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

Face retrieval method based on rapid supervised discrete hashing

A hashing and fast technology, applied in the field of face retrieval based on fast supervised discrete hashing, can solve problems such as not very applicable and high time complexity, and achieve the effect of improving computational efficiency

Active Publication Date: 2016-08-17
天津中科智能识别有限公司
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, "supervised discrete hashing" has high time complexity and is not very suitable for processing large-scale face data.

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 rapid supervised discrete hashing
  • Face retrieval method based on rapid supervised discrete hashing
  • Face retrieval method based on rapid supervised discrete hashing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to make the purpose, technical solutions and advantages of the present invention clearer, the substantive features and advantages of the present invention will be further described below in conjunction with examples, but the present invention is not limited to the listed examples.

[0034] see figure 1 As shown, a face retrieval method based on fast supervised discrete hashing, including the following steps:

[0035] Step S1, the training samples are expressed as where n is the number of training samples, d is the dimension of the training samples, x i Represents the i-th training sample; R is a set of real numbers;

[0036] The test sample is expressed as where m is the number of test samples, t j represents the jth test sample;

[0037] Normalize the training sample and the test sample, and then map the Gaussian nonlinear kernel to the kernel space to obtain the kernelized expression matrix φ(X) of the training sample and the kernelized expression matr...

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 rapid supervised discrete hashing. The method includes the steps of mapping each sample to a nuclear space through a Gaussian kernel to obtain a projection matrix of a nucleated sample, mapping a classification marker of each training sample to a corresponding hash code to obtain a corresponding projection matrix through the least square method, and directly obtaining the hash codes through an analysis method. By means of the method, the precision and speed in a face retrieval application is improved, high precision is ensured, calculation complexity is greatly reduced compared with an existing hash method, and the method is more suitable for processing large-scale data. The method has higher universality and can be used for protection and supervision of information security, public security and financial security.

Description

technical field [0001] The invention relates to the technical fields of machine learning, pattern recognition and digital image processing, and in particular to a face retrieval method based on fast supervised discrete hashing. Background technique [0002] Face retrieval and recognition is a non-contact and non-invasive recognition method accepted by people. It is a very hot research problem in the fields of computer vision, pattern recognition and image processing, and has attracted extensive attention from researchers. The purpose of face retrieval technology is to input an image into the computer and let the computer output many images similar to it. As a scientific problem, face retrieval is a typical computer problem of image understanding and pattern classification. It involves many disciplines such as machine learning, pattern recognition, operations research, digital image processing, and computer vision. As one of the key technologies of biometric identification,...

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): G06K9/00G06K9/62G06F17/30
CPCG06F16/583G06V40/16G06F18/214
Inventor 孙哲南桂杰孙运莲
Owner 天津中科智能识别有限公司