Face detection training method, detection method and apparatus thereof

A training method and face detection technology, applied in the communication field, can solve the problem that the face detection scheme is difficult to take into account the detection speed and detection effect, so as to reduce the complexity and calculation amount, and improve the detection efficiency

Inactive Publication Date: 2017-06-20
SPREADTRUM COMM (TIANJIN) INC
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] However, the above face detection schemes are d...

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 training method, detection method and apparatus thereof
  • Face detection training method, detection method and apparatus thereof
  • Face detection training method, detection method and apparatus thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0133] Currently, face detectors based on SVM and HOG features do not have a processing mechanism for deformation and multi-view. Therefore, the processing of deformed or side-view face targets is its drawback. In addition, the complexity of HOG features is relatively high, resulting in a low detection speed of the entire face, which is difficult to apply to low-power embedded devices.

[0134] The face detector based on DPM and HOG features is suitable for deformed and multi-view targets, but also due to the high complexity of HOG features, the overall face detection speed is low, which is difficult to apply to low-power embedded equipment.

[0135] The target detector based on CNN and Softmax classifiers, although the detection results on the existing standard data sets (such as: Visual Object Classes Challenge, ImageNet) are better than other methods, the operation of this scheme is similar to "black box". The detection of specific targets and adjustment of parameters also requ...

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

A face detection training method, a detection method and an apparatus thereof are disclosed. A face detector comprises a first classifier and a second classifier. The training method comprises the following steps of collecting face and non-face images as training sample sets; extracting a brightness comparison characteristic of each training sample in the training sample sets; according to the brightness comparison characteristic, acquiring a corresponding fern characteristic; using the fern characteristic and a Bayes theorem to carry out training and acquiring the first classifier; using the brightness comparison characteristic and a minimized weight mean square error criterion to carry out P-round training, and acquiring P decision tree classifiers, wherein the P is greater than or equal to 1 and the P is an integer; and cascading the P decision tree classifiers so as to form the second classifier. The face detector acquired through applying the training method is used to carry out face detection so that complexity and a calculated amount of face detection can be reduced and detection efficiency can be increased.

Description

Technical field [0001] The present invention relates to the field of communication technology, in particular to a training method, detection method and device for face detection. Background technique [0002] Face detection is a technology involving computer vision and machine learning. The main purpose is to detect target instances of human faces in images and videos. It can be applied to face recognition, human-computer interaction and other technical fields. [0003] At present, there are many face detection methods, which are distinguished according to models. The mainstream solutions are as follows: [0004] 1) Support Vector Machine (SVM), which is mainly used in the field of pedestrian detection together with Histogram of Oriented Gradient (HOG) features. This scheme calculates dense gradient direction features, and uses simple linear SVM to classify high-dimensional HOG descriptors to achieve good detection results. [0005] 2) Deformable Part-based Model (DPM), which is main...

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): G06K9/00
CPCG06V40/172
Inventor 刘阳陈敏杰潘博阳郭春磊林福辉
Owner SPREADTRUM COMM (TIANJIN) INC
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