Image recognition system based on big data

Abstract

The invention discloses an image recognition system based on big data, and the system comprises a recognition module which is used for recognizing the features and sizes of face images, so as to facilitate the subsequent classification; the input module is used for classifying and storing the face images according to the features and the sizes recognized by the recognition module, and the input module is connected with the recognition module; and the second judgment module is used for judging whether the data identified by the identification module are the same in the input module or not, and the second judgment module is connected with the identification module and the input module. The invention belongs to the technical field of image recognition, and aims to solve the problem that criminal identity recognition cannot be performed on a recognized face in the prior art. The technical effects are that through the arrangement of the recognition module, the input module, the first judgment module and the second reminding module, while the face of a person is recognized, criminal identity recognition can be performed on the person, and the practicability is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular to an image recognition system based on big data. Background Art

[0002] Image recognition refers to the technology of using computers to process, analyze and understand images to identify targets and objects of various different patterns. It is a practical application of deep learning algorithms. Face image recognition is a type of image recognition. Face image recognition is a biometric technology that identifies people based on their facial features. It uses a camera or camera to collect images or video streams containing faces, automatically detects and tracks faces, and then recognizes the detected faces.

[0003] However, when the existing face image recognition is running, the person being recognized may deliberately cover part of his face to prevent danger, resulting in the recognition system being unable to recognize the part of the face. In addition, whether the recognition is successful or not, the system will directly jump to the next picture, lacking a reminder function, resulting in the need for repeated recognition. Therefore, an image recognition system based on big data is invented. Summary of the invention

[0004] In view of the above-mentioned and / or existing problems in an existing image recognition system based on big data, the present invention is proposed.

[0005] Therefore, the purpose of the present invention is to provide an image recognition system based on big data, which can solve the above-mentioned existing problems.

[0006] To solve the above technical problems, according to one aspect of the present invention, the present invention provides the following technical solutions:

[0007] An image recognition system based on big data, comprising:

[0008] The recognition module is used to identify the features and size of the face image for subsequent classification;

[0009] An input module, used for classifying and storing the face images according to the features and sizes identified by the recognition module, wherein the input module is connected to the recognition module;

[0010] A second judgment module is used to judge whether the data identified by the recognition module is the same as that in the input module, and the second judgment module is connected with the recognition module and the input module;

[0011] A first judgment module, used to judge whether there is a criminal in the face image identified by the recognition module, wherein the first judgment module is connected to the recognition module;

[0012] A first reminder module, used to remind the person in the collected image when the second judgment module fails to identify the person, wherein the first reminder module is connected to the second judgment module;

[0013] The second reminder module is used to remind the staff when the first judgment module successfully recognizes, and the second reminder module is connected to the first judgment module.

[0014] As a preferred solution of the image recognition system based on big data described in the present invention, the recognition module includes:

[0015] An image acquisition module, used for acquiring criminal images from the Internet;

[0016] An image acquisition module is used to acquire facial images of people by photographing them;

[0017] The third analysis module is used to analyze the images collected by the image acquisition module and the image collection module to analyze the gender of the person. The third analysis module is connected to the image acquisition module and the image collection module.

[0018] As a preferred solution of the image recognition system based on big data described in the present invention, the recognition module further includes:

[0019] A feature extraction module, used for extracting facial features from the images acquired by the image acquisition module and the image collection module, wherein the feature extraction module is connected to the third analysis module;

[0020] A punctuation module, used for performing punctuation in the features extracted by the feature extraction module, wherein the punctuation module is connected to the feature extraction module;

[0021] A calculation module, used for calculating the distance of the points marked by the punctuation module, wherein the calculation module is connected to the punctuation module;

[0022] The conversion module is used to convert the values ​​calculated by the calculation module to obtain the actual width and length of the face, and the conversion module is connected to the calculation module.

[0023] As a preferred solution of the image recognition system based on big data described in the present invention, the input module includes:

[0024] A numerical statistics module is used to count the numerical values ​​converted by the conversion module, and the numerical statistics module is connected to the conversion module;

[0025] A first database is used to store facial images of women of different sizes, wherein the first database is connected to the numerical statistics module;

[0026] The second database is used to store facial images of men of different sizes, and the second database is connected to the numerical statistics module.

[0027] As a preferred solution of the big data-based image recognition system described in the present invention, the first database and the second database are both provided with a plurality of folders so as to be able to classify and store facial images of different sizes.

[0028] As a preferred solution of the image recognition system based on big data described in the present invention, the second judgment module includes:

[0029] A second analysis module is used to analyze the image recognized by the recognition module to analyze the position of the recognized image in the input module, and the second analysis module is connected to the conversion module;

[0030] The second comparison module is used to compare the image recognized by the recognition module with the image stored in the recording module to compare whether there is a similarity in the recording module. The second comparison module is connected to the second analysis module.

[0031] As a preferred solution of the image recognition system based on big data described in the present invention, the first reminder module includes:

[0032] A counting module, used for calculating the number of comparison failures of the second comparison module, wherein the counting module is connected to the second comparison module;

[0033] The alarm module is used to remind personnel when the counting module reaches the set number of times, and the alarm module is connected to the counting module.

[0034] As a preferred solution of the image recognition system based on big data described in the present invention, the first judgment module includes:

[0035] A first storage module is used to store facial images of female criminals in different sizes;

[0036] The second storage module is used to store facial images of male criminals in different sizes;

[0037] A first analysis module is used to analyze the image recognized by the recognition module to analyze the position of the recognized image in the first storage module and the second storage module, wherein the first analysis module is connected to the recognition module;

[0038] The first comparison module is used to compare the image recognized by the recognition module with the images stored in the first storage module and the second storage module to compare whether there is a similarity. The first comparison module is connected to the first analysis module, the first storage module and the second storage module.

[0039] As a preferred solution of the big data-based image recognition system described in the present invention, the first storage module and the second storage module are both provided with a plurality of folders so as to be able to classify and store facial images of different sizes.

[0040] As a preferred solution of the image recognition system based on big data described in the present invention, the second reminder module includes:

[0041] The second storage module is used to store the contact information of the on-duty personnel;

[0042] An acquisition module, used for acquiring data in the second storage module, wherein the acquisition module is connected to the first judgment module and the second storage module;

[0043] The notification module is used to notify the on-duty personnel according to the data acquired by the acquisition module, and the notification module is connected to the acquisition module.

[0044] Compared with existing technologies:

[0045] By setting up the recognition module, the entry module, the first judgment module and the second reminder module, it is possible to improve the practicality while realizing the face recognition of the personnel; in addition, by setting up the second judgment module and the first reminder module, it is possible to realize the classified storage and classified recognition of facial images. By classifying and storing facial images, targeted recognition can be carried out according to image features, which will improve the recognition efficiency to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0047] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0048] The present invention provides an image recognition system based on big data, please refer to Figure 1 ;

[0049] It includes: a recognition module, which is used to recognize the features and sizes of a face image for subsequent classification; an input module, which is used to classify and store the face image according to the features and sizes recognized by the recognition module, and the input module is connected to the recognition module; a second judgment module, which is used to judge whether the data recognized by the recognition module is the same as that in the input module, and the second judgment module is connected to the recognition module and the input module; a first judgment module, which is used to judge whether there is a criminal in the face image recognized by the recognition module, and the first judgment module is connected to the recognition module; a first reminder module, which is used to remind the person in the collected image when the second judgment module fails to recognize, and the first reminder module is connected to the second judgment module; a second reminder module, which is used to remind the staff when the first judgment module successfully recognizes, and the second reminder module is connected to the first judgment module.

[0050] The identification module includes: an image acquisition module, which is used to obtain criminal images from the Internet; an image collection module, which is used to collect facial images of people by shooting; a third analysis module, which is used to analyze the images collected by the image acquisition module and the image collection module to analyze the gender of the people, and the third analysis module is connected to the image acquisition module and the image collection module; a feature extraction module, which is used to extract facial features from the images collected by the image acquisition module and the image collection module, and the feature extraction module is connected to the third analysis module; a punctuation module, which is used to punctuate the features extracted by the feature extraction module, and the punctuation module is connected to the feature extraction module; a calculation module, which is used to calculate the distance of the points marked by the punctuation module, and the calculation module is connected to the punctuation module; a conversion module, which is used to convert the values ​​calculated by the calculation module to obtain the actual width and length of the face, and the conversion module is connected to the calculation module.

[0051] The input module includes: a numerical statistics module, which is used to count the numerical values ​​converted by the conversion module, and the numerical statistics module is connected to the conversion module; a first database, which is used to store facial images of different sizes of women, and the first database is connected to the numerical statistics module; a second database, which is used to store facial images of different sizes of men, and the second database is connected to the numerical statistics module. The first database and the second database are both provided with a number of folders so that facial images of different sizes can be classified and stored.

[0052] The second judgment module includes: a second analysis module, which is used to analyze the image recognized by the recognition module to analyze the position of the recognized image in the recording module, and the second analysis module is connected to the conversion module; a second comparison module, which is used to compare the image recognized by the recognition module with the image stored in the recording module to compare whether there is a same image in the recording module, and the second comparison module is connected to the second analysis module;

[0053] The first reminder module includes: a counting module, which is used to calculate the number of comparison failures of the second comparison module, and the counting module is connected to the second comparison module; an alarm module, which is used to remind personnel when the counting module reaches a set number of times, and the alarm module is connected to the counting module.

[0054] The first judgment module includes: a first storage module, which is used to store facial images of different sizes of female criminals; a second storage module, which is used to store facial images of different sizes of male criminals; a first analysis module, which is used to analyze the image recognized by the recognition module to analyze the position of the recognized image in the first storage module and the second storage module, and the first analysis module is connected to the recognition module; a first comparison module, which is used to compare the image recognized by the recognition module with the images stored in the first storage module and the second storage module to compare whether there is a similarity, and the first comparison module is connected to the first analysis module, the first storage module and the second storage module. The first storage module and the second storage module are each provided with a plurality of folders so as to be able to classify and store facial images of different sizes.

[0055] The second reminder module includes: a second storage module, used to store the contact information of the on-duty personnel; an acquisition module, used to acquire the data in the second storage module, and the acquisition module is connected to the first judgment module and the second storage module; a notification module, used to notify the on-duty personnel according to the data acquired by the acquisition module, and the notification module is connected to the acquisition module.

[0056] When used, the specific steps are as follows:

[0057] Step 1: The criminal image is obtained from the Internet through the image acquisition module, or the facial image of the person is collected by the image acquisition module by shooting. After that, the images collected by the image acquisition module and the image acquisition module are analyzed by the third analysis module to analyze the gender of the person. After the analysis, the facial features are extracted from the images collected by the image acquisition module and the image acquisition module by the feature extraction module. After the extraction, the features extracted by the feature extraction module are punctuated by the punctuation module. After the punctuation, the distance of the points marked by the punctuation module is calculated by the calculation module. After the calculation, the values ​​calculated by the calculation module are converted by the conversion module to obtain the actual width and length of the face. At this time, the criminal image is correspondingly stored in the first storage module or the second storage module, and the person image is correspondingly stored in the first database or the second database.

[0058] Step 2: When it is necessary to verify the identity of a person, the identification module will be used for identification. After identification, the image identified by the identification module will be analyzed by the second analysis module to analyze the position of the identified image in the input module. After that, the image identified by the identification module will be compared with the image stored in the input module through the second comparison module to compare whether there is a same in the input module. If there is a same, it means that the verification is successful. If not, step three will be executed. In this process, the image identified by the identification module will also be analyzed by the first analysis module to analyze the position of the identified image in the first storage module and the second storage module. After that, the image identified by the identification module will be compared with the images stored in the first storage module and the second storage module through the first comparison module to compare whether there is a same. If not, it means that the person is not a criminal. If they are the same, step four will be executed.

[0059] Step 3: The number of comparison failures of the second comparison module is calculated through the counting module. If the number reaches the set number, the alarm module will remind the personnel;

[0060] Step 4: The data in the second storage module is acquired through the acquisition module. After acquisition, the on-duty personnel are notified through the notification module according to the data acquired by the acquisition module.

Claims

1. An image recognition system based on big data, characterized in that: include: The recognition module is used to identify the features and size of the face image for subsequent classification; An input module is used to classify and store facial images according to the features and sizes identified by the recognition module; A second judgment module is used to judge whether the data identified by the recognition module is the same as that in the input module; The first judgment module is used to judge whether there is a criminal in the face image recognized by the recognition module; A first reminder module is used to remind the person in the collected image when the second judgment module fails to identify the person; The second reminder module is used to remind the staff when the first judgment module successfully recognizes.

2. The image recognition system based on big data according to claim 1, characterized in that: The identification module comprises: An image acquisition module, used for acquiring criminal images from the Internet; An image acquisition module is used to acquire facial images of people by photographing them; The third analysis module is used to analyze the images collected by the image acquisition module and the image collection module to analyze the gender of the person. The third analysis module is connected to the image acquisition module and the image collection module.

3. The image recognition system based on big data according to claim 2, characterized in that: The identification module also includes: A feature extraction module, used for extracting facial features from the images acquired by the image acquisition module and the image collection module, wherein the feature extraction module is connected to the third analysis module; A punctuation module, used for performing punctuation in the features extracted by the feature extraction module, wherein the punctuation module is connected to the feature extraction module; A calculation module, used for calculating the distance of the points marked by the punctuation module, wherein the calculation module is connected to the punctuation module; The conversion module is used to convert the values ​​calculated by the calculation module to obtain the actual width and length of the face, and the conversion module is connected to the calculation module.

4. The image recognition system based on big data according to claim 3, characterized in that: The input module includes: A numerical statistics module is used to count the numerical values ​​converted by the conversion module, and the numerical statistics module is connected to the conversion module; A first database is used to store facial images of women of different sizes, wherein the first database is connected to the numerical statistics module; The second database is used to store facial images of men of different sizes, and the second database is connected to the numerical statistics module.

5. The image recognition system based on big data according to claim 4, characterized in that: The first database and the second database are both provided with a plurality of folders so as to classify and store facial images of different sizes.

6. The image recognition system based on big data according to claim 5, characterized in that: The second judgment module includes: A second analysis module is used to analyze the image recognized by the recognition module to analyze the position of the recognized image in the input module, and the second analysis module is connected to the conversion module; The second comparison module is used to compare the image recognized by the recognition module with the image stored in the recording module to compare whether there is a similarity in the recording module. The second comparison module is connected to the second analysis module.

7. The image recognition system based on big data according to claim 6, characterized in that: The first reminder module includes: A counting module, used for calculating the number of comparison failures of the second comparison module, wherein the counting module is connected to the second comparison module; The alarm module is used to remind personnel when the counting module reaches the set number of times, and the alarm module is connected to the counting module.

8. The image recognition system based on big data according to claim 1, characterized in that: The first judgment module includes: A first storage module is used to store facial images of female criminals in different sizes; The second storage module is used to store facial images of male criminals in different sizes; A first analysis module is used to analyze the image recognized by the recognition module to analyze the position of the recognized image in the first storage module and the second storage module, wherein the first analysis module is connected to the recognition module; The first comparison module is used to compare the image recognized by the recognition module with the images stored in the first storage module and the second storage module to compare whether there is a similarity. The first comparison module is connected to the first analysis module, the first storage module and the second storage module.

9. The image recognition system based on big data according to claim 8, characterized in that: The first storage module and the second storage module are both provided with a plurality of folders so as to classify and store facial images of different sizes.

10. The image recognition system based on big data according to claim 1, characterized in that: The second reminder module includes: The second storage module is used to store the contact information of the on-duty personnel; An acquisition module, used for acquiring data in the second storage module, wherein the acquisition module is connected to the first judgment module and the second storage module; The notification module is used to notify the on-duty personnel according to the data acquired by the acquisition module, and the notification module is connected to the acquisition module.

Images