CN114782954A - Picture identifying code identification method, system, equipment and storage medium - Google Patents
Picture identifying code identification method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN114782954A CN114782954A CN202210407055.9A CN202210407055A CN114782954A CN 114782954 A CN114782954 A CN 114782954A CN 202210407055 A CN202210407055 A CN 202210407055A CN 114782954 A CN114782954 A CN 114782954A
- Authority
- CN
- China
- Prior art keywords
- picture
- target detection
- detection model
- training
- preset
- 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
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a picture verification code identification method, a system, equipment and a storage medium, wherein the method comprises the following steps: preprocessing a plurality of identifying code picture samples belonging to different first categories and having characters to be identified as the same second category to obtain training samples; the pre-processing comprises pixel transformation; constructing an initial target detection model based on a preset target detection model; training the initial target detection model based on the training sample to obtain an application target detection model; identifying the verification code picture to be identified according to the application target detection model; the method and the device are beneficial to reducing the memory resources occupied under the scene of identifying different types of verification code pictures at the same time.
Description
Technical Field
The invention relates to the technical field of machine learning, in particular to a picture verification code identification method, a system, equipment and a storage medium.
Background
Aiming at identifying code pictures with characters as letters or numbers, the existing automatic identification method adopting a deep learning model has the following problems: the deep learning technology is adopted for each type of verification code picture to generate a single model, which results in that when multiple types of verification code pictures are identified simultaneously, each type of verification code needs to use a separate model corresponding to the type of verification code picture, which greatly increases the memory occupation resources.
Disclosure of Invention
In view of the problems in the prior art, an object of the present invention is to provide a method, a system, a device, and a storage medium for identifying a picture verification code, which reduce memory resources occupied in a scene where different types of verification code pictures are identified at the same time.
In order to achieve the above object, the present invention provides a picture verification code identification method, which comprises the following steps:
s110, preprocessing a plurality of identifying code picture samples which belong to different first categories and have characters to be identified as the same second category to obtain training samples; the pre-processing comprises pixel transformation;
s120, constructing an initial target detection model based on a preset target detection model;
s130, training the initial target detection model based on the training sample to obtain an application target detection model; and
and S140, identifying the verification code picture to be identified according to the application target detection model.
Optionally, step S130 includes:
s131, dividing according to a plurality of preset loss thresholds to obtain a plurality of preset segments, and acquiring an average loss value corresponding to each preset segment in the training process; and
and S132, taking the model generated in the corresponding preset segment with the minimum average loss value as an application target detection model.
Optionally, step S110 includes:
performing pixel transformation on the verification code picture sample, and transforming the pixel value into 0 or 255 to generate a gray picture sample; and
and carrying out normalization processing on the gray level picture sample to enable the pixel value to be converted into 0 or 1, and obtaining an initial sample.
Optionally, the preset target detection model includes a first detection module, a second detection module and a third detection module, and a detection object size of the first detection module is larger than a detection object size of the second detection module; the size of the detection object of the second detection module is larger than that of the detection object of the third detection module; the step S120 includes:
and eliminating the second detection module and the third detection module in the preset target detection model, and only reserving the first detection module.
Optionally, step S120 includes:
and discarding a preset number of network layers in a preset target detection model.
Optionally, step S110 includes:
and when the characters to be recognized in the verification code picture sample are letters, numbers or a combination of the letters and the numbers, determining that the characters to be recognized are in the same second category.
Optionally, in the training samples, the proportion of each verification code picture sample belonging to different first categories is equal.
Optionally, the preset target detection model is YOLOv4 algorithm.
The invention also provides a picture verification code identification system, which is used for realizing the picture verification code identification method, and the system comprises the following steps:
the image sample screening module is used for preprocessing a plurality of identifying code image samples which belong to different first classes and have the same second class of characters to be identified to obtain training samples; the pre-processing comprises pixel transformation;
the initial target detection model building module is used for building an initial target detection model based on a preset target detection model;
the model training module is used for training the initial target detection model based on the training sample to obtain an application target detection model; and
and the model application identification module is used for identifying the verification code picture to be identified according to the application target detection model.
The invention also provides a picture identifying code identifying device, which comprises:
a processor;
a memory having stored therein an executable program of the processor;
wherein the processor is configured to perform the steps of any one of the above-described picture validation code identification methods via execution of the executable program.
The present invention also provides a computer-readable storage medium for storing a program which, when executed by a processor, implements the steps of any one of the above-described picture verification code recognition methods.
Compared with the prior art, the invention has the following advantages and prominent effects:
the picture identifying code identifying method, the system, the equipment and the storage medium provided by the invention aim at identifying code pictures with characters formed by letters and/or numbers, and combine the identifying code pictures which belong to different types and can be converted into gray level pictures meeting requirements after pixel conversion to be used as training samples to train the same target detection model, so that a plurality of identifying code pictures of different types can be detected by using the same target detection model, and memory resources occupied by models in a multi-type identifying code picture detection scene are effectively reduced.
Drawings
Other features, objects and advantages of the present invention will become more apparent upon reading of the detailed description of non-limiting embodiments thereof, with reference to the following drawings.
Fig. 1 is a schematic diagram of a picture verification code identification method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of step S110 in a method for identifying a picture verification code according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a picture verification code identification method according to another embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a picture verification code recognition method according to another embodiment of the present invention;
fig. 5 is a schematic structural diagram of a picture verification code recognition system according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an image verification code identification device according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and thus their repetitive description will be omitted.
As shown in fig. 1, an embodiment of the present invention discloses a method for identifying a picture verification code, which includes the following steps:
s110, preprocessing a plurality of identifying code picture samples which belong to different first categories and have characters to be identified as the same second category to obtain training samples. The preprocessing includes pixel transformation.
As shown in fig. 2, in this embodiment, step S110 includes:
s111, collecting a plurality of verification code picture samples which belong to different first classes and have the same second class as the characters to be recognized, and extracting the first class and the position information of each verification code picture sample and the second class corresponding to the characters to be recognized in the pictures.
S112, the verification code picture sample is subjected to pixel conversion, and the pixel value is converted to 0 or 255, thereby generating a grayscale picture sample.
S113, the gray image samples are normalized so that the pixel values are converted to 0 or 1, and an initial sample is obtained. And
s114, combining the initial samples of different first categories according to a preset proportion, and performing character marking, label classification sample vectorization and other preprocessing operations on the initial samples according to the position information.
In the training samples, the proportion of each identifying code picture sample belonging to different first categories is equal. Therefore, the identification accuracy of different types of verification codes after the subsequent target detection model is trained is ensured. That is, for example, when the verification code picture samples have two types, the preset ratio is 1: 1. When the verification code picture samples have three types, the preset ratio is 1:1: 1.
In this embodiment, the plurality of verification code picture samples belong to different first categories, which indicate that there may be differences in background noise, arrangement shape, rotation angle, thickness, or character length between the verification code picture samples. When there is a difference in either aspect, that is, the two picture samples are different types of captcha picture samples, that is, belonging to different first categories.
On the other hand, the characters to be recognized in all the verification code image samples are in the same second category, that is, all the characters to be recognized are letters, numbers or a combination formed by letters and numbers. Meanwhile, the method and the device aim at identifying the identifying code picture of the type of characters.
In this embodiment, different types of verification code pictures are fused together, and a fused gray scale picture is generated after pixel transformation. And in the pixel transformation process, setting a threshold value according to the color difference of the background noise of the sample picture. And carrying out binarization operation according to the set threshold value.
In the embodiment, the sample picture normalization is to normalize the pixel values in the picture within the range of [0,1], and because the nature of the convolutional neural network is a series of numerical operations, the pixel values of the sample gray picture after the pixel transformation are only two 0 and 255, and are changed into 0 and 1 after the normalization, the floating point operations can be effectively reduced, and the model identification efficiency is improved.
The object objects in the pictures, namely the characters to be recognized, can be converted into the numerical indexes through label classification sample vectorization, so that subsequent training is facilitated, and the model training efficiency is improved. The preprocessing can also comprise tag position sample normalization, namely normalizing the position information to be in a range of [0,1], so that the importance of non-important features is reduced, and the accuracy of model operation is improved.
And S120, constructing an initial target detection model based on a preset target detection model. Specifically, in this step, a preset target detection model may be directly used as the initial target detection model. The initial target detection model may also be generated by performing some processing on a preset target detection model. In this embodiment, the preset target detection model is a YOLOv4 algorithm. The YOLOv4 algorithm facilitates ensuring accuracy and efficiency of target detection, both faster and more accurate than other target detectors. The present application is not limited thereto.
And S130, training the initial target detection model based on the training sample to obtain an application target detection model. Specifically, as shown in fig. 3, step S130 includes:
s131, dividing to obtain a plurality of preset segments according to a plurality of preset loss thresholds, and acquiring an average loss value corresponding to each preset segment in the training process. And
and S132, taking the model generated in the corresponding preset segment with the minimum average loss value as an application target detection model.
Specifically, the application target detection model is a trained target detection model, and prediction is performed based on the model. During the initial target detection model training process, the loss value is generally gradually reduced. However, in the process of reduction, there may be a case of fluctuation up and down. In the prior art, in the training process of the model, a preset iteration number is always used as a training termination condition, and an average loss curve of model convergence finally appears in a wave shape, namely fluctuates up and down, and has wave crests and wave troughs. Therefore, when the training reaches the iteration number, the average loss is likely to be at a peak rather than a trough, and the loss value is not the minimum value, so that the corresponding output model parameter is not the optimal model parameter, and the obtained model is not the optimal model.
Based on the above steps S131 and S132, a preset loss upper limit value and a preset loss lower limit value are respectively set to form a loss value interval. That is, the preset loss threshold includes a preset loss upper limit value and a preset loss lower limit value.
The interval of loss values is then divided into a plurality of segments. For example, if the upper limit value is 0.1, the lower limit value is 0.06, and each segment interval may be 0.01, then four segments may be obtained: [0.06,0.07], [0.07,0.08] [0.08,0.09], and [0.09,0.1 ]. Since the loss value in each segment similarly fluctuates up and down around a stable horizontal curve, the present embodiment uses the model generated by the corresponding segment with the smallest average loss value of each segment as the final model. Therefore, the prediction accuracy of the finally obtained model is improved, namely the identification accuracy of the verification code picture is improved.
And S140, identifying the verification code picture to be identified according to the application target detection model. It should be noted that, in the stage of the predictive identification, the verification code picture to be identified also needs to be processed by the preprocessing operation in step S110,
in another embodiment of the present application, another picture authentication code identification method is disclosed. On the basis of the embodiment corresponding to fig. 1, the preset target detection model includes a first detection module, a second detection module and a third detection module, and the size of the detection object of the first detection module is larger than that of the detection object of the second detection module. The size of the object to be detected by the second detection module is larger than the size of the object to be detected by the third detection module. The detection object refers to a character to be recognized in the verification code picture, such as a letter and a number in the picture.
Specifically, in this embodiment, step S120 includes:
and S121, eliminating the second detection module and the third detection module in the preset target detection model, and only reserving the first detection module. That is, only the first detection module for detecting large objects is reserved, while the third detection module for detecting small objects and the second detection module for detecting medium objects are removed. In the embodiment, the characters to be recognized in the verification code picture belong to large objects, and the training and detection logics of the model aiming at the small objects and the medium objects are redundant, so that the time consumption of model training and recognition can be reduced, and the model training and prediction recognition efficiency is improved.
In another embodiment of the present application, another picture authentication code identification method is disclosed. As shown in fig. 4, on the basis of the foregoing embodiment, in step S120, the method not only eliminates the second detection module and the third detection module in the preset target detection model, but also includes: and S122, discarding a preset number of network layers in the preset target detection model, and then constructing an initial target detection model. Since the preset target detection model YOLOv4 has 161 layers, the larger the number of layers, the more complicated the calculation, and the longer the time consumption. After the verification code picture is subjected to pixel transformation and normalization, effective information and background noise are relatively simple (pixel values are only two 0 and 1), and complex operation is not needed. According to the method, only 31 layers of network layers are reserved, so that the time consumption of model training and recognition can be reduced, and the efficiency of model training and prediction recognition can be improved. For comparison of the effect of the YOLOv4 model and the original YOLOv4 model in the present application, reference may be made to the following table 1:
TABLE 1 comparison of results before and after improvement in YOLOv4
| Number of network layers | Model occupied memory | Rate of accuracy | Time Consuming (CPU) | Time consuming (GPU) | |
| Original YOLOv4 model | 161 | 154M | 94％ | 4s | 50ms |
| The scheme of the application | 31 | 16M | 96％ | 1.45s | 11ms |
As can be seen from table 1 above, according to the technical scheme of the present application, memory resources occupied by the model are significantly reduced, accuracy of identifying the captcha image is improved, and both CPU time consumption and GPU time consumption are reduced.
It should be noted that all the above embodiments disclosed in the present application can be freely combined, and the technical solutions obtained by combining them are also within the scope of the present application.
As shown in fig. 5, an embodiment of the present invention further discloses a picture verification code recognition system 5, which includes:
the image sample screening module 51 is configured to perform preprocessing on a plurality of verification code image samples belonging to different first categories and having characters to be recognized in the same second category, so as to obtain a training sample. The preprocessing described above includes a pixel transform operation.
The initial target detection model building module 52 builds an initial target detection model based on a preset target detection model.
The model training module 53 trains the initial target detection model based on the training samples to obtain an application target detection model. And
and the model application identification module 54 identifies the verification code picture to be identified according to the application target detection model.
It is understood that the picture authentication code recognition system of the present invention further includes other existing functional modules that support the operation of the picture authentication code recognition system. The picture authentication code recognition system shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
The picture verification code identification system in this embodiment is used for implementing the above method for identifying a picture verification code, so for the specific implementation steps of the picture verification code identification system, reference may be made to the above description of the method for identifying a picture verification code, and details are not described here again.
The embodiment of the invention also discloses a picture identifying code identifying device, which comprises a processor and a memory, wherein the memory stores an executable program of the processor; the processor is configured to execute the steps of the above-mentioned picture authentication code identification method via execution of an executable program. Fig. 6 is a schematic structural diagram of a picture verification code recognition device disclosed in the present invention. An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 6. The electronic device 600 shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 6, the electronic device 600 is embodied in the form of a general purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one memory unit 620, a bus 630 connecting the different platform components (including the memory unit 620 and the processing unit 610), a display unit 640, etc.
Wherein the storage unit stores program code that may be executed by the processing unit 610 such that the processing unit 610 performs the steps according to various exemplary embodiments of the present invention as described in the picture authentication code identification method section above in this specification. For example, processing unit 610 may perform the steps as shown in fig. 1.
The storage unit 620 may include readable media in the form of volatile storage units, such as a random access memory unit (RAM)6201 and/or a cache storage unit 6202, and may further include a read-only memory unit (ROM) 6203.
The memory unit 620 may also include programs/utilities 6204 having a set (at least one) of program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may comprise an implementation of a network environment.
The electronic device 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any device (e.g., router, modem, etc.) that enables the electronic device 600 to communicate with one or more other computing devices. Such communication may occur via input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, to name a few.
The invention also discloses a computer readable storage medium for storing a program, wherein the program realizes the steps in the picture verification code identification method when executed. In some possible embodiments, the aspects of the present invention may also be implemented in the form of a program product including program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned picture authentication code recognition methods of the present specification, when the program product is run on the terminal device.
As shown above, when the program of the computer-readable storage medium of this embodiment is executed, for the verification code pictures of characters formed by letters and/or numbers, the verification code pictures belonging to different types and capable of being converted into grayscale pictures meeting requirements are subjected to pixel conversion, and then combined to be used as training samples to train the same target detection model, so that multiple verification code pictures of different types can be detected by using the same target detection model, and memory resources occupied by models in a multi-type verification code picture detection scene are effectively reduced.
Fig. 7 is a schematic structural diagram of a computer-readable storage medium of the present invention. Referring to fig. 7, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In situations involving remote computing devices, the remote computing devices may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to external computing devices (e.g., through the internet using an internet service provider).
The picture identifying code identifying method, the system, the equipment and the storage medium provided by the embodiment of the invention aim at identifying code pictures with characters formed by letters and/or numbers, and combine the identifying code pictures belonging to different types and capable of being converted into gray level pictures meeting requirements after pixel conversion to be used as training samples to train the same target detection model, so that a plurality of identifying code pictures of different types can be detected by using the same target detection model, and memory resources occupied by models in a multi-type identifying code picture detection scene are effectively reduced.
The foregoing is a further detailed description of the invention in connection with specific preferred embodiments and it is not intended to limit the invention to the specific embodiments described. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (11)
1. A picture identifying code identifying method is characterized by comprising the following steps:
s110, preprocessing a plurality of identifying code picture samples belonging to different first classes and having characters to be identified as the same second class to obtain training samples; the pre-processing comprises pixel transformation;
s120, constructing an initial target detection model based on a preset target detection model;
s130, training the initial target detection model based on the training sample to obtain an application target detection model; and
and S140, identifying the verification code picture to be identified according to the application target detection model.
2. The picture authentication code recognition method of claim 1, wherein the step S130 comprises:
s131, dividing to obtain a plurality of preset segments according to a plurality of preset loss thresholds, and acquiring an average loss value corresponding to each preset segment in the training process; and
and S132, taking the model generated in the corresponding preset segment with the minimum average loss value as an application target detection model.
3. The picture authentication code recognition method of claim 1, wherein the step S110 comprises:
performing pixel transformation on the verification code picture sample, and transforming the pixel value into 0 or 255 to generate a gray picture sample; and
and carrying out normalization processing on the gray level picture sample to enable the pixel value to be converted into 0 or 1, and obtaining an initial sample.
4. The picture authentication code recognition method according to claim 1, wherein the predetermined target detection model includes a first detection module, a second detection module and a third detection module, and a detection object size of the first detection module is larger than a detection object size of the second detection module; the size of the detection object of the second detection module is larger than that of the detection object of the third detection module; the step S120 includes:
and eliminating the second detection module and the third detection module in the preset target detection model, and only reserving the first detection module.
5. The picture authentication code recognition method of claim 1, wherein the step S120 comprises:
and discarding a preset number of network layers in a preset target detection model.
6. The picture authentication code recognition method of claim 1, wherein the step S110 comprises:
and when the characters to be recognized in the verification code picture sample are letters, numbers or a combination of the letters and the numbers, determining that the characters to be recognized are in the same second category.
7. The picture verification code identification method according to claim 1, wherein in the training samples, the proportion of each verification code picture sample belonging to different first categories is equal.
8. The picture validation code identification method of claim 1, wherein the predetermined target detection model is the YOLOv4 algorithm.
9. A picture authentication code recognition system for implementing the picture authentication code recognition method according to claim 1, the system comprising:
the image sample screening module is used for preprocessing a plurality of identifying code image samples which belong to different first categories and have characters to be identified as the same second category to obtain training samples; the pre-processing comprises pixel transformation;
the initial target detection model building module is used for building an initial target detection model based on a preset target detection model;
the model training module is used for training the initial target detection model based on the training sample to obtain an application target detection model; and
and the model application identification module is used for identifying the verification code picture to be identified according to the application target detection model.
10. An image authentication code recognition apparatus, comprising:
a processor;
a memory having stored therein an executable program of the processor;
wherein the processor is configured to perform the steps of the picture authentication code identification method of any one of claims 1 to 8 via execution of the executable program.
11. A computer-readable storage medium storing a program, wherein the program, when executed by a processor, implements the steps of the picture authentication code recognition method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210407055.9A CN114782954A (en) | 2022-04-18 | 2022-04-18 | Picture identifying code identification method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210407055.9A CN114782954A (en) | 2022-04-18 | 2022-04-18 | Picture identifying code identification method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114782954A true CN114782954A (en) | 2022-07-22 |
Family
ID=82431068
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210407055.9A Pending CN114782954A (en) | 2022-04-18 | 2022-04-18 | Picture identifying code identification method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114782954A (en) |
-
2022
- 2022-04-18 CN CN202210407055.9A patent/CN114782954A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114399769B (en) | Training method of text recognition model, and text recognition method and device | |
| CN110942074B (en) | Character segmentation recognition method and device, electronic equipment and storage medium | |
| CN111368878B (en) | Optimization method based on SSD target detection, computer equipment and medium | |
| CN113657274B (en) | Table generation method and device, electronic equipment and storage medium | |
| CN112149754B (en) | Information classification method, device, equipment and storage medium | |
| CN111611988A (en) | Picture verification code identification method and device, electronic equipment and computer readable medium | |
| CN112883990A (en) | Data classification method and device, computer storage medium and electronic equipment | |
| CN115829058A (en) | Training sample processing method, cross-modal matching method, device, equipment and medium | |
| CN111563429A (en) | Drawing verification method and device, electronic equipment and storage medium | |
| CN112287957A (en) | Target matching method and device | |
| CN114581732A (en) | Image processing and model training method, device, equipment and storage medium | |
| CN113643260A (en) | Method, apparatus, device, medium and product for detecting image quality | |
| CN112857746A (en) | Tracking method and device of lamplight detector, electronic equipment and storage medium | |
| CN112364821A (en) | Self-recognition method and device for power mode data of relay protection device | |
| CN113762455A (en) | Detection model training method, single character detection method, device, equipment and medium | |
| CN114255381B (en) | Training method of image recognition model, image recognition method, device and medium | |
| CN114782954A (en) | Picture identifying code identification method, system, equipment and storage medium | |
| CN115858776A (en) | Variant text classification recognition method, system, storage medium and electronic equipment | |
| CN115565186A (en) | Method and device for training character recognition model, electronic equipment and storage medium | |
| CN115063826A (en) | Mobile terminal driver license identification method and system based on deep learning | |
| CN113947195A (en) | Model determination method and device, electronic equipment and memory | |
| US20210012472A1 (en) | Adaptive video subsampling for energy efficient object detection | |
| CN110059180B (en) | Article author identity recognition and evaluation model training method and device and storage medium | |
| CN113591787A (en) | Method, device, equipment and storage medium for identifying optical fiber link component | |
| CN111178630A (en) | Load prediction method and device |
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 |