A method and system for face recognition
A face recognition system and face recognition technology, applied in the field of security, can solve the problems of high equipment requirements, low comparison angle, poor comparison effect, etc., and achieve the effect of improving comparison efficiency
Inactive Publication Date: 2018-12-21
中山市昭歌云视频安防科技有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] In the field of security, with the advent of the era of all-round and multi-level monitoring, more and more security monitoring equipment has been produced. Most of the security monitoring equipment collects face information through cameras for face recognition. At present, face recognition on the market The method has the following defects: 1) After the portrait capture camera is used to capture the image, the image is uploaded to the server and then compared with the software, which requires very high requirements for the front-end equipment; 2) The current comparison angle in the industry is low, requiring personnel to face it directly Facing the surveillance camera; 3) The current comparison effect in the industry is poor; 4) The current comparison speed in the industry is relatively slow
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:
[0033] Such as figure 1 As shown, a face recognition method includes the following steps:
[0034] Step 1), extracting feature metrics for recognition 1, first determine some salient feature points according to the side profile curve, and derive a set of feature metrics for recognition from these salient feature points. The characteristic measure may be distance or angle.
[0035] Step 2), determine the geometric characteristics of the organ 2, design an organ model with adjustable parameters, the organ model with adjustable parameters is the deformable template, define an energy function, and minimize the energy function by adjusting the model parameters, at this time The model parameters serve as the geometric features of the organ. But it is non-localized, the support of its kernel function extends in the entire coordinate space, and it is no...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present application discloses a face recognition method and system, wherein, the method comprises five steps of extracting feature metrics for recognition, determining the geometric characteristics of an organ, establishing a dynamic link model (DLA), comparative analysis, and face recognition. The invention can realize face recognition comparison in a faster, more efficient and cheaper manner, and provides convenience for later scene application. Based on back-end software recognition, there is no requirement for the front-end camera. The system performs uploading through the video streamto the server, captures the facial feature information through the video stream, and then compares with the database. The angle of comparison is 70%, and the camera does not need to face the camera.The algorithm is based on depth learning algorithm, which can be completed in one second in the database of 50,000 people, and greatly improves the comparative efficiency.
Description
technical field [0001] The invention relates to the security field, in particular to a face recognition method and system. Background technique [0002] In the field of security, with the advent of the era of all-round and multi-level monitoring, more and more security monitoring equipment has been produced. Most of the security monitoring equipment collects face information through cameras for face recognition. At present, face recognition on the market The method has the following defects: 1) After the portrait capture camera is used to capture the image, the image is uploaded to the server and then compared with the software, which requires very high requirements for the front-end equipment; 2) The current comparison angle in the industry is low, requiring personnel to face it directly Facing the surveillance camera; 3) The current comparison effect in the industry is poor; 4) The current comparison speed in the industry is relatively slow. Contents of the invention ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06T17/20
CPCG06T17/20G06V20/653G06V40/168
Inventor 陆俞江陆新献
Owner 中山市昭歌云视频安防科技有限公司