Face detection method based on HOG characteristics

A face detection and feature vector technology, applied in the field of face detection, can solve the problem that the robustness needs to be improved, and achieve the effect of strong robustness

Active Publication Date: 2013-12-11
HOPE CLEAN ENERGY (GRP) CO LTD
View PDF2 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] After decades of research, researchers have proposed a large number of face detection algorithms, but the robustness to illumination, expression, environmental changes, etc. needs to be improved, and the contradiction between detection speed and accuracy needs to be improved.

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 detection method based on HOG characteristics
  • Face detection method based on HOG characteristics
  • Face detection method based on HOG characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] Face detection method, including the following steps, such as image 3 Shown:

[0046] Step 1. Carry out light preprocessing to the image;

[0047] Step 2. Calculate the image HOG integral map;

[0048] Step 3. Detect the current window: According to the current window position, first extract the local HOG features in the window, input the local HOG features into the local classifiers, combine the local classification results into feature vectors, and finally input the feature vectors into the final classifier to obtain The detection result of the current window;

[0049] Step 4. If it is not the last window, move the window and return to step 3. If it is the last window, change the detection scale and judge whether it exceeds the maximum window scale. If not, return to step 3. If yes, the detection ends.

[0050] Image preprocessing is used to deal with images with too dark light and too strong light, and specifically includes the following steps:

[0051] (1) Imag...

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 provides a face detection method based on the HOG characteristics. The face detection method comprises the steps of firstly, training a large number of partial SVM classifiers based on the HOG characteristics, then selecting some partial SVM classifiers which have the good classification effect from the partial SVM classifiers, combining classification results of the selected partial SVM classifiers to a training sample into new characteristic vectors, and finally using SVMs to train the vectors to obtain the final classifier. According to the face detection method based on the HOG characteristics, the HOG partial characteristics are used for being combined with the partial classifiers, and the good robustness is achieved on the conditions such as uneven facial expression illumination and uneven partial illumination.

Description

technical field [0001] The invention relates to image processing technology, in particular to face detection technology. technical background [0002] Face recognition collects face images, detects the position of the face in the image, extracts the face image and compares it with the features in the database to obtain the recognition result. [0003] In the face recognition system, there are two main problems to be solved: (1) face detection; (2) face feature extraction. Face detection is the core technology of the system. Through a suitable algorithm, the position of the face in the picture can be accurately and quickly found out from the image and the size of the face can be obtained. After the face detection, the face features are extracted through the feature extraction algorithm, and then compared with the feature library to obtain the identity of the face. The result obtained by face detection is the material basis of the face recognition stage, so the accuracy of 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): G06K9/00G06K9/62
Inventor 解梅慕春雷陈路蔡家柱
Owner HOPE CLEAN ENERGY (GRP) 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

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