Golden monkey face detection method based on increment self-paced learning and regional color quantification

A technology of color quantification and face detection, which is applied to computer components, character and pattern recognition, instruments, etc., can solve the problems of many suspected areas of the monkey body and the rapid detection of unfavorable facial suspected areas, etc., to reduce the area and number, and accurately Detection effect

Inactive Publication Date: 2017-05-24
NORTHWEST UNIV
View PDF1 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the case of large scenes, the background information occupies a large part of the image information, and the traditional pixel-based color quantization method is no longer applicable. The main reason is that the background contai

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
  • Golden monkey face detection method based on increment self-paced learning and regional color quantification
  • Golden monkey face detection method based on increment self-paced learning and regional color quantification
  • Golden monkey face detection method based on increment self-paced learning and regional color quantification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The face of the snub-nosed monkey has certain similarities with the human face, one of which is that its face also has a certain area of ​​skin, and the skin has the unique color of the golden monkey - light blue, with the increase of age, the depth of blue gradually fades. For this reason, the present invention collects the face skin part of the golden monkey of different age stages, such as figure 2 shown, and its color characteristics are analyzed, image 3 Color-coded strip plots for face regions.

[0060] However, it is difficult to perform face detection only through the color features of the facial skin area. The main reason is that the face of the snub-nosed monkey does not have a large area of ​​skin unlike a human face. In addition to the skin area, the face of the snub-nosed monkey also has more hair areas, resulting in a smaller skin area. Throughout the body of the snub-nosed monkey, there are certain differences in the color of its facial skin and hair...

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 golden monkey face detection method based on increment self-paced learning and regional color quantification. Regional color quantification is used for increasing the difference between a background and monkey body color characteristics so as to more accurately perform segmentation of a monkey body region and reduce the area and the number of the detected suspected monkey body regions. Then face skin suspected region detection is performed in the detected monkey body region. Finally accurate face detection is performed by using increment self-paced learning.

Description

technical field [0001] The invention relates to a golden monkey face detection method based on incremental self-step learning and regional color quantization. Background technique [0002] There have been many research results on facial features in the research of animal individual recognition. These results mostly use face detection and recognition methods to solve the problems existing in the process of animal face detection and recognition. Among them, there are monkeys (mainly for Macaque) facial feature extraction and localization algorithm. However, these methods only use traditional image segmentation methods to simply achieve rough positioning of monkey face regions in images under certain conditions, and do not have high accuracy and versatility. The animal individual recognition methods based on facial features basically apply the existing face detection and recognition methods directly (or slightly improved). In the prior art, there are many problems in directly...

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): G06K9/00G06K9/34G06K9/62
CPCG06V40/162G06V40/171G06V10/267G06F18/24
Inventor 许鹏飞郭松涛陈晓江袁晶何刚陈峰李保国房鼎益
Owner NORTHWEST 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