Face retrieval method based on multitask convolution nerve network

A convolutional neural network, multi-task technology, applied in the field of face retrieval based on multi-task convolutional neural network, can solve the problem that cannot meet the fast and accurate recognition requirements of face recognition, and the work efficiency and work quality of face recognition are low. , reduce the use experience and other problems, achieve the effect of significant production practical significance, improve product use experience, and save time

Active Publication Date: 2017-06-09
天津中科智能识别有限公司
View PDF12 Cites 140 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, with the advent of the era of big data, the scale of data that people need to process is often very large
As the capacity of the database increases, the possibility of similar faces appearing in the database will increase accordingly. When face recognition is performed based on the existing face recognit

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 retrieval method based on multitask convolution nerve network
  • Face retrieval method based on multitask convolution nerve network
  • Face retrieval method based on multitask convolution nerve network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0051] figure 1 A flow chart of a face retrieval method based on multi-task convolutional neural network provided by the present invention;

[0052] See figure 1 , A face retrieval method based on multi-task convolutional neural network provided by the present invention includes the following steps:

[0053] The first step: For any face image (including face image and video) that needs face recognition, detect the face position in it, and detect the key to the face image according to the obtained face position Point location

[0054] In the present invention, in the first step, it should be noted that the existing face detection algorithm can be applied to detect the position of the face in the face image, and according to the face position obtained...

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 face retrieval method based on a multitask convolution nerve network; the method comprises the following steps: detecting a random face image so as to obtain face position and key point positions; preprocessing the face image; pre-building the multitask convolution nerve network, and training the same; inputting the preprocessed face image into the trained multitask convolution nerve network; pre-building a face feature database; calculating identity feature similarity for the face image and the face feature database, thus obtaining a candidate face image list; calculating a plurality of attribute feature expression vector similarities between the face image and the candidate face images; carrying out normalization and fusing; ranking the images according to the fuse similarity scores, thus obtaining a retrieval result. The method can realize face image high quality identification, thus fast and effectively determining user IDs corresponding to mass face images, and satisfying people demands on the face identification function.

Description

Technical field [0001] The invention relates to the technical fields of artificial intelligence, pattern recognition and digital image processing, and particularly relates to a face retrieval method based on a multi-task convolutional neural network. Background technique [0002] At present, with the continuous development of human science and technology, face recognition technology is becoming more and more popular in people’s daily lives. Whether in artificial intelligence research or public safety applications, face recognition technology has always been a cutting-edge and popular technology, and it has an important role. Status. [0003] As a type of biometric recognition technology, face recognition has good development and application prospects due to its non-contact and convenient collection characteristics. Face recognition technology has played a very important role in many application scenarios, such as airport security check, border inspection and customs clearance. Wi...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/161G06V40/168G06V40/172G06F18/22G06F18/253
Inventor 孙哲南赫然谭铁牛宋凌霄曹冬李琦
Owner 天津中科智能识别有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap