Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for performing multi-visual-angle face detection by means of integral channel features

A technology of aggregating channel features and face detection, applied in the field of face detection of computer vision, can solve the problems of slow speed and low accuracy of multi-view face detection, and achieve the effect of improving the speed of face detection

Inactive Publication Date: 2017-03-22
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF7 Cites 35 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the deficiencies of the prior art, such as low precision and slow speed of multi-view face detection, and provide a method for multi-view face detection using aggregated channel features. By using the 10 ACF proposed by Piotr Dollar The channel is improved to 8 channels, that is, the three LUV color channels are changed to a single grayscale channel. The improved new ACF feature will greatly improve the face detection speed, and the detection speed is fast and accurate

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
  • Method for performing multi-visual-angle face detection by means of integral channel features
  • Method for performing multi-visual-angle face detection by means of integral channel features
  • Method for performing multi-visual-angle face detection by means of integral channel features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] Such as figure 1 As shown, a method of multi-view face detection using aggregated channel features, the method steps are as follows:

[0035] A. Obtain and detect a face image, and construct an image pyramid on the face image;

[0036] B. Extract the aggregate channel features of each layer from the image pyramid; calculate the real size of the 1st, 9th, and 17th layers, and then estimate the size of other images between them based on these sizes, which will speed up the calculation and quickly form a feature pyramid; details as follows:

[0037] B1, convert the original RGB image of the face image in step A into a grayscale image, which is a color channel feature extraction;

[0038] B2, calculating the gradient magnitude value of each pixel in step B1, which is a gradient magnitude feature extraction;

[0039] B3. Calculate the gradient direction histogram of each pixel in the 6 gradient directions, which is the feature extraction of the 6 direction histograms;

...

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 method for performing multi-visual-angle face detection by means of integral channel features. The method is mainly characterized in that three LUV color channels in ten ACF channels are improved for obtaining a gray scale single channel, thereby forming an eight-channel characteristic and realizing quicker feature extraction; four-stage Adaboost cascaded classifier training is performed on the extracted features, thereby forming a cascaded strong classifier which comprises 4096 weak classifiers; and image detection is performed by means of the cascaded classifier and a quick feature pyramid method for quickly and accurately detecting faces. According to the method of the invention, detecting blocks are acquired by means of successive sliding of a sliding window on a characteristic pyramid according to a step length; the detecting blocks are classified by means of the trained Adaboost classifier; overlapped window elimination is performed on the detecting blocks which comprise the faces through a non-maximum suppression method; a final face detection window is kept and detection precision is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision face detection, in particular to a method for multi-view face detection by using aggregation channel features. Background technique [0002] Human face is a common and complex visual pattern, and the reflected visual information plays an important role and significance in the communication and interaction between people. Face detection is the key first step in the face recognition system, and it is also a hot spot in the field of computer vision and pattern recognition research. In recent years, with the development of technologies such as computer vision, pattern recognition and artificial intelligence, as well as the urgent needs of intelligent transportation, intelligent monitoring and security fields, pedestrian detection technology has received more and more attention, but it is difficult to detect occluded and overlapping pedestrians. , so face detection is needed to replace pedestr...

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): G06K9/00G06K9/46G06K9/62
CPCG06V40/161G06V40/172G06V40/168G06V10/50G06V10/56G06F18/2451
Inventor 刁海峰魏永涛
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products