CN110706185A - Image processing method and device, equipment and storage medium - Google Patents
Image processing method and device, equipment and storage medium Download PDFInfo
- Publication number
- CN110706185A CN110706185A CN201910966913.1A CN201910966913A CN110706185A CN 110706185 A CN110706185 A CN 110706185A CN 201910966913 A CN201910966913 A CN 201910966913A CN 110706185 A CN110706185 A CN 110706185A
- Authority
- CN
- China
- Prior art keywords
- neural network
- network model
- image
- picture
- training
- 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.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 84
- 238000003062 neural network model Methods 0.000 claims abstract description 58
- 238000012549 training Methods 0.000 claims abstract description 55
- 238000001514 detection method Methods 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000013528 artificial neural network Methods 0.000 claims abstract description 16
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 9
- 238000013519 translation Methods 0.000 claims description 26
- 238000005457 optimization Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 14
- 238000004891 communication Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 238000004091 panning Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012550 audit Methods 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Editing Of Facsimile Originals (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application discloses an image processing method, an image processing device, image processing equipment and a storage medium. Inputting a picture to be processed to a neural network model; outputting a detection result whether the picture information is finished or not according to the neural network model; the method also comprises the following steps of increasing the generalization ability of the neural network model when training the neural network model: an accelerated neural network training mode is used when the pictures in the training set are processed; in the image enhancement stage, a non-translational or non-rotational processing regime is used. The method and the device solve the technical problem of poor image processing effect on the integrity of the information of the identity card. Through the method and the device, the traditional convolutional neural network training is optimized, and the method and the device are more suitable for the scene of the detection of the lack of the edges of the identity card.
Description
Technical Field
The present application relates to the field of image processing, and in particular, to an image processing method, an image processing apparatus, a device, and a storage medium.
Background
When the online business is checked, the validity detection of the identity card photo provided by the user becomes an important link of online business.
The inventor finds that the detection of whether the identity card in the identity card picture uploaded by the user is complete lacks the detection of the missing edge of the identity card, and further, the target image processing is difficult because the features are positioned at the edge part of the picture and have no obvious features with the normal picture.
Aiming at the problem of poor image processing effect on the integrity of the identity card information in the related technology, no effective solution is provided at present.
Disclosure of Invention
The present application mainly aims to provide an image processing method, an image processing apparatus, a device, and a storage medium, so as to solve the problem of poor image processing effect on integrity of identification card information.
In order to achieve the above object, according to one aspect of the present application, there is provided an image processing method for detecting whether image information is complete.
The image processing method according to the application comprises the following steps: inputting a picture to be processed to a neural network model; outputting a detection result whether the picture information is finished or not according to the neural network model; the method also comprises the following steps of increasing the generalization ability of the neural network model when training the neural network model: an accelerated neural network training mode is used when the pictures in the training set are processed; in the image enhancement stage, a non-translational or non-rotational processing regime is used.
Further, the using of the accelerated neural network training mode in processing the pictures in the training set includes:
and setting hyper-parameter selection of the Batchnorm algorithm model based on a preset convolutional neural network, and training the marked data set by adopting the Batchnorm algorithm model.
Further, in the image enhancement stage, the processing mode using non-translation or non-rotation includes:
and in the image enhancement stage, performing image enhancement processing by using a processing mode of non-horizontal translation.
Further, in the image enhancement stage, the processing mode using non-translation or non-rotation includes:
in the image enhancement stage, a non-rotation processing mode is used for carrying out image enhancement processing.
Further, the detecting whether the image information is complete includes: whether the image information of the identity card is complete or not is detected,
inputting a picture to be processed into a neural network model, comprising:
inputting the picture of the identity card to be processed into the neural network model,
outputting a detection result of whether the picture information is finished or not according to the neural network model, wherein the detection result comprises the following steps:
and outputting a detection result of whether the identity card picture is lack of edges according to the neural network model.
In order to achieve the above object, according to another aspect of the present application, there is provided an image processing apparatus for detecting whether image information is complete.
An image processing apparatus according to the present application includes: the input module is used for inputting the picture to be processed to the neural network model; the output module is used for outputting a detection result whether the picture information is finished or not according to the neural network model; further comprising: an optimization module, configured to, when training the neural network model, further include a step for increasing a generalization capability of the neural network model: an accelerated neural network training mode is used when the pictures in the training set are processed; in the image enhancement stage, a non-translational or non-rotational processing regime is used.
Further, the optimization module is used for
And setting hyper-parameter selection of the Batchnorm algorithm model based on a preset convolutional neural network, and training the marked data set by adopting the Batchnorm algorithm model.
Further, the optimization module is used for
And in the image enhancement stage, performing image enhancement processing by using a processing mode of non-horizontal translation.
In the image enhancement stage, a non-rotation processing mode is used for carrying out image enhancement processing.
In order to achieve the above object, according to still another aspect of the present application, there is provided an electronic apparatus.
An electronic device according to the present application comprises a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the image processing method when executing the program.
To achieve the above object, according to still another aspect of the present application, there is provided a computer-readable storage medium.
The computer-readable storage medium according to the present application comprises steps on which a computer program is stored which, when being executed by a processor, carries out the image processing method as described.
In the image processing method, the image processing device, the image processing equipment and the image processing storage medium, a mode of inputting a picture to be processed to a neural network model is adopted, a detection result of whether picture information is finished or not is output according to the neural network model, and an accelerated neural network training mode is used when pictures in a training set are processed; in the image enhancement stage, a non-translation or non-rotation processing mode is used, the purpose of carrying out the special scene of edge deletion detection on the identity card is achieved, the technical effect of better recognition effect during online service audit is achieved, and the technical problem of poor image processing effect on the information integrity of the identity card is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, serve to provide a further understanding of the application and to enable other features, objects, and advantages of the application to be more apparent. The drawings and their description illustrate the embodiments of the invention and do not limit it. In the drawings:
FIG. 1 is a schematic flow chart diagram of an image processing method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of an image processing apparatus according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In this application, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "middle", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings. These terms are used primarily to better describe the present application and its embodiments, and are not used to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meaning of these terms in this application will be understood by those of ordinary skill in the art as appropriate.
Furthermore, the terms "mounted," "disposed," "provided," "connected," and "sleeved" are to be construed broadly. For example, it may be a fixed connection, a removable connection, or a unitary construction; can be a mechanical connection, or an electrical connection; may be directly connected, or indirectly connected through intervening media, or may be in internal communication between two devices, elements or components. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
As shown in fig. 1, the method includes steps S101 to S105 as follows:
step S101, inputting a picture to be processed to a neural network model;
the neural network model uses a standard convolutional neural network and detects whether the identity card in the identity card photo uploaded by the user is complete.
Step S102, outputting a detection result whether the picture information is finished or not according to the neural network model;
and detecting the truncation characteristics concerned with the edge of the identity card for the edge lack of the identity card according to the neural network model, wherein the characteristics are positioned at the edge part of the picture compared with the complete identity card. Therefore, during training, fine parameter adjustment needs to be carried out according to the characteristics of the photos, and a better identity card missing edge detection effect can be achieved.
Step S103, when the neural network model is trained, the method further comprises a step for increasing the generalization ability of the neural network model;
the generalization ability for increasing the neural network model refers to the adaptability of a machine learning algorithm to training samples. The generalization ability is used as an index for evaluating a neural network model.
Step S104, an accelerated neural network training mode is used when the pictures in the training set are processed;
and an accelerated neural network training mode is used when the pictures in the training set are processed, so that the method can be better suitable for detecting scenes aiming at the lacking edges of the identity cards.
Specifically, if the BatchNorm technique is used, rather than the usual dropout, the effect of increasing the generalization capability of the model is achieved.
In step S105, in the image enhancement stage, a non-translational or non-rotational processing method is used.
When the image enhancement stage processing is carried out on the picture to be processed, a non-translation or non-rotation processing mode is used. Since the method of translating and rotating the picture left and right, which is commonly used in the image enhancement stage, is not suitable for the scene of the detection of the lacking edge of the identification card, the complete identification card picture may become the lacking edge sample after translation or rotation. Non-translational or non-rotational processing is used during the image enhancement stage.
From the above description, it can be seen that the following technical effects are achieved by the present application:
in the embodiment of the application, a mode of inputting the picture to be processed to a neural network model is adopted, a detection result of whether picture information is finished or not is output according to the neural network model, and an accelerated neural network training mode is used when pictures in a training set are processed; in the image enhancement stage, a non-translation or non-rotation processing mode is used, the purpose of carrying out the special scene of edge deletion detection on the identity card is achieved, the technical effect of better recognition effect during online service audit is achieved, and the technical problem of poor image processing effect on the information integrity of the identity card is solved.
According to the embodiment of the present application, as a preferable aspect in the embodiment, the method for using the accelerated neural network training mode when processing the pictures in the training set includes:
and setting hyper-parameter selection of the Batchnorm algorithm model based on a preset convolutional neural network, and training the marked data set by adopting the Batchnorm algorithm model.
Specifically, in the hyper-selection of BatchNorm, an excessively large epsilon causes a phenomenon in which the gradient disappears. Preferably, the Batchnorm algorithm model uses epsilon of 0.00001.
According to the embodiment of the present application, as a preferred embodiment, the processing method using non-translation or non-rotation in the image enhancement stage includes: and in the image enhancement stage, performing image enhancement processing by using a processing mode of non-horizontal translation.
And in the image enhancement stage, performing image enhancement processing by using a processing mode of non-horizontal translation.
It will be apparent to those skilled in the art that the picture enhancement processing may be performed using a processing manner other than left-right panning.
Specifically, it is considered that image enhancement is also a relatively common way to add training data, but the common method of translating and rotating pictures left and right is not suitable for the scenes of detecting the lack of edges of the id card, because the complete id card picture may become a sample of the lack of edges after translation or rotation. Therefore, during training, the picture enhancement is not performed by using the left-right translation and rotation technology.
According to the embodiment of the present application, as a preferred embodiment, the processing method using non-translation or non-rotation in the image enhancement stage includes: in the image enhancement stage, a non-rotation processing mode is used for carrying out image enhancement processing.
And in the image enhancement stage, a non-rotation processing mode is adopted for carrying out image enhancement processing.
It will be apparent to those skilled in the art that the picture enhancement processing may be performed using a processing manner other than left-right panning.
Specifically, it is considered that image enhancement is also a relatively common way to add training data, but the common method of translating and rotating pictures left and right is not suitable for the scenes of detecting the lack of edges of the id card, because the complete id card picture may become a sample of the lack of edges after translation or rotation. Therefore, during training, the picture enhancement is not performed by using the left-right translation and rotation technology.
According to the embodiment of the present application, as a preferable option in the embodiment, the detecting whether the image information is complete includes: whether the image information of the identity card is complete or not is detected,
inputting a picture to be processed into a neural network model, comprising:
inputting a picture of the identity card to be processed into a neural network model;
outputting a detection result of whether the picture information is finished or not according to the neural network model, wherein the detection result comprises the following steps:
and outputting a detection result of whether the identity card picture is lack of edges according to the neural network model.
A standard neural network is used for detecting whether the image information of the identity card is complete or not, and inputting a picture of the identity card to be processed to a neural network model; and outputting a detection result of whether the identity card picture is lack of edges according to the neural network model.
And the BatchNorm is used for processing the picture aiming at the detection scene of the lack of the identity card, dropout is abandoned, and the optimization mode of translation and rotation is abandoned in the image enhancement stage.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
According to an embodiment of the present application, there is also provided an image processing apparatus for implementing the above method, as shown in fig. 2, the apparatus including: the input module 10 is used for inputting the picture to be processed to the neural network model; the output module 13 is used for outputting a detection result whether the picture information is finished or not according to the neural network model; further comprising: an optimization module 12, configured to, when training the neural network model, further include a step of increasing a generalization ability of the neural network model: an accelerated neural network training mode is used when the pictures in the training set are processed; in the image enhancement stage, a non-translational or non-rotational processing regime is used.
In the input module 10 of the embodiment of the application, the neural network model uses a standard convolutional neural network, and detects whether the identity card in the identity card photo uploaded by the user is complete.
According to the neural network model, the cut-off characteristics of the edge of the identity card are focused on in the detection of the missing edge of the identity card, and compared with the complete identity card, the characteristics are located on the edge part of a photo. Therefore, during training, fine parameter adjustment needs to be carried out according to the characteristics of the photos, and a better identity card missing edge detection effect can be achieved.
The generalization ability of the optimization module 12 for increasing the neural network model in the embodiment of the present application refers to the adaptability of the machine learning algorithm to the training samples. The generalization ability is used as an index for evaluating a neural network model.
In the optimization module 12 of the embodiment of the present application, an accelerated neural network training mode is used when the pictures in the training set are processed, so that the method can be better applied to the detection scene aiming at the lack of edges of the identification card.
Specifically, if the BatchNorm technique is used, rather than the usual dropout, the effect of increasing the generalization capability of the model is achieved.
In the optimization module 12 of the embodiment of the present application, when the image enhancement stage processing is performed on the picture to be processed, a non-translation or non-rotation processing manner is used. Since the method of translating and rotating the picture left and right, which is commonly used in the image enhancement stage, is not suitable for the scene of the detection of the lacking edge of the identification card, the complete identification card picture may become the lacking edge sample after translation or rotation. Non-translational or non-rotational processing is used during the image enhancement stage.
According to the embodiment of the present application, as a preferred option in the embodiment, as shown in fig. 2, the optimization module is configured to set the hyper-parameter selection of the Batchnorm algorithm model based on a preset convolutional neural network, and train on the marked data set by using the Batchnorm algorithm model.
Specifically, in the hyper-selection of BatchNorm, an excessively large epsilon causes a phenomenon in which the gradient disappears. Preferably, the Batchnorm algorithm model uses epsilon of 0.00001.
According to the embodiment of the present application, as shown in fig. 2, the optimization module is configured to perform a picture enhancement processing in a non-horizontal-shift processing manner in an image enhancement stage.
And in the image enhancement stage, performing image enhancement processing by using a processing mode of non-horizontal translation.
It will be apparent to those skilled in the art that the picture enhancement processing may be performed using a processing manner other than left-right panning.
Specifically, it is considered that image enhancement is also a relatively common way to add training data, but the common method of translating and rotating pictures left and right is not suitable for the scenes of detecting the lack of edges of the id card, because the complete id card picture may become a sample of the lack of edges after translation or rotation. Therefore, during training, the picture enhancement is not performed by using the left-right translation and rotation technology.
According to the embodiment of the present application, as shown in fig. 2, in the image enhancement stage, the non-rotation processing mode preferably performs the picture enhancement processing.
And in the image enhancement stage, a non-rotation processing mode is adopted for carrying out image enhancement processing.
It will be apparent to those skilled in the art that the picture enhancement processing may be performed using a processing manner other than left-right panning.
Specifically, it is considered that image enhancement is also a relatively common way to add training data, but the common method of translating and rotating pictures left and right is not suitable for the scenes of detecting the lack of edges of the id card, because the complete id card picture may become a sample of the lack of edges after translation or rotation. Therefore, during training, the picture enhancement is not performed by using the left-right translation and rotation technology.
The embodiment of the application also provides computer equipment. As shown in fig. 3, the computer device 30 may include: the at least one processor 301, e.g., CPU, the at least one network interface 304, the user interface 303, the memory 305, the at least one communication bus 302, and optionally, a display screen 306. Wherein a communication bus 302 is used to enable the connection communication between these components. The user interface 303 may include a touch screen, a keyboard or a mouse, among others. The network interface 304 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), and a communication connection may be established with the server via the network interface 304. The memory 305 may be a high-speed RAM memory or a non-volatile memory (non-volatile memory), such as at least one disk memory, and the memory 305 includes a flash in the embodiment of the present invention. The memory 305 may alternatively be at least one memory system located remotely from the processor 301. As shown in fig. 3, memory 305, which is a type of computer storage medium, may include an operating system, a network communication module, a user interface module, and program instructions.
It should be noted that the network interface 304 may be connected to a receiver, a transmitter or other communication module, and the other communication module may include, but is not limited to, a WiFi module, a bluetooth module, etc., and it is understood that the computer device in the embodiment of the present invention may also include a receiver, a transmitter, other communication module, etc.
Processor 301 may be configured to call program instructions stored in memory 305 and cause computer device 30 to:
inputting a picture to be processed to a neural network model;
outputting a detection result whether the picture information is finished or not according to the neural network model;
the method also comprises the following steps of increasing the generalization ability of the neural network model when training the neural network model:
an accelerated neural network training mode is used when the pictures in the training set are processed;
in the image enhancement stage, a non-translational or non-rotational processing regime is used.
It will be apparent to those skilled in the art that the modules or steps of the present application described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present application is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. An image processing method for detecting whether image information is complete, comprising:
inputting a picture to be processed to a neural network model;
outputting a detection result whether the picture information is finished or not according to the neural network model;
the method also comprises the following steps of increasing the generalization ability of the neural network model when training the neural network model:
an accelerated neural network training mode is used when the pictures in the training set are processed;
in the image enhancement stage, a non-translational or non-rotational processing regime is used.
2. The image processing method of claim 1, wherein using an accelerated neural network training mode in processing pictures in a training set comprises:
and setting hyper-parameter selection of the Batchnorm algorithm model based on a preset convolutional neural network, and training the marked data set by adopting the Batchnorm algorithm model.
3. The image processing method according to claim 1, wherein, in the image enhancement stage, using a non-translational or non-rotational processing mode comprises:
and in the image enhancement stage, performing image enhancement processing by using a processing mode of non-horizontal translation.
4. The image processing method according to claim 1, wherein, in the image enhancement stage, using a non-translational or non-rotational processing mode comprises:
in the image enhancement stage, a non-rotation processing mode is used for carrying out image enhancement processing.
5. The image processing method according to claim 1, wherein the detecting whether the image information is complete comprises: whether the image information of the identity card is complete or not is detected,
inputting a picture to be processed into a neural network model, comprising:
inputting a picture of the identity card to be processed into a neural network model;
outputting a detection result of whether the picture information is finished or not according to the neural network model, wherein the detection result comprises the following steps:
and outputting a detection result of whether the identity card picture is lack of edges according to the neural network model.
6. An image processing apparatus for detecting whether image information is complete, comprising:
the input module is used for inputting the picture to be processed to the neural network model;
the output module is used for outputting a detection result whether the picture information is finished or not according to the neural network model;
further comprising: an optimization module, configured to, when training the neural network model, further include a step for increasing a generalization capability of the neural network model:
an accelerated neural network training mode is used when the pictures in the training set are processed;
in the image enhancement stage, a non-translational or non-rotational processing regime is used.
7. The image processing apparatus of claim 6, wherein the optimization module is configured to
And setting hyper-parameter selection of the Batchnorm algorithm model based on a preset convolutional neural network, and training the marked data set by adopting the Batchnorm algorithm model.
8. The image processing apparatus of claim 6, wherein the optimization module is configured to
And in the image enhancement stage, performing image enhancement processing by using a processing mode of non-horizontal translation.
In the image enhancement stage, a non-rotation processing mode is used for carrying out image enhancement processing.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the image processing method according to any of claims 1 to 6 are implemented when the program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the image processing method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910966913.1A CN110706185A (en) | 2019-09-30 | 2019-09-30 | Image processing method and device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910966913.1A CN110706185A (en) | 2019-09-30 | 2019-09-30 | Image processing method and device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110706185A true CN110706185A (en) | 2020-01-17 |
Family
ID=69199481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910966913.1A Pending CN110706185A (en) | 2019-09-30 | 2019-09-30 | Image processing method and device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110706185A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112541899A (en) * | 2020-12-15 | 2021-03-23 | 平安科技（深圳）有限公司 | Incomplete certificate detection method and device, electronic equipment and computer storage medium |
| CN112883959A (en) * | 2021-01-21 | 2021-06-01 | 平安银行股份有限公司 | Method, device, equipment and storage medium for detecting integrity of identity card license |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251338A (en) * | 2016-07-20 | 2016-12-21 | 北京旷视科技有限公司 | Target integrity detection method and device |
| CN108629168A (en) * | 2017-03-23 | 2018-10-09 | 三星电子株式会社 | Face authentication method, equipment and computing device |
| CN109472229A (en) * | 2018-10-30 | 2019-03-15 | 福州大学 | Shaft tower Bird's Nest detection method based on deep learning |
| CN109740627A (en) * | 2018-11-27 | 2019-05-10 | 南京邮电大学 | A kind of insect image identification identifying system and its method based on parallel-convolution neural network |
| CN109934200A (en) * | 2019-03-22 | 2019-06-25 | 南京信息工程大学 | A kind of RGB color remote sensing images cloud detection method of optic and system based on improvement M-Net |
| CN110084237A (en) * | 2019-05-09 | 2019-08-02 | 北京化工大学 | Detection model construction method, detection method and the device of Lung neoplasm |
-
2019
- 2019-09-30 CN CN201910966913.1A patent/CN110706185A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106251338A (en) * | 2016-07-20 | 2016-12-21 | 北京旷视科技有限公司 | Target integrity detection method and device |
| CN108629168A (en) * | 2017-03-23 | 2018-10-09 | 三星电子株式会社 | Face authentication method, equipment and computing device |
| CN109472229A (en) * | 2018-10-30 | 2019-03-15 | 福州大学 | Shaft tower Bird's Nest detection method based on deep learning |
| CN109740627A (en) * | 2018-11-27 | 2019-05-10 | 南京邮电大学 | A kind of insect image identification identifying system and its method based on parallel-convolution neural network |
| CN109934200A (en) * | 2019-03-22 | 2019-06-25 | 南京信息工程大学 | A kind of RGB color remote sensing images cloud detection method of optic and system based on improvement M-Net |
| CN110084237A (en) * | 2019-05-09 | 2019-08-02 | 北京化工大学 | Detection model construction method, detection method and the device of Lung neoplasm |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112541899A (en) * | 2020-12-15 | 2021-03-23 | 平安科技（深圳）有限公司 | Incomplete certificate detection method and device, electronic equipment and computer storage medium |
| CN112541899B (en) * | 2020-12-15 | 2023-12-22 | 平安科技（深圳）有限公司 | Incomplete detection method and device of certificate, electronic equipment and computer storage medium |
| CN112883959A (en) * | 2021-01-21 | 2021-06-01 | 平安银行股份有限公司 | Method, device, equipment and storage medium for detecting integrity of identity card license |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20160042249A1 (en) | Event-based image classification and scoring | |
| CN105981368A (en) | Photo composition and position guidance in an imaging device | |
| KR101725884B1 (en) | Automatic processing of images | |
| CN105138962A (en) | Image display method and image display device | |
| CN104410785A (en) | An information processing method and electronic device | |
| US20140223474A1 (en) | Interactive media systems | |
| CN112215171B (en) | Target detection method, device, equipment and computer readable storage medium | |
| CN109978805A (en) | It takes pictures processing method, device, mobile terminal and storage medium | |
| CN114529490B (en) | Data processing method, device, equipment and readable storage medium | |
| CN109948525A (en) | It takes pictures processing method, device, mobile terminal and storage medium | |
| CN107295082A (en) | Running software processing method, apparatus and system | |
| CN105005599A (en) | Photograph sharing method and mobile terminal | |
| CN111400596B (en) | Information sharing method and device | |
| CN111027450A (en) | Bank card information identification method and device, computer equipment and storage medium | |
| CN110706185A (en) | Image processing method and device, equipment and storage medium | |
| US20200389600A1 (en) | Environment-driven user feedback for image capture | |
| CN107330848A (en) | Image processing method, mobile terminal and storage device | |
| CN109246467A (en) | Label is to the method, apparatus of sharing video frequency, video camera and smart phone | |
| CN104239527A (en) | Method, device and terminal for screening pictures | |
| US10445585B1 (en) | Episodic image selection | |
| CN108401173A (en) | Interactive terminal, method and the computer readable storage medium of mobile live streaming | |
| KR20170001792A (en) | Personal customized contents service system and method | |
| CN105022480A (en) | Input method and terminal | |
| CN109286718A (en) | Screen recording method and device and electronic equipment | |
| US20230401265A1 (en) | Cross-application componentized document generation |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200117 |
|
| RJ01 | Rejection of invention patent application after publication |