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

Rapid face comparison method

A fast and comparison technology, applied in the field of face recognition, can solve problems such as time consumption extension, achieve the effect of speeding up the operation process and improving the speed of face comparison

Pending Publication Date: 2020-04-28
SINOCLOUD WISDOM BEIJING TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, in the face features obtained based on the neural network model, the face comparison method is to use a face feature to compare the cosine similarity with the database feature. When comparing multiple pictures of a single person, time consumption will be prolonged.

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
  • Rapid face comparison method
  • Rapid face comparison method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0026] Such as figure 1 As shown, a fast face comparison method includes the following steps:

[0027] S1: Obtain a face picture. The camera can be called through opencv to capture face photos. Face photos can be multiple snapshots of a person in a continuous period of time, or multiple snapshots of different faces in the current picture.

[0028] S2: Obtain the face features of the picture through the neural network model and o...

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 discloses a rapid face comparison method. The method comprises the following steps of S1, obtaining a face picture; S2, acquiring face features of the picture through a neural network model, outputting key features and storing the key features into a first matrix; S3, acquiring key features in the face feature database and storing the key features into a second matrix; S4, performingcosine similarity comparison on the first matrix and the second matrix; and S5, taking the maximum value of each column of the matrix after comparison and the corresponding bit sequence to obtain a comparison value of each face feature of the first matrix, and completing comparison. According to the invention, the face comparison speed can be effectively improved, and the operation process is accelerated. And the method can be expanded to comparison between a single person and a database, and multiple persons can compare with the database at the same time without slowing down the time.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a method for quickly comparing faces. Background technique [0002] Face recognition refers to the process of encoding the facial features of the detected face area in the input image or video, and then performing identity recognition based on the facial features of the face. The main process is divided into three steps: face detection and alignment, face feature encoding, and face recognition. As an effective way of non-contact recognition, face recognition is safe, intelligent and convenient. As the main means of identification, it has been widely used in transportation, public safety, finance and many other fields. [0003] At present, among the face features obtained based on the neural network model, the face comparison method is to use a face feature to compare the cosine similarity with the database feature. When comparing multiple images of a single person, time consumpt...

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
CPCG06V40/166G06V40/168
Inventor 安泽民
Owner SINOCLOUD WISDOM BEIJING TECH