Face retrieval method and apparatus as well as storage medium and device

A face and target face technology, applied in the field of deep learning, can solve problems such as low retrieval accuracy and poor stability of face retrieval methods, and achieve good results, guaranteed accuracy, and excellent stability

Active Publication Date: 2018-06-01
TENCENT TECH (SHENZHEN) CO LTD +1
View PDF6 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a face retrieval method, device, storage medium and equipment, which solves the problem in the related art that the face retrieval method has poor stability and leads to low retrieval accuracy

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 and apparatus as well as storage medium and device
  • Face retrieval method and apparatus as well as storage medium and device
  • Face retrieval method and apparatus as well as storage medium and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to make the object, technical solution and advantages of the present invention clearer, the implementation manner of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0039] Before explaining the embodiments of the present invention in detail, some terms involved in the embodiments of the present invention will be explained first.

[0040] Deep Learning: This concept originated from the study of artificial neural networks. For example, a multi-layer perceptron with multiple hidden layers is a deep learning structure. Among them, deep learning forms more abstract high-level features by combining low-level features to explore the distributed feature representation of data.

[0041] To put it another way, deep learning is a method based on representational learning from data. There are many ways to represent an observation (such as an image). For example, it can be represented by a vector of the int...

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 and apparatus as well as a storage medium and device, which belongs to the technical field of deep learning. The method comprises the following steps: acquiring a target face image to be retrieved; extracting features of the target face image according to each residual block connected successively in a deep residual network to obtain target face feature information, wherein any one residual block comprises an identity mapping and at least two convolution layers, and the identity mapping of any one residual block points, from an input end of anyone residual block, to an output end of any one residual block; and performing the face retrieval in a face database according to the target face feature information to obtain a face retrieval result, wherein the face retrieval result at least comprises an identity marker matched with the target face feature information. By adopting the face retrieval method and apparatus, the face retrieval is realized on the basis of the deep residual network, the retrieval accuracy of the deep residual network is not prone to influence by external factors, the face retrieval method is excellent in stability, and the face retrieval accuracy is also ensured.

Description

technical field [0001] The present invention relates to the technical field of deep learning, in particular to a face retrieval method, device, storage medium and equipment. Background technique [0002] Face retrieval is an emerging biometric technology that combines computer image processing knowledge and biostatistics knowledge. It currently has broad application prospects. It is widely used in schools, hospitals, commercial streets, hotels, dining and entertainment venues, office buildings, elevators and other places. [0003] Most of the current face retrieval systems are implemented based on traditional machine learning, such as face retrieval methods based on eigenfaces, iterative algorithms based on the combination of histogram or color and other features, etc. [0004] The retrieval accuracy of face retrieval methods based on traditional machine learning is easily affected by external factors. The poor stability of the retrieval method leads to insufficient retrie...

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): G06F17/30G06K9/00
CPCG06F16/583G06V40/168Y02D10/00
Inventor 王川南陈志博张杰岳文龙
Owner TENCENT TECH (SHENZHEN) CO LTD
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