CN110610113A - AI chip-based high-density dynamic face recognition device and method - Google Patents
AI chip-based high-density dynamic face recognition device and method Download PDFInfo
- Publication number
- CN110610113A CN110610113A CN201810611887.6A CN201810611887A CN110610113A CN 110610113 A CN110610113 A CN 110610113A CN 201810611887 A CN201810611887 A CN 201810611887A CN 110610113 A CN110610113 A CN 110610113A
- Authority
- CN
- China
- Prior art keywords
- image
- color
- features
- gray level
- module
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a high-density dynamic face recognition device based on an AI chip, which comprises an acquisition module, a face recognition module and a face recognition module, wherein the acquisition module is used for acquiring images containing face characteristics; the preprocessing module is used for preprocessing the image and removing background noise; the color image characteristic extraction module is used for extracting color characteristics in the image; the gray level image feature extraction module is used for converting the color image into a gray level image and extracting the gray level features in the image; the characteristic synthesis module is used for synthesizing the color characteristic and the gray characteristic; and the recognition module is used for carrying out face recognition according to the synthesized features. The invention can improve the defects of the prior art and improves the realization of high-density dynamic recognition of the face information.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a high-density dynamic face recognition device and method based on an AI chip.
Background
In recent years, face recognition technology is rapidly developed and widely applied to multiple fields such as security verification and data analysis. However, the existing face recognition technology has a slow recognition speed, and cannot realize accurate high-density dynamic recognition.
Disclosure of Invention
The invention aims to provide a high-density dynamic face recognition device and method based on an AI chip, which can solve the defects of the prior art and improve the high-density dynamic recognition of face information.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows.
A high-density dynamic face recognition device based on AI chip includes:
the acquisition module is used for acquiring an image containing human face features;
the preprocessing module is used for preprocessing the image and removing background noise;
the color image characteristic extraction module is used for extracting color characteristics in the image;
the gray level image feature extraction module is used for converting the color image into a gray level image and extracting the gray level features in the image;
the characteristic synthesis module is used for synthesizing the color characteristic and the gray characteristic;
and the recognition module is used for carrying out face recognition according to the synthesized features.
The identification method of the high-density dynamic face identification device based on the AI chip comprises the following steps:
A. the acquisition module acquires an image containing human face features;
B. the preprocessing module preprocesses the image to remove background noise;
C. sending the preprocessed image to a color image feature extraction module to extract color features in the image;
D. the preprocessed image is sent to a gray level image feature extraction module, the color image is converted into a gray level image, and gray level features in the image are extracted;
E. the characteristic synthesis module synthesizes the color characteristic and the gray characteristic;
F. and the recognition module carries out face recognition according to the synthesized features.
Preferably, in step C, extracting color features in the image comprises the steps of,
c1, establishing a feature matrix of the color image, and extracting a feature vector of the color image;
c2, carrying out iterative processing on the color image by using the feature vector until the difference value of the feature value corresponding to the feature vector of the color image after iterative processing is smaller than a set threshold value;
and C3, layering the color image according to the RGB values of the color image, traversing each layer of the color image, and taking the linearly related features as color features.
Preferably, in step D, extracting the grayscale feature in the image includes the steps of,
d1, comparing the gray level image with the face contour stored in the database, and extracting the face contour in the gray level image;
d2, blurring the face contour in the gray level image;
d3, establishing a similarity matrix of the face contour in the gray level image after fuzzification and the face contour stored in the database, and taking the face contour in the gray level image corresponding to the similarity matrix with linear correlation as a gray level feature.
Preferably, the step F of combining the color feature and the gray feature includes the steps of,
f1, establishing a two-dimensional coordinate system for the original image;
f2, synthesizing the color features and the gray features according to the coordinates;
and F3, performing synchronous blurring processing on the synthesized color features according to the blurring processing of the gray images at the same positions.
Preferably, in step E, a mapping relationship between the gray scale features and the color features is established; traversing the image, and if the mapping relation meets the judgment condition prestored in the database, establishing an identification point; and if the number and the density of the identification points exceed the set threshold, the identification points are considered to be matched with the face information prestored in the database.
Adopt the beneficial effect that above-mentioned technical scheme brought to lie in: the invention carries out combined recognition by utilizing the color characteristics and the gray characteristics of the image, has high recognition speed and high accuracy and is suitable for high-density dynamic face recognition occasions.
Drawings
FIG. 1 is a block diagram of one embodiment of the present invention.
Detailed Description
The standard parts used in the invention can be purchased from the market, the special-shaped parts can be customized according to the description and the description of the attached drawings, and the specific connection mode of each part adopts the conventional means of mature bolts, rivets, welding, sticking and the like in the prior art, and the detailed description is not repeated.
Referring to FIG. 1, one embodiment of the present invention includes
The system comprises an acquisition module 1, a display module and a processing module, wherein the acquisition module is used for acquiring images containing human face characteristics;
the preprocessing module 2 is used for preprocessing the image and removing background noise;
the color image characteristic extraction module 3 is used for extracting color characteristics in the image;
the gray level image feature extraction module 4 is used for converting the color image into a gray level image and extracting the gray level features in the image;
the characteristic synthesis module 5 is used for synthesizing the color characteristic and the gray characteristic;
and the recognition module 6 is used for carrying out face recognition according to the synthesized features.
The identification method of the high-density dynamic face identification device based on the AI chip comprises the following steps:
A. the acquisition module 1 acquires an image containing human face features;
B. the preprocessing module 2 preprocesses the image to remove background noise;
C. the preprocessed image is sent to a color image feature extraction module 3, and color features in the image are extracted;
D. the preprocessed image is sent to a gray level image feature extraction module 4, the color image is converted into a gray level image, and the gray level feature in the image is extracted;
E. the characteristic synthesis module 5 synthesizes the color characteristic and the gray characteristic;
F. the recognition module 6 performs face recognition according to the synthesized features.
In step C, extracting color features in the image comprises the following steps,
c1, establishing a feature matrix of the color image, and extracting a feature vector of the color image;
c2, carrying out iterative processing on the color image by using the feature vector until the difference value of the feature value corresponding to the feature vector of the color image after iterative processing is smaller than a set threshold value;
and C3, layering the color image according to the RGB values of the color image, traversing each layer of the color image, and taking the linearly related features as color features.
In step D, extracting the gray scale features in the image comprises the following steps,
d1, comparing the gray level image with the face contour stored in the database, and extracting the face contour in the gray level image;
d2, blurring the face contour in the gray level image;
d3, establishing a similarity matrix of the face contour in the gray level image after fuzzification and the face contour stored in the database, and taking the face contour in the gray level image corresponding to the similarity matrix with linear correlation as a gray level feature.
In step F, the synthesis of the color feature and the gray feature comprises the following steps,
f1, establishing a two-dimensional coordinate system for the original image;
f2, synthesizing the color features and the gray features according to the coordinates;
and F3, performing synchronous blurring processing on the synthesized color features according to the blurring processing of the gray images at the same positions.
In the step E, establishing a mapping relation between the gray characteristic and the color characteristic; traversing the image, and if the mapping relation meets the judgment condition prestored in the database, establishing an identification point; and if the number and the density of the identification points exceed the set threshold, the identification points are considered to be matched with the face information prestored in the database.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, are merely for convenience of description of the present invention, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (6)
1. A high-density dynamic face recognition device based on AI chip is characterized by comprising:
the system comprises an acquisition module (1) for acquiring an image containing human face features;
the preprocessing module (2) is used for preprocessing the image and removing background noise;
the color image characteristic extraction module (3) is used for extracting color characteristics in the image;
the gray level image characteristic extraction module (4) is used for converting the color image into a gray level image and extracting the gray level characteristics in the image;
the characteristic synthesis module (5) is used for synthesizing the color characteristic and the gray characteristic;
and the recognition module (6) is used for carrying out face recognition according to the synthesized features.
2. An AI-chip-based high-density dynamic face recognition method according to claim 1, characterized by comprising the steps of:
A. the acquisition module (1) acquires an image containing human face features;
B. the preprocessing module (2) preprocesses the image to remove background noise;
C. the preprocessed image is sent to a color image feature extraction module (3) to extract color features in the image;
D. the preprocessed image is sent to a gray level image feature extraction module (4), the color image is converted into a gray level image, and gray level features in the image are extracted;
E. the characteristic synthesis module (5) synthesizes the color characteristic and the gray characteristic;
F. and the recognition module (6) performs face recognition according to the synthesized features.
3. The AI chip-based high-density dynamic face recognition device recognition method of claim 2, wherein: in step C, extracting color features in the image comprises the following steps,
c1, establishing a feature matrix of the color image, and extracting a feature vector of the color image;
c2, carrying out iterative processing on the color image by using the feature vector until the difference value of the feature value corresponding to the feature vector of the color image after iterative processing is smaller than a set threshold value;
and C3, layering the color image according to the RGB values of the color image, traversing each layer of the color image, and taking the linearly related features as color features.
4. The AI chip-based high-density dynamic face recognition device recognition method of claim 2, wherein: in step D, extracting the gray scale features in the image comprises the following steps,
d1, comparing the gray level image with the face contour stored in the database, and extracting the face contour in the gray level image;
d2, blurring the face contour in the gray level image;
d3, establishing a similarity matrix of the face contour in the gray level image after fuzzification and the face contour stored in the database, and taking the face contour in the gray level image corresponding to the similarity matrix with linear correlation as a gray level feature.
5. The AI chip-based high-density dynamic face recognition device recognition method of claim 4, wherein: in step F, the synthesis of the color feature and the gray feature comprises the following steps,
f1, establishing a two-dimensional coordinate system for the original image;
f2, synthesizing the color features and the gray features according to the coordinates;
and F3, performing synchronous blurring processing on the synthesized color features according to the blurring processing of the gray images at the same positions.
6. The AI chip-based high-density dynamic face recognition device recognition method of claim 5, wherein: in the step E, establishing a mapping relation between the gray characteristic and the color characteristic; traversing the image, and if the mapping relation meets the judgment condition prestored in the database, establishing an identification point; and if the number and the density of the identification points exceed the set threshold, the identification points are considered to be matched with the face information prestored in the database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810611887.6A CN110610113A (en) | 2018-06-14 | 2018-06-14 | AI chip-based high-density dynamic face recognition device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810611887.6A CN110610113A (en) | 2018-06-14 | 2018-06-14 | AI chip-based high-density dynamic face recognition device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110610113A true CN110610113A (en) | 2019-12-24 |
Family
ID=68887520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810611887.6A Pending CN110610113A (en) | 2018-06-14 | 2018-06-14 | AI chip-based high-density dynamic face recognition device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110610113A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120301020A1 (en) * | 2011-05-23 | 2012-11-29 | Infosys Limited | Method for pre-processing an image in facial recognition system |
| CN103246877A (en) * | 2013-05-13 | 2013-08-14 | 北京工业大学 | Image contour based novel human face recognition method |
| CN103593598A (en) * | 2013-11-25 | 2014-02-19 | 上海骏聿数码科技有限公司 | User online authentication method and system based on living body detection and face recognition |
| CN103839042A (en) * | 2012-11-27 | 2014-06-04 | 腾讯科技（深圳）有限公司 | Human face recognition method and human face recognition system |
| CN106384086A (en) * | 2016-08-31 | 2017-02-08 | 广州市贺氏办公设备有限公司 | Dual-camera face identification method and system |
-
2018
- 2018-06-14 CN CN201810611887.6A patent/CN110610113A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120301020A1 (en) * | 2011-05-23 | 2012-11-29 | Infosys Limited | Method for pre-processing an image in facial recognition system |
| CN103839042A (en) * | 2012-11-27 | 2014-06-04 | 腾讯科技（深圳）有限公司 | Human face recognition method and human face recognition system |
| CN103246877A (en) * | 2013-05-13 | 2013-08-14 | 北京工业大学 | Image contour based novel human face recognition method |
| CN103593598A (en) * | 2013-11-25 | 2014-02-19 | 上海骏聿数码科技有限公司 | User online authentication method and system based on living body detection and face recognition |
| CN106384086A (en) * | 2016-08-31 | 2017-02-08 | 广州市贺氏办公设备有限公司 | Dual-camera face identification method and system |
Non-Patent Citations (1)
| Title |
|---|
| 唐辉: "基于典型相关分析的人脸识别方法研究", 《万方数据知识服务平台》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084156B (en) | Gait feature extraction method and pedestrian identity recognition method based on gait features | |
| CN107316031A (en) | The image characteristic extracting method recognized again for pedestrian | |
| CN102663411B (en) | Recognition method for target human body | |
| CN113408584B (en) | RGB-D multi-modal feature fusion 3D target detection method | |
| CN110335233B (en) | Highway guardrail plate defect detection system and method based on image processing technology | |
| CN104408780A (en) | Face recognition attendance system | |
| CN111126240A (en) | Three-channel feature fusion face recognition method | |
| CN110991258B (en) | Face fusion feature extraction method and system | |
| CN106327534A (en) | Tire inner wall texture identification method based on locating block | |
| CN109784216B (en) | Vehicle-mounted thermal imaging pedestrian detection Rois extraction method based on probability map | |
| CN110991398A (en) | Gait recognition method and system based on improved gait energy map | |
| EP3852007A3 (en) | Method, apparatus, electronic device, readable storage medium and program for classifying video | |
| CN114842524B (en) | Face false distinguishing method based on irregular significant pixel cluster | |
| CN112836651A (en) | Gesture image feature extraction method based on dynamic fusion mechanism | |
| CN107729863B (en) | Human finger vein recognition method | |
| Zhao et al. | A robust color-independent text detection method from complex videos | |
| CN113780207A (en) | System and method for goat face recognition | |
| CN110490210B (en) | Color texture classification method based on t sampling difference between compact channels | |
| CN111931689B (en) | Method for extracting video satellite data identification features on line | |
| CN110610113A (en) | AI chip-based high-density dynamic face recognition device and method | |
| CN110222599B (en) | Gait recognition method based on Gaussian mapping | |
| Saranya et al. | An approach towards ear feature extraction for human identification | |
| CN113392852A (en) | Vehicle detection method and system based on deep learning | |
| Venkateswara et al. | Multiresolution Match Kernels for gesture video classification | |
| CN111723612A (en) | Face recognition and face recognition network training method and device, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191224 |