KR20210057845A - Deep Learning Frame Work-Based Image Recognition Method and System Using Training Image Data - Google Patents

Abstract

The present invention provides a deep learning artificial neural network-based image recognition method and a system used therefor. The method includes the steps of: training a deep learning model based on a deep learning framework using the training image data to obtain at least two deep learning models; selecting a predetermined number of deep learning models corresponding to the number of the obtained deep learning models or less from the deep learning models obtained in descending order of recognition accuracy for the verified image data; and recognizing image data to be recognized using at least one of the selected deep learning models. According to the present invention, it is possible to partially solve or alleviate the technical problems of the deep learning framework-related technology by the deep learning image recognition method and apparatus, and a computer-readable storage medium.

Description

Deep Learning Frame Work-Based Image Recognition Method and System Using Training Image Data

The present invention relates to an image recognition method and system, and more particularly, to a deep learning artificial neural network-based image recognition method and system.

In general, deep learning is a field of machine learning that predicts and classifies based on attributes learned through training data, and is a technology that enables programs to make approximate judgments about various situations.

Observed values (eg, images) can be expressed in various ways as vectors of intensity values of various pixels, or more abstractly, as a series of edges, regions with specific shapes, and so on.

The advantage of deep learning is to replace manual acquisition of functions with efficient autonomous or semi-autonomous algorithms for function learning and hierarchical function extraction.

Deep learning is a discipline that combines theory and practice. With the emergence of new algorithmic theories, various deep learning frameworks continue to appear, but the functions provided by deep learning frameworks are relatively simple and lead to deterioration of the user experience.

Therefore, there is a need to partially solve or alleviate the technical problem of the technology related to the deep learning framework by a deep learning image recognition method and apparatus, and a computer-readable storage medium.

Korean Patent Laid-Open Patent No. 10-2014-0000559 "Image recognition method and system", 2014.01.03

In order to solve the problems of the prior art as described above, an object of the present invention is to partially solve or alleviate the technical problem of the deep learning framework related technology by using a deep learning image recognition method and apparatus, and a computer-readable storage medium. have.

Other objects of the present invention will be easily understood through the description of the following embodiments.

In order to achieve the above object, according to an aspect of the present invention, in a deep learning-based image recognition method, at least two deep learning models are trained based on a deep learning framework using training image data. Obtaining a running model; Selecting a predetermined number of deep learning models corresponding to the number or less of the acquired deep learning models from the deep learning models obtained in descending order of recognition accuracy for the verified image data; And recognizing image data to be recognized using at least one of the selected deep learning models.

The method may further include performing image preprocessing on at least one of the training image data, the verified image data, and the image data to be recognized.

In the performing of the image preprocessing, the image preprocessing may include at least one of random cropping, rotation, flipping, brightness adjustment, and contrast adjustment.

The method may further include storing the pre-processed image data in a pre-established memory database.

Recognizing the image data to be recognized may include providing the selected deep learning model to a user; And acquiring a deep learning model selected by the user and recognizing image data to be recognized using the deep learning model selected by the user.

Obtaining the at least two deep learning models may include pushing state information on a training process to a user.

The step of obtaining the at least two deep learning models may include drawing a performance curve for the deep learning model being trained using a web application programming interface in real time.

In the step of obtaining the at least two deep learning models, a plurality of deep learning frameworks may be the same or two or more.

According to another aspect of the present invention, there is provided a deep learning-based image recognition apparatus, comprising: a processor; And a memory storing instructions that, when executed by the processor, cause the processor to acquire at least two deep learning models by training a deep learning model based on a deep learning framework by using the training image data. And, the processor selects a predetermined number of deep learning models from the deep learning models obtained in descending order of recognition accuracy for the verified image data, and the predetermined number is less than or equal to the number of acquired deep learning models. And, there is provided an image recognition system based on a deep learning artificial neural network that recognizes image data to be recognized using at least one of the selected deep learning models.

When executed by the processor, the command may cause the processor to perform image preprocessing on at least one of training image data, verification image data, and image data to be recognized.

The image preprocessing may include at least one of random cropping, rotation, flipping, brightness adjustment, and contrast adjustment.

When executed by the processor, the command may cause the processor to establish a memory database and store a pre-processed image database in a preset memory database.

The instruction, when executed by the processor, causes the processor to provide a selected deep training model to a user, obtain a deep learning model selected by the user, and an image to be recognized using the deep learning model selected by the user. You can make your data aware.

The instruction, when executed by the processor, causes the processor to train a deep learning model based on a deep learning framework by using training image data to obtain at least two deep learning models. You can have the status information pushed to the user.

The instruction, when executed by the processor, causes the processor to train a deep learning model based on a deep learning framework by using training image data to obtain at least two deep learning models, a web application programming interface It can be used to draw the performance curve of the deep learning model currently being trained in real time.

According to the deep learning artificial neural network-based image recognition method and system according to the present invention, the deep learning image recognition method and device, and the effect of partially solving or mitigating the technical problem of the deep learning framework related technology by a computer-readable storage medium Have.

1 is a flowchart illustrating a deep learning-based image recognition method according to an embodiment of the present invention.
2 is a flowchart illustrating a deep learning-based image recognition method according to another embodiment of the present invention.
3 is a flowchart illustrating a deep learning-based image recognition method according to another embodiment of the present invention.
4 is a flowchart illustrating a deep learning-based image recognition method according to another embodiment of the present invention.
5 is a block diagram illustrating a deep learning-based image recognition apparatus according to an embodiment of the present invention.
6 is a block diagram illustrating a deep learning-based image recognition apparatus according to another embodiment of the present invention.
7 is a block diagram illustrating a computer device according to an embodiment of the present invention.

In the present invention, various modifications may be made and various embodiments may be provided, and specific embodiments will be illustrated in the drawings and described in detail. However, this is not intended to limit the present invention to a specific embodiment, and should be understood as including all changes, equivalents, or substitutes included in the technical spirit and scope of the present invention, and may be modified in various other forms. It can be, and the scope of the present invention is not limited to the following examples.

Hereinafter, embodiments according to the present invention will be described in detail with reference to the accompanying drawings, and the same reference numerals are assigned to the same or corresponding components regardless of the reference numerals, and redundant descriptions thereof will be omitted.

1 is a flowchart illustrating a deep learning-based image recognition method according to an embodiment of the present invention.

Referring to FIG. 1, step 101 is an optional step, and image preprocessing is performed on image data to be processed. In some embodiments, the image data to be processed includes at least one of training image data for training a deep learning model, verification image data for verifying the trained deep learning model, and image data to be recognized based on a deep learning framework. Can include. However, it should be exemplified that the image preprocessing process is not required in this method. That is, the present method may directly process an original image or may process image data processed by a third party. As such, the pre-processing step 101 is optional.

In step 102, the deep learning model acquires at least two deep learning models trained based on the deep learning framework by using the trained image data. In some embodiments, the number of deep learning frameworks may be two or more.

In this embodiment, the deep learning framework may be PyTorch, Tensorflow, Caffe, Keras, MXNet, and the like, and is not limited to this embodiment. At least two deep learning models may be obtained by training a deep learning model based on a deep learning framework using the training image data. For example, different deep learning models can be obtained by setting different initial parameters and using the same training image data.

Optionally, a plurality of different deep learning models train deep learning models based on different deep learning frameworks using the same training image data, or train deep learning models with different activation functions using the same training image data. By doing so, or by training the same or different deep learning models using different training image data or the like, different deep learning models can be obtained.

These different deep learning models can reflect the features learned by the corresponding deep learning framework from the corresponding training image data under the corresponding initial parameter setting, so that the deep learning model will have different recognition accuracy for the same verification image data. I can.

In step 103, a predetermined number of deep learning models are selected from deep learning models obtained in descending order of recognition accuracy for the verified image data.

The predetermined number may be less than or equal to the number of acquired deep learning models, and the predetermined number may be set according to system performance and/or implementation requirements in a specific implementation, and is not limited to the present invention. For example, the predetermined number may be 2.

In this embodiment, after a plurality of deep learning models are acquired through training, it is often necessary to verify the recognition accuracy of the deep learning model trained on the verification set or verification image data. Accordingly, in this embodiment, according to the recognition accuracy of each deep learning model acquired through training on the verification image data, a predetermined number of deep learning models are selected in descending order of recognition accuracy. For example, if the predetermined number is 2, the deep learning model with the highest accuracy among the deep learning models acquired through training according to the recognition accuracy of the deep learning model obtained through training for the verification set and the second highest accuracy. You can choose a high deep learning model.

After the step of selecting a predetermined number of deep learning models, the step of recognizing image data to be recognized using at least one of the selected deep learning models may be performed, which provides the selected deep learning model to a user (104 ), acquiring a deep learning model selected by the user, and recognizing image data to be recognized using the deep learning model selected by the user (105).

Step 104 is an optional step, and the selected deep learning model may be provided to the user.

In this embodiment, after a predetermined deep learning model is selected from a deep learning model acquired through training in descending order of recognition accuracy for a verification set, the selected deep learning model may be provided to the user.

In certain implementations, after a predetermined number of deep learning models are selected in descending order of recognition accuracy for the validation set, the selected deep learning model may be stored, and the stored deep learning model is provided to the user to determine the deep learning model to be used by the user You can choose. For example, a plurality of options and corresponding descriptions are provided in a user interface displayed on the display, so that the user can select an option for use.

Step 105 is an optional step. A deep learning model selected by the user is obtained, and image data to be recognized can be recognized using a deep learning model selected by the user. I can.

In this embodiment, after new image data is received, the deep learning model to be used may be determined according to an option that can be selected by the user on, for example, a user interface, and the image data to be recognized uses a deep learning model. Can be recognized.

More generally, after a predetermined number of deep learning models are selected from the acquired deep learning models in descending order of recognition accuracy for the verification image data, the image data to be recognized may be recognized using at least one of the selected deep learning models. . For example, at least one deep learning model may not be manually selected by the user, but may be automatically selected by a computer, server, etc. (e.g., a deep learning model with the highest accuracy, a training convergence rate is The fastest deep learning model, the deepest learning model with the fastest recognition speed, or a deep learning model that satisfies other conditions). In other words, this step can be fully automated without user participation.

In the deep learning-based image recognition method, after image preprocessing is performed on the image data to be processed, the deep learning model can be trained based on the deep learning framework by acquiring at least two deep learning models using the training image data. have. A predetermined number of deep learning models are selected from the deep learning models acquired through training in descending order of recognition accuracy for the verification set, the selected deep learning models are provided to the user, and the deep learning models selected by the user are obtained. Image data to be recognized is recognized using a deep learning model selected by a user.

In this way, an overall solution for providing a deep learning framework can be realized, which is convenient for a user to acquire a deep learning model and then recognize the image data received through the acquired deep learning model, and It can improve recognition accuracy and improve user experience.

In some embodiments, the number of deep learning frameworks may be two or more, and in step 102 of providing the selected deep learning model to a user, the plurality of deep learning frameworks may be the same or two or more.

2 is a flowchart illustrating a deep learning-based image recognition method according to another embodiment of the present invention.

As shown in FIG. 2, step 101 of the embodiment shown in FIG. 1 may include the following steps.

In step 201, one or more operations of random cropping, rotation, flipping, brightness adjustment, and contrast adjustment are performed on the image data to be processed.

In this embodiment, before the image data is trained, it is necessary to first perform image pre-processing on the image data to be processed, which performs operations such as random cropping, rotation, flipping, brightness adjustment, and contrast adjustment, etc. Includes performing.

Further, after step 201, the method may further include the following steps.

In step 202, the preprocessed image data is stored in a pre-established memory database.

In this embodiment, the pre-established memory database may be a deep learning database such as Lightning Memory-Mapped Database (hereinafter, simply LMDB) or LevelDB.

Of course, other types of databases could also be used as the memory database. The specific type of memory database used is not limited in this embodiment.

In this embodiment, after image preprocessing is performed on the image data to be processed, step 102 may be directly performed, or step 202 may be performed first, and if step 102 is performed, in step 102, deep learning In order to obtain a model, a deep learning model can be trained based on a deep learning framework by using training image data stored in a memory database.

3 is a flowchart illustrating a deep learning-based image recognition method according to another embodiment of the present invention.

As shown in Fig. 3, after step 102 of the embodiment shown in Fig. 1, the method may further include the following steps:

In step 301, in the process of training the deep learning model based on the deep learning framework using the training image data, in order to obtain at least two deep learning models, state information on the training process is pushed to the user.

In this embodiment, in order to facilitate the user to concentrate on the training process, the step of obtaining a deep learning model in the process of training a deep learning model based on a deep learning framework using training image data, error, information or Status information about the training process, such as alerts, can be pushed in real time to an account of instant messaging software registered by the user, such as WeChat or QQ.

Of course, the status information about the training course can be pushed in real time to the email account registered by the user, and the status information about the training course can also be sent in short messages. As long as the state information about the training process can be pushed to the user, the method of pushing the state information about the training process is not limited in this embodiment.

4 is an exemplary flowchart of a deep learning-based image recognition method according to another embodiment of the present invention.

4 is a flowchart illustrating a deep learning-based image recognition method according to another embodiment of the present invention.

In step 401, in the process of training the deep learning model based on the deep learning framework using the training image data, in the step of acquiring at least two deep learning models, a performance curve for the deep learning model currently being trained is Derived in real time using a web application programming interface (API).

In step 402, the derived performance curve is presented.

In this embodiment, in the process of training a deep learning model based on a deep learning framework using training image data, a deep learning model, a performance curve such as training loss, training accuracy, or a confusion matrix, etc. Get One of the deep learning models currently being trained can be drawn in real time using a web API (for example, a crayon or a tensor board) and presented to the user.

The deep learning-based image recognition method according to some embodiments of the present invention provides an overall solution of a deep learning framework that is convenient for a user to acquire a deep learning model, and through this, it is possible to realize the recognition of received image data. Acquire a deep learning model to improve the accuracy of image recognition and improve user experience.

5 is a block diagram illustrating a deep learning-based image recognition apparatus according to an embodiment of the present invention. The deep learning-based image recognition apparatus according to an embodiment of the present invention may perform the deep learning-based image recognition method according to the embodiment of the present invention.

As shown in FIG. 5, the deep learning-based image recognition apparatus includes an optional image preprocessing module 51, a training module 52, a model screening module 53, an optional providing module 54, and a recognition module 55. can do.

The optional image preprocessing module 51 is configured to perform image preprocessing on image data to be processed.

The training module 52 is configured to acquire at least two deep learning models by training a deep learning model based on the deep learning framework using the training image data. In this embodiment, the deep learning framework may be PyTorch, Tensorflow, Caffe, Keras, MXNet, and the like, and is not limited to this embodiment. The training module 52 trains a deep learning model based on a deep learning framework using the training image data, which can obtain at least two deep learning models.

The model screening module 53 is configured to select a predetermined number of deep learning models from the deep learning models obtained by the training module 52 in descending order of recognition accuracy for the verification image data; Here, the predetermined number is less than or equal to the number of acquired deep learning models. The predetermined number may be set according to system performance and/or implementation requirements in a specific implementation, and is not limited to this embodiment. For example, the predetermined number may be 2.

In this embodiment, after performing training to obtain the deep learning model, the training module 52 needs to verify the recognition accuracy of the deep learning model with respect to the verification set. Accordingly, in this embodiment, the model screening module 53 selects a predetermined number of deep learning models in descending order of the recognition accuracy of the deep learning model obtained through training on the verification set.

For example, when the preset number is 2, the model screening module 53 provides the highest recognition accuracy and the second highest recognition accuracy among the deep learning models acquired through training according to the recognition accuracy of the acquired deep learning model. You can select the deep learning model you have through training on the validation set.

The optional providing module 54 is configured to provide the deep learning model selected by the model screening module 53 to the user. In this embodiment, the model screening module 53 selects a predetermined number of deep learning models from the acquired deep learning models through training in descending order of recognition accuracy for the verification set, and then the providing module 54 selects the selected deep learning models. The running model can be provided to the user.

In a specific implementation, the model screening module 53 selects a predetermined number of deep learning models in descending order of recognition accuracy for the validation set, and then the model screening module 53 provides the selected deep learning model and then stores the provided model. I can. The deep learning model stored by the model screening model 53 is provided to the user, so that the user can select a deep learning model to use.

The optional recognition module 55 is configured to acquire a deep learning model selected by a user and recognize image data to be recognized through the deep learning model selected by the user.

In this embodiment, after the new image data is received, the recognition module 55 may acquire a deep learning model selected by the user and realize recognition of the image data received through the deep learning model selected by the user.

As described above, after a predetermined number of deep learning models are selected from the acquired deep learning models, the recognition module 55 may recognize image data to be recognized using at least one of the selected deep learning models without user participation. . Descending order of recognition accuracy for verification image data. For example, at least one deep learning model may not be manually selected by the user, but may be automatically selected by a computer, server, etc. Is the fastest deep learning model, the deepest learning model with the fastest recognition speed, or a deep learning model that satisfies other conditions is recognized by these deep learning models).

In the deep learning-based image recognition apparatus, after the selective image preprocessing module 51 performs image preprocessing on the image data to be processed, the training module 52 uses at least the treering image data based on the deep learning framework. Tree deep learning models. Following the two deep learning models, the model screening module 53 selects a predetermined number of deep expectation models from the deep learning models acquired through training in descending order of recognition accuracy for the verification set, and an optional provision module 54 ) Provides the selected deep learning. The selective recognition module 55 may acquire the deep learning model selected by the user and recognize the received image data using the deep learning model selected by the user. In this way, an overall solution for providing a deep learning framework can be realized, which means that the user acquires a deep learning model, and then realizes the recognition of the image data received through the acquired deep learning model, resulting in the accuracy of the image. Improves.

6 is an exemplary structural diagram of an image recognition apparatus based on deep learning according to another embodiment of the present invention.

6 is different from the deep learning-based image recognition device shown in FIG. 5. The image preprocessing module 51 may be specifically configured to perform one or a combination of the following operations such as random cropping, rotation, flipping, brightness adjustment, and contrast adjustment on image data to be processed.

In this embodiment, before the training module 52 trains the image data, the image pre-processing module 51 must first perform image pre-processing on the image data to be processed, which is a random cropping and rotating image data to be processed. , Flipping, adjusting brightness and/or adjusting contrast, and the like.

In addition, the deep learning-based image recognition apparatus includes a database setting module 56 and a storage module 57, the database setting module 56 is configured to build a memory database, and the storage module 57 is an image preprocessing module ( 51) is configured to store the processed image data in a memory database previously established by the database setting module 56 after performing image pre-processing on the image data to be processed.

In this embodiment, the memory database pre-built by the data setting module 56 may be a deep learning database such as LMDB or LevelDB. Of course, other types of databases can also be used as the memory. The specific type of memory database used is not limited in this embodiment.

After the image preprocessing module 51 performs image preprocessing on the image data to be processed, the storage module 57 may store the processed image data in a memory database previously established by the database setting module 56.

In addition, the deep learning-based image recognition device may include a message pushing module 58. The message pushing module 58 is configured to push state information about a training process to a user in a process of training a deep learning model based on a deep learning framework that uses training image data to obtain a deep learning model.

In this embodiment, in order to facilitate the user to concentrate on the training process, in the process of training a deep learning model based on a deep learning framework using training image data, in order to obtain a deep learning model, a message pushing module 58 can push status information about the training process, such as errors, information or warnings, in real time to an account of instant messaging software registered by the user, such as WeChat or QQ.

Of course, the message pushing module 58 can also push status information about the training process in real time to an account in an email registered by the user, or the message pushing module 58 can also send a short message about status information about the training process. Through the user's mobile phone. The method of pushing the status information for the training process by the message pushing module 58 is not limited in this embodiment as long as the status information for the training process can be pushed to the user.

In addition, the deep learning-based image recognition device may further include a real-time monitoring module 59 and a presentation module 510.

The real-time monitoring module 59 uses the training image data to train the deep learning model based on the deep learning framework by the training module 52 in real time using a web API to obtain a deep learning model. It is configured to derive a performance curve for the model.

The presentation module 510 is configured to present a performance curve derived by the real-time monitoring module 59.

In this embodiment, in the process of training a deep learning model based on a deep learning framework using training image data, a deep learning model, a performance curve such as training loss, training accuracy, and/or a confusion matrix are obtained. The web interface of the deep learning model currently being trained can be derived in real time by using a web API (eg, crayon or tensor board) by the real-time monitoring module 59 and presented to the user.

The deep learning-based image recognition apparatus according to some embodiments of the present invention provides an overall solution of a deep learning framework that is convenient for acquiring a deep learning model, and through this, it is possible to realize the recognition of received image data. Acquire a deep learning model to improve the accuracy of image recognition and improve user experience.

7 is a block diagram illustrating a computer device according to an embodiment of the present invention.

As shown in FIG. 7, the computer device may include a memory, a processor, and a computer program stored in a memory and executable on a processor. When executed by the processor, the computer program may perform a deep learning-based image recognition method according to some embodiments of the present disclosure.

The computer device may be a terminal device or a server. The specific form of the computer device is not limited in this embodiment.

The computer device 12 shown in FIG. 7 is for illustrative purposes only, and no limitations should be imposed on the functions and scope of use of the embodiments of the present invention.

The computer device 12 is implemented in the form of a general-purpose computing device. Components of the computer device 12 include one or more processors or processing units 16, system memory 28, and a bus 18 for connecting different system components (including system memory 28 and processing unit 16). ), but is not limited thereto.

Computer device 12 typically includes a variety of computer system readable media. These media may be any available media that can be accessed by computer device 12, including volatile and non-volatile media, removable and non-removable media.

The system memory 28 may include a computer system readable medium in the form of a volatile memory such as random access memory (RAM) 30 and or cache memory 32. Computer device 12 is another removable/non-removable and volatile/non-volatile computer system storage medium. By way of example only, storage system 34 can be used to read and write from non-removable and non-volatile magnetic media (not shown in FIG. 7) (generally referred to as “hard drivers”). As shown in Fig. 7, a magnetic disk driver for reading and writing from a removable and nonvolatile magnetic disk (e.g., "floppy disk") and an optical disk driver for reading and writing from a removable and nonvolatile optical disk (e.g., There are cases such as CD-ROM (Compact Disc Read Only Memory), hereinafter, DVD-ROM (Digital Video Disc Read Only Memory) or other optical media, etc. Bus 18 through one or more data medium interfaces, The memory 28 may include at least one program product having a group of (eg, at least one) program modules configured to perform the functions of various embodiments of the present disclosure.

The program/utility 40 having at least one program module 42 may be stored in the memory 28, for example. Such program modules 42 include, but are not limited to, an operating system, one or more applications, other program modules, and program data, and each or some combination of these examples may include an implementation of a network environment. Program module 42 generally performs functions and/or methods described in embodiments of the present disclosure.

Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays, etc.), and may also communicate with one or more devices that allow a user to interact with the computer. have. It may include device 12 and or any device (eg, network card, modem, etc.) that enables computer device 12 to communicate with one or more other computing devices. This communication can be performed through an input/output (I/O) interface 22. Further, the computer device 12 may communicate with one or more networks (eg, a local area network (LAN), a wide area communication device). It is possible to have a network (hereinafter simply WAN) and a public network (eg, the Internet) through the network adapter 20. As shown in FIG. 7, network adapter 20 communicates with other modules of computer device 12 via bus 18.

The processing unit 16 executes various types of functional applications and data processing by executing a program stored in the system memory 28, for example, a deep learning-based image recognition method according to an embodiment of the present invention.

An embodiment of the present invention further provides a non-transitory computer-readable storage medium in which a computer program is stored. When the computer program is executed by a processor, it may perform a deep learning-based image recognition method according to an exemplary embodiment of the present disclosure.

Computer-readable signal media may include data signals that propagate in baseband or as part of a carrier wave, the data signals carrying computer-readable program code. The propagated data signal can take a variety of forms including, but not limited to, electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can transmit, propagate, or transmit a program for use by or in connection with an instruction execution system, device, or device. have.

Program code embodied in a computer-readable medium may be transmitted using any suitable medium including, but not limited to, wireless, wired, fiber optic cable, RF, or the like, or any suitable combination thereof.

Computer program code for performing an operation according to an embodiment of the present disclosure includes one or more programming languages, or object-oriented programming languages such as Java, Smalltalk, C++, and also includes conventional procedural programming thereof. It can be written using combinations. Languages such as "C" language or similar programming language. The program code can be fully executed on the user computer, partially executed on the user computer, executed as a standalone software package, executed partially on the user computer and partially on a remote computer, or fully executed on a remote computer or server. In the case of a remote computer, the remote computer may be connected or connected to the user computer through any kind of network including a local area network (hereinafter, referred to as a LAN) or a wide area network (hereinafter referred to as a short WAN).

An embodiment of the present invention provides a computer program product. When the instructions of the computer program product are executed by the processor, the deep learning-based image recognition method according to the exemplary embodiment of the present disclosure may be executed.

Although the present invention has been described with reference to the accompanying drawings, various modifications and variations can be made without departing from the technical spirit of the present invention. Therefore, the scope of the present invention should not be limited to the described embodiments, and should be defined by the claims and equivalents as well as the claims to be described later.

12: Computer device 14: External device
16: processing unit 18: bus
20: network adapter 22: input/output interface
28: system memory 30: random access memory (RAM)
32: cache memory 34: storage system
40: utility 42: program module
51: image preprocessing module 52: training module
53: model screening module 54: optional provided module
55: recognition module 56: database building module
57: storage module 58: message pushing module
59: real-time monitoring module 510: presentation module

Claims (13)

In the deep learning-based image recognition method,
Training a deep learning model based on a deep learning framework using the training image data to obtain at least two deep learning models;
Selecting a predetermined number of deep learning models corresponding to the number or less of the acquired deep learning models from the deep learning models obtained in descending order of recognition accuracy for the verified image data; And
Recognizing image data to be recognized using at least one of the selected deep learning models;
Containing, deep learning artificial neural network-based image recognition method. The method according to claim 1,
The deep learning artificial neural network-based image recognition method further comprising performing image preprocessing on at least one of the training image data, the verified image data, and the image data to be recognized. The method according to claim 2,
The step of performing the image pre-processing,
The image recognition method based on a deep learning artificial neural network, wherein the image preprocessing includes at least one of random cropping, rotation, flipping, brightness adjustment, and contrast adjustment. The method of claim 3,
The image recognition method based on a deep learning artificial neural network, further comprising the step of storing the pre-processed image data in a pre-established memory database. The method according to claim 1,
Recognizing the image data to be recognized,
Providing the selected deep learning model to a user; And
Acquiring a deep learning model selected by a user and recognizing image data to be recognized using the deep learning model selected by the user;
Containing, deep learning artificial neural network-based image recognition method. The method according to claim 1,
The step of obtaining the at least two deep learning models,
Deep learning artificial neural network based image recognition method comprising the step of pushing the state information on the training process to the user. The method according to claim 1,
The step of obtaining the at least two deep learning models,
A deep learning artificial neural network based image recognition method comprising the step of drawing a performance curve for a deep learning model being trained using a web application programming interface in real time. The method according to claim 1,
The step of obtaining the at least two deep learning models,
A deep learning artificial neural network-based image recognition method in which multiple deep learning frameworks are the same or more than one. In the deep learning-based image recognition device,
Processor; And
A memory storing instructions that, when executed by the processor, cause the processor to acquire at least two deep learning models by training a deep learning model based on a deep learning framework by using the training image data; and ,
The processor,
Select a predetermined number of deep learning models from deep learning models acquired in descending order of recognition accuracy for verified image data, and make the predetermined number less than or equal to the number of acquired deep learning models,
A deep learning artificial neural network based image recognition system for recognizing image data to be recognized using at least one of the selected deep learning models. The method of claim 9,
The command is:
A deep learning artificial neural network based image recognition system that, when executed by the processor, causes the processor to perform image preprocessing on at least one of training image data, verification image data, and image data to be recognized. The method of claim 10,
The image pre-processing,
A deep learning artificial neural network based image recognition system comprising at least one of random cropping, rotation, flipping, brightness adjustment, and contrast adjustment. The method of claim 9,
The above command is:
The deep learning artificial neural network based image recognition system, when executed by the processor, causes the processor to establish a memory database and store the pre-processed image database in a preset memory database. The method of claim 9,
The command is:
When executed by the processor, to cause the processor to provide the selected deep training model to the user, to obtain the deep learning model selected by the user, and to recognize the image data to be recognized using the deep learning model selected by the user. A deep learning artificial neural network based image recognition system.

Images