Human face detecting method based on sequence simplifying support vector

A support vector and face detection technology, applied in the field of image processing, can solve a lot of time and application field limitations, and achieve the effect of reducing complexity and improving identification speed

Inactive Publication Date: 2009-12-23
XIDIAN UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The simplified support vector method proposed by Burges uses the gradient descent algorithm or the conjugate gradient descent algorithm in the process of solving the reduced vector set, resulting in a large amount of time for the process
The proposed fixed-point iterative method to solve the reduction set can only be used for the Gaussian kernel function, which limits the application field of the method

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
  • Human face detecting method based on sequence simplifying support vector
  • Human face detecting method based on sequence simplifying support vector
  • Human face detecting method based on sequence simplifying support vector

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] refer to figure 1 , the present invention includes two parts, a training process and an identification process, wherein the training process includes training sample set acquisition, support vector machine training and reduction vector solution; the identification process includes test sample set acquisition and identification result output. The specific implementation is as follows:

[0028] Step 1: Preprocess the original image.

[0029] Input a set of 20×20 MIT images, including face images and non-face image segments, and stretch each image line into a 1×400 vector to obtain a sample set: {(x i ,y i )|x i ∈ R 400 ,y i ∈{+1,-1}, i=1,...,7087}, where the number of input samples is 7087, the sample dimension is 400, and the i-th sample is identified as y i , so that the +1 class represents the face sample, and the -1 class represents the non-human face; the samples are randomly sorted, and the 10-fold cross-validation method is used for training and identificatio...

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 human face detecting method based on a sequence simplifying support vector, mainly solving the problem that the prior human face detecting method has low identifying rate and low reduced vector collection rate of resolution. The method uses the strategy of replacing the support vector collection by the reduced vector collection to enhance the identifying rate and adopts the sequence simplifying method to solve the reduced vector collection. The method comprises a treatment training image training part and a treatment testing image identifying part, wherein the treatment training image training part carries out pre-treatment of line drawing on the original training images and uses the training samples after line drawing to train and support a vector machine and solve a reduced vector set; the treatment testing image identifying part carries out pre-treatment of line drawing on the images to be tested and uses the reduced vector set to identify the testing samples after line drawing and the result output. The invention can detect the images in real time, have the advantages of low computing complexity and storage space and can be used for human face detection in fields of machine learning and pattern identification and other detection systems with a large quantity of data.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to the detection of human faces, which can be used for the supervision and protection of public security, information security and financial security. Background technique [0002] Biometric identification technology is the use of permanent biological characteristics of people themselves, such as fingerprints, faces, irises, palm prints, etc. to identify people. Fingerprint, palm type, iris and other recognition technologies require the cooperation of the person to be recognized, and cannot be completed without the person being recognized knowing. However, facial recognition can use a camera to capture images at a relatively long distance, and the person involved is not aware of it. It is of great significance in practice to complete the identity confirmation and identification work. It can be seen that face recognition technology is a very important and practical method f...

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
Inventor 张莉陈桂荣宴哲胡志焦李成
Owner XIDIAN UNIV
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