desalination image;
and collecting the texture deepening image and the texture fading image into the sample image set.
Optionally, the randomly locally deepening the texture of the image to obtain a texture deepened image includes:
counting the number of textures of the image texture;
selecting image textures with a preset proportion as textures to be processed according to the number of the textures;
and adjusting the pixel value of the pixel on the texture to be processed to obtain a texture deepened image.
Optionally, the training a pre-constructed original recognition model by using the first training set to obtain an initial recognition model includes:
carrying out image recognition on the first training set by using the original recognition model to obtain a recognition result;
calculating the loss value of the real label corresponding to the recognition result and each image in the first training set;
and carrying out parameter adjustment on the original identification model according to the loss value to obtain an initial identification model.
Optionally, the extracting the first feature vector of the images in the second training set includes:
performing horizontal convolution operation on the images in the second training set by using a preset first gradient operator to obtain a horizontal gradient component;
performing vertical convolution operation on the images in the second training set by using a preset second gradient operator to obtain a vertical gradient component;
calculating the first feature vector from the horizontal gradient component and the vertical gradient component.
Optionally, the performing, by using a preset first gradient operator, a horizontal convolution operation on the image of the image in the second training set to obtain a horizontal gradient component includes:
acquiring a convolution step length and a convolution length;
calculating the horizontal convolution times according to the convolution step length and the convolution length;
and carrying out convolution operation on each image in the second training set according to the convolution step length by using the first gradient operator to obtain a horizontal gradient component.
Optionally, the calculating the first feature vector according to the horizontal gradient component and the vertical gradient component includes:
carrying out normalization calculation on the horizontal gradient component to obtain a horizontal normalization component;
carrying out normalization calculation on the vertical gradient component to obtain a vertical normalization component;
and carrying out square summation on the horizontal normalization component and the vertical normalization component to obtain the first feature vector.
In order to solve the above problem, the present invention also provides an apparatus for recognizing an object in an image, the apparatus comprising:
the image amplification module is used for acquiring a sample image containing a target object, and performing image amplification on the sample image to obtain a sample image set;
the first training module is used for constructing a first training set and a testing set by using the noise images with the same type as the sample images and the sample image set, and training a pre-constructed original recognition model by using the first training set to obtain an initial recognition model;
the model testing module is used for testing the initial recognition model by using the test set, selecting error results of preset types in the test results to construct a second training set, and constructing a third training set by using the sample images;
the feature extraction module is used for extracting a first feature vector of the images in the second training set and extracting a second feature vector of the images in the third training set;
the second training module is used for calculating a loss value between the first characteristic vector and the second characteristic vector, and updating parameters of the initial recognition model according to the loss value to obtain a standard recognition model;
and the image recognition module is used for acquiring an image to be recognized, and performing target object recognition on the image to be recognized by using the standard recognition model to obtain a target object recognition result in the image.
In order to solve the above problem, the present invention also provides an electronic device, including:
a memory storing at least one instruction; and
and the processor executes the instructions stored in the memory to realize the method for identifying the target object in the image.
In order to solve the above problem, the present invention further provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the method for identifying an object in an image described above.
According to the embodiment of the invention, the original small amount of samples can be expanded through image expansion, and the model is trained simultaneously by utilizing the sample image set and the noise image obtained after the expansion, so that the accuracy and the robustness of the model are improved; and then testing the model, constructing a training set by using error results in the test results, and retraining the model with the sample image, so that the accuracy of the model for identifying the target object can be further improved. Therefore, the method, the device, the electronic equipment and the computer readable storage medium for identifying the target object in the image, which are provided by the invention, can solve the problem of low accuracy in identifying the target object.
Drawings
Fig. 1 is a schematic flowchart of a method for identifying an object in an image according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of generating a first feature vector according to an embodiment of the present invention;
FIG. 3 is a functional block diagram of an apparatus for recognizing an object in an image according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device for implementing the method for identifying the target object in the image according to an embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment of the application provides a method for identifying a target object in an image. The execution subject of the target object identification method in the image includes, but is not limited to, at least one of electronic devices such as a server and a terminal, which can be configured to execute the method provided by the embodiment of the present application. In other words, the method for identifying the target object in the image may be performed by software or hardware installed in the terminal device or the server device, and the software may be a block chain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
Fig. 1 is a schematic flow chart of a method for identifying an object in an image according to an embodiment of the present invention. In this embodiment, the method for identifying an object in an image includes:
and S1, acquiring a sample image containing the target object, and carrying out image amplification on the sample image to obtain a sample image set.
In the embodiment of the present invention, the sample image includes a specific target object and a real label corresponding to the target object, for example, when the target object is an apple, the sample image is an image including the apple, and the real label is "apple"; or, when the target object is a focus of a certain disease, the sample image is an image containing the focus, and the real label is a disease name corresponding to the focus.
According to the embodiment of the invention, the prestored sample image can be captured from the pre-constructed block chain link points through the java sentences with the data capturing function, and the efficiency of obtaining the sample image can be improved by utilizing the high throughput of the block chain to the data.
The embodiment of the invention can realize image amplification on the sample image by performing geometric transformation, color change, contrast adjustment, partial shielding and the like on the sample image.
In one embodiment of the present invention, the sample image is stretched horizontally and vertically to obtain a sample image set with different lengths, widths or a combination thereof.
Alternatively, the sample image is stained so that the color of the sample image is changed to a plurality of different colors, thereby obtaining a sample image set including sample images of the plurality of different colors.
Alternatively, a plurality of sample image sets in which different portions are masked are obtained by locally masking the sample images. For example, masking the upper half of an object in the sample image set results in a sample image in which only the lower half of the object is visible, masking the right half of the object in the sample image set results in a sample image in which only the left half of the object is visible, and aggregating the sample images in which different regions are masked into a sample image set.
In an embodiment of the present invention, the performing image amplification on the sample image to obtain a sample image set includes:
performing texture description on the sample image to obtain the image texture of the sample image;
randomly and locally deepening the texture of the image to obtain a texture deepened image;
performing random local desalination on the image file to obtain a texture desalination image;
and collecting the texture deepening image and the texture fading image into the sample image set.
In detail, the texture description of the sample image can be realized by using image texture extraction algorithms such as a Gray-level co-occurrence matrix (GLCM) method and Local Binary Pattern (LBP) method, so as to highlight the image texture in the sample image.
Specifically, the randomly locally deepening the image texture to obtain a texture deepened image includes:
counting the number of textures of the image texture;
selecting image textures with a preset proportion as textures to be processed according to the number of the textures;
and adjusting the pixel value of the pixel on the texture to be processed to obtain a texture deepened image.
In one application scene, the image texture with the preset proportion is selected according to the texture quantity, and the pixel value of the selected texture to be processed is adjusted (for example, the pixel value of the texture to be processed is adjusted to be a black range), so that the texture to be processed is deepened, and a texture deepened image is obtained.
Similarly, the step of performing random local desalination on the image file to obtain a texture-desalinated image is consistent with the step of deepening the texture, for example, the pixel value on the texture to be processed is adjusted to a white range to realize the desalination of the texture to be processed, so as to obtain the texture-desalinated image.
S2, constructing a first training set and a testing set by using the noise images with the same type as the sample images and the sample image set, and training the pre-constructed original recognition model by using the first training set to obtain an initial recognition model.
In the embodiment of the present invention, the noise image is an image of the same type as the sample image, but the noise image is different from the target object in the sample image (for example, the noise image and the sample image are both fruit images, but watermelon is included in the noise image, and apple is included in the sample image), and similarly, the noise image also includes a true tag corresponding to the noise image. For example, the target object included in the sample image is a lesion of a lung disease, but a lesion of a possible liver disease is included in the noisy image.
According to the embodiment of the invention, the noise image and the sample image set are collected, and the collected sample image and the noise image are divided into the first training set and the testing set according to the preset division ratio. Wherein the first training set and the test set both include sample images and noise images.
In the embodiment of the invention, the original recognition model can adopt networks with an image recognition function, such as VGG Network, GoogleNet, Residual Network and the like.
In one embodiment of the invention, EfficientNet is used as a backbone network of the original recognition model, and the EfficientNet is a composite multi-dimensional convolutional neural network, so that the accuracy in the image processing process is improved, and the accuracy of image recognition is further improved.
Further, the embodiment of the invention trains the original recognition model by using the training set to adjust the model parameters in the original recognition model, improve the accuracy of the original recognition model in recognizing the image and obtain the initial recognition model.
In detail, the training a pre-constructed original recognition model by using the first training set to obtain an initial recognition model includes:
carrying out image recognition on the first training set by using the original recognition model to obtain a recognition result;
calculating the loss value of the real label corresponding to the recognition result and each image in the first training set;
and carrying out parameter adjustment on the original identification model according to the loss value to obtain an initial identification model.
Specifically, the recognition result is a recognition result of the original recognition model on the type of the target object contained in each image in the first training set, for example, the first training set includes a sample image a, a sample image B, and a noise image C, where the true labels of the sample image a and the sample image B are apples (i.e., the target object is an apple), the true label of the image C is watermelon, but the recognition result obtained by the original recognition model is: the sample image A is an apple, the sample image B is a watermelon, and the noise image C is an apple.
And calculating the loss value of the identification result and the real label corresponding to each image in the first training set by using a preset first loss function, and further performing parameter adjustment on the original identification model according to the loss value so as to improve the accuracy of the original identification model.
For example, vector conversion is performed on the real labels in the first training set to obtain real vectors; performing vector conversion on the recognition result to obtain recognition vectors, respectively calculating loss values between the real vectors corresponding to each image in the first training set and the recognition vectors, and further adjusting parameters of the original recognition model according to the loss values by using a preset optimization algorithm, wherein the optimization algorithm includes but is not limited to: a batch gradient descent algorithm, a random gradient descent algorithm, a small batch gradient descent algorithm.
And S3, testing the initial recognition model by using the test set, selecting error results of preset types in the test results to construct a second training set, and constructing a third training set by using the sample images.
In the embodiment of the present invention, the initial recognition model obtained in step S2 may be tested by using a test set, for example, the test set is input into the initial recognition model to obtain a test result of the initial recognition model for each image in the test set.
In an embodiment of the present invention, when the second training set is constructed by using a preset type of error result in the test result, the preset type of error result includes an error result of a noise image in the test set.
For example, the test set contains a sample image D, a sample image E, a noise image F and a noise image G, wherein the true labels of the sample image D and the sample image E are apples, and the true labels of the noise image E and the noise image F are watermelons; after the initial recognition model recognizes the test set, the obtained test result is as follows: and the sample image D and the noise image F are apples, and the sample image E and the noise image G are watermelons, so that the noise image F and the sample image E are error results in the test result, and the noise image F is selected as the second training set.
Further, the embodiment of the present invention uses at least one sample image in the sample image set generated in step S1 as a third training set.
According to the embodiment of the invention, the second training set is constructed by using the error result in the test result, and the third training set is constructed by using the sample image, so that the images which are easy to be identified by the initial identification model and wrong in the noise image and the sample image containing the target object can be respectively constructed into the training sets, the subsequent further training of the initial identification model is facilitated, and the accuracy of the initial identification model is improved.
And S4, extracting a first feature vector of the images in the second training set, and extracting a second feature vector of the images in the third training set.
In the embodiment of the invention, the first feature vector of the images in the second training set can be extracted by utilizing algorithms with image feature extraction, such as an HOG algorithm, an LBP algorithm, a Harr algorithm and the like.
Further, the step of extracting the second feature vector of the images in the third training set is consistent with the step of extracting the first feature vector of the images in the second training set, and is not repeated here.
In an embodiment of the present invention, referring to fig. 2, the extracting the first feature vector of the images in the second training set includes:
s21, performing horizontal convolution operation on the images in the second training set by using a preset first gradient operator to obtain a horizontal gradient component;
s22, performing vertical convolution operation on the images in the second training set by using a preset second gradient operator to obtain a vertical gradient component;
and S23, calculating the first feature vector according to the horizontal gradient component and the vertical gradient component.
In detail, the first gradient operator and the second gradient operator are preset matrices, for example, the first gradient operator may be [ -1, 0, 1], and the second gradient operator may be [1, 0, -1], and a horizontal gradient component and a vertical gradient component corresponding to each image can be obtained by performing a convolution operation on the first gradient operator and the second gradient operator respectively with each image in the second training set.
Specifically, the performing horizontal convolution operation on the image of the image in the second training set by using a preset first gradient operator to obtain a horizontal gradient component includes:
acquiring a convolution step length and a convolution length;
calculating the horizontal convolution times according to the convolution step length and the convolution length;
and carrying out convolution operation on each image in the second training set according to the convolution step length by using the first gradient operator to obtain a horizontal gradient component.
The convolution step length refers to the pixel length of the first gradient operator which needs to move after the first gradient operator performs convolution operation once, the convolution length refers to the pixel length of each image in the second training set in the horizontal direction, and the convolution step length is divided by the convolution length, so that the horizontal convolution frequency of each image in the second training set in the horizontal direction can be calculated.
In one embodiment of the present invention, the calculating the first feature vector according to the horizontal gradient component and the vertical gradient component includes:
carrying out normalization calculation on the horizontal gradient component to obtain a horizontal normalization component;
carrying out normalization calculation on the vertical gradient component to obtain a vertical normalization component;
and carrying out square summation on the horizontal normalization component and the vertical normalization component to obtain the first feature vector.
In detail, the horizontal gradient component and the vertical gradient component may be calculated by using a preset function with a threshold value range of (0, 1), such as a linear function, a logarithmic function, or an inverse cotangent function, to realize the normalization process for the horizontal gradient component and the vertical gradient component.
Specifically, the horizontal normalized component and the vertical normalized component may be squared and summed using the following square summation formula to obtain the first feature vector:
wherein L is the first feature vector, α is the horizontal normalization component, and β is the vertical normalization component.
S5, calculating a loss value between the first characteristic vector and the second characteristic vector, and performing parameter updating on the initial recognition model according to the loss value to obtain a standard recognition model.
In the embodiment of the invention, the loss value of the identification result and the real label corresponding to each image in the first training set can be calculated by using the preset second loss function, so that the parameter adjustment of the initial identification model is realized, and the accuracy of the initial identification model is improved.
The second loss function may be the same as or different from the first loss function in step S2.
In detail, the step of updating the parameters of the initial recognition model by using the loss values to obtain the standard recognition model is consistent with the step of adjusting the parameters of the original recognition model when the pre-constructed original recognition model is trained by using the first training set in step S2, and is not repeated here.
And S6, acquiring an image to be recognized, and recognizing the target object of the image to be recognized by using the standard recognition model to obtain a target object recognition result in the image.
In the embodiment of the invention, the image to be recognized can be an image containing a target object or not, when the image to be recognized is obtained, the standard recognition model can be used for recognizing the target object of the image to be recognized, and the recognition result of the type of the target object in the image is obtained.
According to the embodiment of the invention, the original small amount of samples can be expanded through image expansion, and the model is trained simultaneously by utilizing the sample image set and the noise image obtained after the expansion, so that the accuracy and the robustness of the model are improved; and then testing the model, constructing a training set by using error results in the test results, and retraining the model with the sample image, so that the accuracy of the model for identifying the target object can be further improved. Therefore, the method for identifying the target object in the image can solve the problem of low accuracy of identifying the target object.
Fig. 3 is a functional block diagram of an apparatus for recognizing an object in an image according to an embodiment of the present invention.
The apparatus 100 for recognizing an object in an image according to the present invention may be installed in an electronic device. According to the realized functions, the device 100 for identifying the target object in the image can comprise an image amplification module 101, a first training module 102, a model testing module 103, a feature extraction module 104, a second training module 105 and an image identification module 106. The module of the present invention, which may also be referred to as a unit, refers to a series of computer program segments that can be executed by a processor of an electronic device and that can perform a fixed function, and that are stored in a memory of the electronic device.
In the present embodiment, the functions regarding the respective modules/units are as follows:
the image amplification module 101 is configured to obtain a sample image including a target object, and perform image amplification on the sample image to obtain a sample image set;
in the embodiment of the present invention, the sample image includes a specific target object and a real label corresponding to the target object, for example, when the target object is an apple, the sample image is an image including the apple, and the real label is "apple"; or, when the target object is a focus of a certain disease, the sample image is an image containing the focus, and the real label is a disease name corresponding to the focus.
According to the embodiment of the invention, the prestored sample image can be captured from the pre-constructed block chain link points through the java sentences with the data capturing function, and the efficiency of obtaining the sample image can be improved by utilizing the high throughput of the block chain to the data.
The embodiment of the invention can realize image amplification on the sample image by performing geometric transformation, color change, contrast adjustment, partial shielding and the like on the sample image.
In one embodiment of the present invention, the sample image is stretched horizontally and vertically to obtain a sample image set with different lengths, widths or a combination thereof.
Alternatively, the sample image is stained so that the color of the sample image is changed to a plurality of different colors, thereby obtaining a sample image set including sample images of the plurality of different colors.
Alternatively, a plurality of sample image sets in which different portions are masked are obtained by locally masking the sample images. For example, masking the upper half of an object in the sample image set results in a sample image in which only the lower half of the object is visible, masking the right half of the object in the sample image set results in a sample image in which only the left half of the object is visible, and aggregating the sample images in which different regions are masked into a sample image set.
In an embodiment of the present invention, the image amplification module 101 is specifically configured to:
acquiring a sample image containing a target object;
performing texture description on the sample image to obtain the image texture of the sample image;
randomly and locally deepening the texture of the image to obtain a texture deepened image;
performing random local desalination on the image file to obtain a texture desalination image;
and collecting the texture deepening image and the texture fading image into the sample image set.
In detail, the texture description of the sample image can be realized by using image texture extraction algorithms such as a Gray-level co-occurrence matrix (GLCM) method and Local Binary Pattern (LBP) method, so as to highlight the image texture in the sample image.
Specifically, the randomly locally deepening the image texture to obtain a texture deepened image includes:
counting the number of textures of the image texture;
selecting image textures with a preset proportion as textures to be processed according to the number of the textures;
and adjusting the pixel value of the pixel on the texture to be processed to obtain a texture deepened image.
In one application scene, the image texture with the preset proportion is selected according to the texture quantity, and the pixel value of the selected texture to be processed is adjusted (for example, the pixel value of the texture to be processed is adjusted to be a black range), so that the texture to be processed is deepened, and a texture deepened image is obtained.
Similarly, the step of performing random local desalination on the image file to obtain a texture-desalinated image is consistent with the step of deepening the texture, for example, the pixel value on the texture to be processed is adjusted to a white range to realize the desalination of the texture to be processed, so as to obtain the texture-desalinated image.
The first training module 102 is configured to construct a first training set and a test set by using the noise images of the same type as the sample images and the sample image set, and train a pre-constructed original recognition model by using the first training set to obtain an initial recognition model;
in the embodiment of the present invention, the noise image is an image of the same type as the sample image, but the noise image is different from the target object in the sample image (for example, the noise image and the sample image are both fruit images, but watermelon is included in the noise image, and apple is included in the sample image), and similarly, the noise image also includes a true tag corresponding to the noise image. For example, the target object included in the sample image is a lesion of a lung disease, but a lesion of a possible liver disease is included in the noisy image.
According to the embodiment of the invention, the noise image and the sample image set are collected, and the collected sample image and the noise image are divided into the first training set and the testing set according to the preset division ratio. Wherein the first training set and the test set both include sample images and noise images.
In the embodiment of the invention, the original recognition model can adopt networks with an image recognition function, such as VGG Network, GoogleNet, Residual Network and the like.
In one embodiment of the invention, EfficientNet is used as a backbone network of the original recognition model, and the EfficientNet is a composite multi-dimensional convolutional neural network, so that the accuracy in the image processing process is improved, and the accuracy of image recognition is further improved.
Further, the embodiment of the invention trains the original recognition model by using the training set to adjust the model parameters in the original recognition model, improve the accuracy of the original recognition model in recognizing the image and obtain the initial recognition model.
In detail, the first training module 102 is specifically configured to:
carrying out image recognition on the first training set by using the original recognition model to obtain a recognition result;
calculating the loss value of the real label corresponding to the recognition result and each image in the first training set;
and carrying out parameter adjustment on the original identification model according to the loss value to obtain an initial identification model.
Specifically, the recognition result is a recognition result of the original recognition model on the type of the target object contained in each image in the first training set, for example, the first training set includes a sample image a, a sample image B, and a noise image C, where the true labels of the sample image a and the sample image B are apples (i.e., the target object is an apple), the true label of the image C is watermelon, but the recognition result obtained by the original recognition model is: the sample image A is an apple, the sample image B is a watermelon, and the noise image C is an apple.
And calculating the loss value of the identification result and the real label corresponding to each image in the first training set by using a preset first loss function, and further performing parameter adjustment on the original identification model according to the loss value so as to improve the accuracy of the original identification model.
For example, vector conversion is performed on the real labels in the first training set to obtain real vectors; performing vector conversion on the recognition result to obtain recognition vectors, respectively calculating loss values between the real vectors corresponding to each image in the first training set and the recognition vectors, and further adjusting parameters of the original recognition model according to the loss values by using a preset optimization algorithm, wherein the optimization algorithm includes but is not limited to: a batch gradient descent algorithm, a random gradient descent algorithm, a small batch gradient descent algorithm.
The model testing module 103 is configured to test the initial recognition model by using the test set, select an error result of a preset type in the test result to construct a second training set, and construct a third training set by using the sample image;
in an embodiment of the present invention, the initial recognition model obtained in the first training module 102 may be tested by using a test set, for example, the test set is input into the initial recognition model, so as to obtain a test result of each image in the test set by the initial recognition model.
In an embodiment of the present invention, when the second training set is constructed by using a preset type of error result in the test result, the preset type of error result includes an error result of a noise image in the test set.
For example, the test set contains a sample image D, a sample image E, a noise image F and a noise image G, wherein the true labels of the sample image D and the sample image E are apples, and the true labels of the noise image E and the noise image F are watermelons; after the initial recognition model recognizes the test set, the obtained test result is as follows: and the sample image D and the noise image F are apples, and the sample image E and the noise image G are watermelons, so that the noise image F and the sample image E are error results in the test result, and the noise image F is selected as the second training set.
Further, the embodiment of the present invention uses at least one sample image in the sample image set generated in the image amplification module 101 as a third training set.
According to the embodiment of the invention, the second training set is constructed by using the error result in the test result, and the third training set is constructed by using the sample image, so that the images which are easy to be identified by the initial identification model and wrong in the noise image and the sample image containing the target object can be respectively constructed into the training sets, the subsequent further training of the initial identification model is facilitated, and the accuracy of the initial identification model is improved.
The feature extraction module 104 is configured to extract a first feature vector of the images in the second training set, and extract a second feature vector of the images in the third training set;
in the embodiment of the invention, the first feature vector of the images in the second training set can be extracted by utilizing algorithms with image feature extraction, such as an HOG algorithm, an LBP algorithm, a Harr algorithm and the like.
Further, the step of extracting the second feature vector of the images in the third training set is consistent with the step of extracting the first feature vector of the images in the second training set, and is not repeated here.
In an embodiment of the present invention, the feature extraction module 104 is specifically configured to:
performing horizontal convolution operation on the images in the second training set by using a preset first gradient operator to obtain a horizontal gradient component;
performing vertical convolution operation on the images in the second training set by using a preset second gradient operator to obtain a vertical gradient component;
calculating the first feature vector according to the horizontal gradient component and the vertical gradient component;
and extracting a second feature vector of the images in the third training set.
In detail, the first gradient operator and the second gradient operator are preset matrices, for example, the first gradient operator may be [ -1, 0, 1], and the second gradient operator may be [1, 0, -1], and a horizontal gradient component and a vertical gradient component corresponding to each image can be obtained by performing a convolution operation on the first gradient operator and the second gradient operator respectively with each image in the second training set.
Specifically, the performing horizontal convolution operation on the image of the image in the second training set by using a preset first gradient operator to obtain a horizontal gradient component includes:
acquiring a convolution step length and a convolution length;
calculating the horizontal convolution times according to the convolution step length and the convolution length;
and carrying out convolution operation on each image in the second training set according to the convolution step length by using the first gradient operator to obtain a horizontal gradient component.
The convolution step length refers to the pixel length of the first gradient operator which needs to move after the first gradient operator performs convolution operation once, the convolution length refers to the pixel length of each image in the second training set in the horizontal direction, and the convolution step length is divided by the convolution length, so that the horizontal convolution frequency of each image in the second training set in the horizontal direction can be calculated.
In one embodiment of the present invention, the calculating the first feature vector according to the horizontal gradient component and the vertical gradient component includes:
carrying out normalization calculation on the horizontal gradient component to obtain a horizontal normalization component;
carrying out normalization calculation on the vertical gradient component to obtain a vertical normalization component;
and carrying out square summation on the horizontal normalization component and the vertical normalization component to obtain the first feature vector.
In detail, the horizontal gradient component and the vertical gradient component may be calculated by using a preset function with a threshold value range of (0, 1), such as a linear function, a logarithmic function, or an inverse cotangent function, to realize the normalization process for the horizontal gradient component and the vertical gradient component.
Specifically, the horizontal normalized component and the vertical normalized component may be squared and summed using the following square summation formula to obtain the first feature vector:
wherein L is the first feature vector, α is the horizontal normalization component, and β is the vertical normalization component.
The second training module 105 is configured to calculate a loss value between the first feature vector and the second feature vector, and perform parameter update on the initial recognition model according to the loss value to obtain a standard recognition model;
in the embodiment of the invention, the loss value of the identification result and the real label corresponding to each image in the first training set can be calculated by using the preset second loss function, so that the parameter adjustment of the initial identification model is realized, and the accuracy of the initial identification model is improved.
The second loss function may be the same as or different from the first loss function in the first training module 102.
In detail, the step of updating the parameters of the initial recognition model by using the loss values to obtain the standard recognition model is consistent with the step of adjusting the parameters of the original recognition model when the first training set is used to train the pre-constructed original recognition model in the first training module 102, and is not repeated here.
The image recognition module 106 is configured to obtain an image to be recognized, and perform target object recognition on the image to be recognized by using the standard recognition model to obtain a target object recognition result in the image.
In the embodiment of the invention, the image to be recognized can be an image containing a target object or not, when the image to be recognized is obtained, the standard recognition model can be used for recognizing the target object of the image to be recognized, and the recognition result of the type of the target object in the image is obtained.
According to the embodiment of the invention, the original small amount of samples can be expanded through image expansion, and the model is trained simultaneously by utilizing the sample image set and the noise image obtained after the expansion, so that the accuracy and the robustness of the model are improved; and then testing the model, constructing a training set by using error results in the test results, and retraining the model with the sample image, so that the accuracy of the model for identifying the target object can be further improved. Therefore, the device for identifying the target object in the image can solve the problem of low accuracy of identifying the target object.
Fig. 4 is a schematic structural diagram of an electronic device for implementing a method for recognizing an object in an image according to an embodiment of the present invention.
The electronic device 1 may comprise a processor 10, a memory 11 and a bus, and may further comprise a computer program, such as an in-image object recognition program 12, stored in the memory 11 and executable on the processor 10.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, removable hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may in some embodiments be an internal storage unit of the electronic device 1, such as a removable hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, which are provided on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 may be used not only to store application software installed in the electronic device 1 and various types of data, such as codes of the object recognition program 12 in the image, but also to temporarily store data that has been output or is to be output.
The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or may be composed of a plurality of integrated circuits packaged with the same or different functions, including one or more Central Processing Units (CPUs), microprocessors, digital Processing chips, graphics processors, and combinations of various control chips. The processor 10 is a Control Unit (Control Unit) of the electronic device, connects various components of the electronic device by using various interfaces and lines, and executes various functions and processes data of the electronic device 1 by running or executing programs or modules (e.g., an object recognition program in an image, etc.) stored in the memory 11 and calling data stored in the memory 11.
The bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is arranged to enable connection communication between the memory 11 and at least one processor 10 or the like.
Fig. 4 only shows an electronic device with components, and it will be understood by those skilled in the art that the structure shown in fig. 4 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than those shown, or some components may be combined, or a different arrangement of components.
For example, although not shown, the electronic device 1 may further include a power supply (such as a battery) for supplying power to each component, and preferably, the power supply may be logically connected to the at least one processor 10 through a power management device, so as to implement functions of charge management, discharge management, power consumption management, and the like through the power management device. The power supply may also include any component of one or more dc or ac power sources, recharging devices, power failure detection circuitry, power converters or inverters, power status indicators, and the like. The electronic device 1 may further include various sensors, a bluetooth module, a Wi-Fi module, and the like, which are not described herein again.
Further, the electronic device 1 may further include a network interface, and optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the electronic device 1 and other electronic devices.
Optionally, the electronic device 1 may further comprise a user interface, which may be a Display (Display), an input unit (such as a Keyboard), and optionally a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the electronic device 1 and for displaying a visualized user interface, among other things.
It is to be understood that the described embodiments are for purposes of illustration only and that the scope of the appended claims is not limited to such structures.
The object recognition program 12 in the image stored by the memory 11 in the electronic device 1 is a combination of instructions that, when executed in the processor 10, may implement:
obtaining a sample image containing a target object, and carrying out image amplification on the sample image to obtain a sample image set;
constructing a first training set and a test set by using the noise images with the same type as the sample images and the sample image set, and training a pre-constructed original recognition model by using the first training set to obtain an initial recognition model;
testing the initial recognition model by using the test set, selecting error results of preset types in test results to construct a second training set, and constructing a third training set by using the sample images;
extracting a first feature vector of the images in the second training set, and extracting a second feature vector of the images in the third training set;
calculating a loss value between the first feature vector and the second feature vector, and updating parameters of the initial identification model according to the loss value to obtain a standard identification model;
and acquiring an image to be recognized, and recognizing the target object of the image to be recognized by using the standard recognition model to obtain a target object recognition result in the image.
Specifically, the specific implementation method of the processor 10 for the instruction may refer to the description of the relevant steps in the embodiments corresponding to fig. 1 to fig. 4, which is not repeated herein.
Further, the integrated modules/units of the electronic device 1, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. The computer readable storage medium may be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying said computer program code, recording medium, U-disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM).
The present invention also provides a computer-readable storage medium, storing a computer program which, when executed by a processor of an electronic device, may implement:
obtaining a sample image containing a target object, and carrying out image amplification on the sample image to obtain a sample image set;
constructing a first training set and a test set by using the noise images with the same type as the sample images and the sample image set, and training a pre-constructed original recognition model by using the first training set to obtain an initial recognition model;
testing the initial recognition model by using the test set, selecting error results of preset types in test results to construct a second training set, and constructing a third training set by using the sample images;
extracting a first feature vector of the images in the second training set, and extracting a second feature vector of the images in the third training set;
calculating a loss value between the first feature vector and the second feature vector, and updating parameters of the initial identification model according to the loss value to obtain a standard identification model;
and acquiring an image to be recognized, and recognizing the target object of the image to be recognized by using the standard recognition model to obtain a target object recognition result in the image.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus, device and method can be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is only one logical functional division, and other divisions may be realized in practice.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional module.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof.
The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
Furthermore, it is obvious that the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural. A plurality of units or means recited in the system claims may also be implemented by one unit or means in software or hardware. The terms second, etc. are used to denote names, but not any particular order.
Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.
Claims (10)
1. A method for identifying an object in an image, the method comprising:
obtaining a sample image containing a target object, and carrying out image amplification on the sample image to obtain a sample image set;
constructing a first training set and a test set by using the noise images with the same type as the sample images and the sample image set, and training a pre-constructed original recognition model by using the first training set to obtain an initial recognition model;
testing the initial recognition model by using the test set, selecting error results of preset types in test results to construct a second training set, and constructing a third training set by using the sample images;
extracting a first feature vector of the images in the second training set, and extracting a second feature vector of the images in the third training set;
calculating a loss value between the first feature vector and the second feature vector, and updating parameters of the initial identification model according to the loss value to obtain a standard identification model;
and acquiring an image to be recognized, and recognizing the target object of the image to be recognized by using the standard recognition model to obtain a target object recognition result in the image.
2. The method for identifying the target object in the image according to claim 1, wherein the image amplification of the sample image to obtain a sample image set comprises:
performing texture description on the sample image to obtain the image texture of the sample image;
randomly and locally deepening the texture of the image to obtain a texture deepened image;
performing random local desalination on the image file to obtain a texture desalination image;
and collecting the texture deepening image and the texture fading image into the sample image set.
3. The method for identifying the object in the image according to claim 2, wherein the step of randomly and locally deepening the texture of the image to obtain a texture deepened image comprises the steps of:
counting the number of textures of the image texture;
selecting image textures with a preset proportion as textures to be processed according to the number of the textures;
and adjusting the pixel value of the pixel on the texture to be processed to obtain a texture deepened image.
4. The method for recognizing the target object in the image according to claim 1, wherein the training the pre-constructed original recognition model by using the first training set to obtain the initial recognition model comprises:
carrying out image recognition on the first training set by using the original recognition model to obtain a recognition result;
calculating the loss value of the real label corresponding to the recognition result and each image in the first training set;
and carrying out parameter adjustment on the original identification model according to the loss value to obtain an initial identification model.
5. The method for identifying the target object in the image according to any one of claims 1 to 4, wherein the extracting the first feature vector of the image in the second training set comprises:
performing horizontal convolution operation on the images in the second training set by using a preset first gradient operator to obtain a horizontal gradient component;
performing vertical convolution operation on the images in the second training set by using a preset second gradient operator to obtain a vertical gradient component;
calculating the first feature vector from the horizontal gradient component and the vertical gradient component.
6. The method for identifying the target object in the image according to claim 5, wherein the performing a horizontal convolution operation on the image of the image in the second training set by using a preset first gradient operator to obtain a horizontal gradient component comprises:
acquiring a convolution step length and a convolution length;
calculating the horizontal convolution times according to the convolution step length and the convolution length;
and carrying out convolution operation on each image in the second training set according to the convolution step length by using the first gradient operator to obtain a horizontal gradient component.
7. The method for identifying an object in an image according to claim 5, wherein said calculating the first feature vector according to the horizontal gradient component and the vertical gradient component comprises:
carrying out normalization calculation on the horizontal gradient component to obtain a horizontal normalization component;
carrying out normalization calculation on the vertical gradient component to obtain a vertical normalization component;
and carrying out square summation on the horizontal normalization component and the vertical normalization component to obtain the first feature vector.
8. An apparatus for identifying an object in an image, the apparatus comprising:
the image amplification module is used for acquiring a sample image containing a target object, and performing image amplification on the sample image to obtain a sample image set;
the first training module is used for constructing a first training set and a testing set by using the noise images with the same type as the sample images and the sample image set, and training a pre-constructed original recognition model by using the first training set to obtain an initial recognition model;
the model testing module is used for testing the initial recognition model by using the test set, selecting error results of preset types in the test results to construct a second training set, and constructing a third training set by using the sample images;
the feature extraction module is used for extracting a first feature vector of the images in the second training set and extracting a second feature vector of the images in the third training set;
the second training module is used for calculating a loss value between the first characteristic vector and the second characteristic vector, and updating parameters of the initial recognition model according to the loss value to obtain a standard recognition model;
and the image recognition module is used for acquiring an image to be recognized, and performing target object recognition on the image to be recognized by using the standard recognition model to obtain a target object recognition result in the image.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and the number of the first and second groups,
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method of identifying an object in an image as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a method for identifying an object in an image according to any one of claims 1 to 7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110581184.5A CN113283446B (en) | 2021-05-27 | 2021-05-27 | Method and device for identifying object in image, electronic equipment and storage medium |
| PCT/CN2021/109479 WO2022247005A1 (en) | 2021-05-27 | 2021-07-30 | Method and apparatus for identifying target object in image, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110581184.5A CN113283446B (en) | 2021-05-27 | 2021-05-27 | Method and device for identifying object in image, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113283446A true CN113283446A (en) | 2021-08-20 |
| CN113283446B CN113283446B (en) | 2023-09-26 |
Family
ID=77281917
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110581184.5A Active CN113283446B (en) | 2021-05-27 | 2021-05-27 | Method and device for identifying object in image, electronic equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113283446B (en) |
| WO (1) | WO2022247005A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114359645A (en) * | 2022-01-12 | 2022-04-15 | 中国平安人寿保险股份有限公司 | Image expansion method, device, equipment and storage medium based on characteristic region |
| CN114549928A (en) * | 2022-02-21 | 2022-05-27 | 平安科技（深圳）有限公司 | Image enhancement processing method and device, computer equipment and storage medium |
| CN115546536A (en) * | 2022-09-22 | 2022-12-30 | 南京森林警察学院 | Ivory product identification method and system |
| CN117893779A (en) * | 2024-01-19 | 2024-04-16 | 广东筠诚建筑科技有限公司 | Method and system for realizing abnormality identification under building construction based on machine vision |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117094966B (en) * | 2023-08-21 | 2024-04-05 | 青岛美迪康数字工程有限公司 | Tongue image identification method and device based on image amplification and computer equipment |
| CN116958503B (en) * | 2023-09-19 | 2024-03-12 | 广东新泰隆环保集团有限公司 | Image processing-based sludge drying grade identification method and system |
| CN117671497B (en) * | 2023-12-04 | 2024-05-28 | 广东筠诚建筑科技有限公司 | Engineering construction waste classification method and device based on digital images |
| CN117687385A (en) * | 2023-12-14 | 2024-03-12 | 深圳市摩天星智能科技有限公司 | Automatic test method and system applied to flat PCBA control module |
| CN117523345B (en) * | 2024-01-08 | 2024-04-23 | 武汉理工大学 | Target detection data balancing method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080052075A1 (en) * | 2006-08-25 | 2008-02-28 | Microsoft Corporation | Incrementally regulated discriminative margins in MCE training for speech recognition |
| US20160148074A1 (en) * | 2014-11-26 | 2016-05-26 | Captricity, Inc. | Analyzing content of digital images |
| US20190147320A1 (en) * | 2017-11-15 | 2019-05-16 | Uber Technologies, Inc. | "Matching Adversarial Networks" |
| CN110135514A (en) * | 2019-05-22 | 2019-08-16 | 国信优易数据有限公司 | A kind of workpiece classification method, device, equipment and medium |
| CN111079785A (en) * | 2019-11-11 | 2020-04-28 | 深圳云天励飞技术有限公司 | Image identification method and device and terminal equipment |
| CN111639704A (en) * | 2020-05-28 | 2020-09-08 | 深圳壹账通智能科技有限公司 | Target identification method, device and computer readable storage medium |
| CN111914939A (en) * | 2020-08-06 | 2020-11-10 | 平安科技（深圳）有限公司 | Method, device and equipment for identifying blurred image and computer readable storage medium |
| CN112101542A (en) * | 2020-07-24 | 2020-12-18 | 北京沃东天骏信息技术有限公司 | Training method and device of machine learning model, and face recognition method and device |
| CN112581522A (en) * | 2020-11-30 | 2021-03-30 | 平安科技（深圳）有限公司 | Method and device for detecting position of target object in image, electronic equipment and storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110796057A (en) * | 2019-10-22 | 2020-02-14 | 上海交通大学 | Pedestrian re-identification method and device and computer equipment |
| CN112232384A (en) * | 2020-09-27 | 2021-01-15 | 北京迈格威科技有限公司 | Model training method, image feature extraction method, target detection method and device |
-
2021
- 2021-05-27 CN CN202110581184.5A patent/CN113283446B/en active Active
- 2021-07-30 WO PCT/CN2021/109479 patent/WO2022247005A1/en active Application Filing
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080052075A1 (en) * | 2006-08-25 | 2008-02-28 | Microsoft Corporation | Incrementally regulated discriminative margins in MCE training for speech recognition |
| US20160148074A1 (en) * | 2014-11-26 | 2016-05-26 | Captricity, Inc. | Analyzing content of digital images |
| US20190147320A1 (en) * | 2017-11-15 | 2019-05-16 | Uber Technologies, Inc. | "Matching Adversarial Networks" |
| CN110135514A (en) * | 2019-05-22 | 2019-08-16 | 国信优易数据有限公司 | A kind of workpiece classification method, device, equipment and medium |
| CN111079785A (en) * | 2019-11-11 | 2020-04-28 | 深圳云天励飞技术有限公司 | Image identification method and device and terminal equipment |
| CN111639704A (en) * | 2020-05-28 | 2020-09-08 | 深圳壹账通智能科技有限公司 | Target identification method, device and computer readable storage medium |
| CN112101542A (en) * | 2020-07-24 | 2020-12-18 | 北京沃东天骏信息技术有限公司 | Training method and device of machine learning model, and face recognition method and device |
| CN111914939A (en) * | 2020-08-06 | 2020-11-10 | 平安科技（深圳）有限公司 | Method, device and equipment for identifying blurred image and computer readable storage medium |
| CN112581522A (en) * | 2020-11-30 | 2021-03-30 | 平安科技（深圳）有限公司 | Method and device for detecting position of target object in image, electronic equipment and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114359645A (en) * | 2022-01-12 | 2022-04-15 | 中国平安人寿保险股份有限公司 | Image expansion method, device, equipment and storage medium based on characteristic region |
| CN114359645B (en) * | 2022-01-12 | 2024-05-21 | 中国平安人寿保险股份有限公司 | Image expansion method, device, equipment and storage medium based on characteristic area |
| CN114549928A (en) * | 2022-02-21 | 2022-05-27 | 平安科技（深圳）有限公司 | Image enhancement processing method and device, computer equipment and storage medium |
| WO2023155299A1 (en) * | 2022-02-21 | 2023-08-24 | 平安科技（深圳）有限公司 | Image enhancement processing method and apparatus, computer device and storage medium |
| CN115546536A (en) * | 2022-09-22 | 2022-12-30 | 南京森林警察学院 | Ivory product identification method and system |
| CN117893779A (en) * | 2024-01-19 | 2024-04-16 | 广东筠诚建筑科技有限公司 | Method and system for realizing abnormality identification under building construction based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022247005A1 (en) | 2022-12-01 |
| CN113283446B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113283446A (en) | Method and device for identifying target object in image, electronic equipment and storage medium | |
| CN112465060A (en) | Method and device for detecting target object in image, electronic equipment and readable storage medium | |
| CN112396005A (en) | Biological characteristic image recognition method and device, electronic equipment and readable storage medium | |
| CN113705462B (en) | Face recognition method, device, electronic equipment and computer readable storage medium | |
| CN112052850A (en) | License plate recognition method and device, electronic equipment and storage medium | |
| CN112137591B (en) | Target object position detection method, device, equipment and medium based on video stream | |
| CN115374189B (en) | Block chain-based food safety tracing method, device and equipment | |
| CN112749653A (en) | Pedestrian detection method, device, electronic equipment and storage medium | |
| CN112580684A (en) | Target detection method and device based on semi-supervised learning and storage medium | |
| CN114708461A (en) | Multi-modal learning model-based classification method, device, equipment and storage medium | |
| CN112016617A (en) | Fine-grained classification method and device and computer-readable storage medium | |
| CN115471775A (en) | Information verification method, device and equipment based on screen recording video and storage medium | |
| CN112101481A (en) | Method, device and equipment for screening influence factors of target object and storage medium | |
| CN115409041B (en) | Unstructured data extraction method, device, equipment and storage medium | |
| CN113705686B (en) | Image classification method, device, electronic equipment and readable storage medium | |
| CN115439850A (en) | Image-text character recognition method, device, equipment and storage medium based on examination sheet | |
| CN114463685A (en) | Behavior recognition method and device, electronic equipment and storage medium | |
| CN112580505B (en) | Method and device for identifying network point switch door state, electronic equipment and storage medium | |
| CN112233194B (en) | Medical picture optimization method, device, equipment and computer readable storage medium | |
| CN113869385A (en) | Poster comparison method, device and equipment based on target detection and storage medium | |
| CN114187476A (en) | Vehicle insurance information checking method, device, equipment and medium based on image analysis | |
| CN114049676A (en) | Fatigue state detection method, device, equipment and storage medium | |
| CN112561893A (en) | Picture matching method and device, electronic equipment and storage medium | |
| CN113255456A (en) | Non-active living body detection method, device, electronic equipment and storage medium | |
| CN113705459A (en) | Face snapshot method and device, electronic equipment and storage medium |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20221010 Address after: 518000 Guangdong, Shenzhen, Futian District Futian street Fu'an community Yitian road 5033, Ping An financial center, 23 floor. Applicant after: PING AN TECHNOLOGY (SHENZHEN) Co.,Ltd. Applicant after: SHANDONG EYE INSTITUTE Address before: 518000 Guangdong, Shenzhen, Futian District Futian street Fu'an community Yitian road 5033, Ping An financial center, 23 floor. Applicant before: PING AN TECHNOLOGY (SHENZHEN) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |