Unlock instant, AI-driven research and patent intelligence for your innovation.

Face feature compression method and device

A face feature and compression method technology, applied in the field of computer vision, can solve the problems of inapplicability and high cost of security tasks, achieve the effect of enhancing classification effect, reducing storage space, improving accuracy and reliability

Active Publication Date: 2019-07-05
SHANGHAI SENSETIME INTELLIGENT TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional security tasks based on face recognition technology are often built on large-scale distributed servers or large-scale cloud service platforms, and large-scale deployment often leads to higher costs
Therefore, traditional security tasks based on face recognition technology are not applicable in some small-scale, low-cost application scenarios

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face feature compression method and device
  • Face feature compression method and device
  • Face feature compression method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0084] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.

[0085] In order to make it easier for those skilled in the art to understand the technical solutions provided by the embodiments of the present disclosure, the technical environment in which the technical solutions are implemented is firstly described below.

[0086] The face recognition technology based on edge nodes can enable terminals with weak computing power to realize the functi...

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

No PUM Login to View More

Abstract

The invention relates to a face feature compression method and device. The method comprises the steps of obtaining face features of a face image to be identified; and inputting the face features intoa feature compression network, and outputting compressed face features of the face features through the feature compression network, the feature compression network being obtained by training a corresponding relation between a plurality of historical face features and the compressed face features of the historical face features. According to the technical scheme provided by the embodiment of the invention, the face recognition function can be realized in the edge nodes with relatively weak computing power, and the face features are compressed, so that the storage space of the preset face set can be reduced, the calculation efficiency of feature matching can be improved, and the face recognition efficiency can be improved.

Description

technical field [0001] The present disclosure relates to the technical field of computer vision, in particular to a face feature compression method and device. Background technique [0002] Since the face has the characteristics of good structural features and high recognition, face recognition technology has become one of the more mature application technologies in the field of security monitoring. Traditional security tasks based on face recognition technology are often built on large-scale distributed servers or large-scale cloud service platforms, and large-scale deployment often leads to higher costs. Therefore, traditional security tasks based on face recognition technology are not applicable in some small-scale, low-cost application scenarios. [0003] Therefore, there is an urgent need in the related art for a face recognition method that can be implemented in a small-scale and low-cost scenario. Contents of the invention [0004] In order to overcome the problem...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/169G06V40/172
Inventor 徐晓阳吴佳飞
Owner SHANGHAI SENSETIME INTELLIGENT TECH CO LTD