Image feature extraction method and device

A technology of image feature extraction and image feature, applied in the direction of acquisition/recognition of facial features, instruments, characters and pattern recognition, etc. The effect of adaptability and good recognition effect

Active Publication Date: 2018-12-07
CAPITAL NORMAL UNIVERSITY
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In short, the above two processing methods have great limitations in processing color facial expression images, and the image features of the extracted facial expression images cannot effectively represent the features of the expression in the image, and then the image features Can not achieve better recognition effect when used for facial expression recognition

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
  • Image feature extraction method and device
  • Image feature extraction method and device
  • Image feature extraction method and device

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0058] figure 2 A flow chart of an image feature extraction method provided by an embodiment of the present invention is shown. refer to figure 2 , image feature extraction methods include:

[0059] Step S10: The processor 106 represents the first facial expression image as a quaternion matrix.

[0060] The expression image of the first face image may be a common RGB image, including a red channel image, a green channel image, and a blue channel image. Now formula (1) can be adopted to represent the first facial expression image:

[0061] f q (x,y)=if R (x,y)+jf G (x,y)+kf B (x,y) (1)

[0062] Among them, f q (x, y) is the quaternion matrix corresponding to the first face image, f R (x,y) is the red channel image, f G (x,y) is the green channel image, f B (x,y) is the blue channel image. In this representation method, the quaternion matrix corresponding to the first face image is a pure quaternion matrix, which does not have a corresponding real part matrix, and...

no. 2 example

[0099] Figure 4 A functional block diagram of the image feature extraction device 200 provided by the second embodiment of the present invention is shown. refer to Figure 4 , the device includes: an image representation module 210 , a phase and magnitude calculation module 220 , a phase and magnitude encoding module 230 and a feature synthesis module 240 .

[0100]Wherein, the image representation module 210 is used to represent the first facial expression image as a quaternion matrix; the phase and amplitude calculation module 220 is used to calculate and obtain three phase matrices and the amplitude matrix of the quaternion matrix; And the amplitude encoding module 230 is used for carrying out partial encoding to described three phase matrices respectively to obtain three encoded phase matrices, and carries out local encoding to described amplitude matrix to obtain encoded amplitude matrix; Feature synthesis module 240 is used for respectively Perform statistics on eleme...

no. 3 example

[0103] The third embodiment of the present invention provides a computer storage medium, and computer program instructions are stored in the computer storage medium. When the computer program instructions are read and executed by the processor of the computer, the image feature extraction method provided by the embodiment of the present invention is executed. The computer storage medium can be implemented as, but not limited to figure 1 Memory 102 is shown.

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 relates to provides an image feature extraction method and device, and relates to the technical field of expression identification. The method comprises that a first face expression image is represented into a quaternion matrix; three phase matrixes and an amplitude matrix of the quaternion matrix are obtained; the three phase matrixes are coded partially to obtain three coded phasematrixes respectively, and the amplitude matrix is coded partially to obtain a coded amplitude matrix; and element values of each of the three coded phase matrixes and the coded amplitude matrix are counted to obtain an image feature of the first face expression image. According to the method, color information, grayscale information and internal connection therebetween included by the face expression image are taken into full consideration when the image feature is extracted, the extracted image feature can represent the expression feature in the image effectively, and a better identificationeffect can be achieved when the image feature is used for expression identification.

Description

technical field [0001] The present invention relates to the technical field of computer networks, in particular to an image feature extraction method and device. Background technique [0002] In interpersonal communication, facial expressions convey very important information. In order to enable computers to acquire emotional perception and understanding capabilities, expression recognition has become a research hotspot in recent years and has been applied in the fields of human-computer interaction, mobile Internet and health management. [0003] In the prior art, the images processed by the facial expression recognition method are usually grayscale images. For color facial expression images, one processing method is to convert them into grayscale images for processing, which will cause the color information of the images to be lost. Another processing method is to process each color channel separately, but this processing method fails to fully consider the internal relat...

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
CPCG06V40/175G06V40/168
Inventor 邵珠宏薛志毅尚媛园赵晓旭
Owner CAPITAL NORMAL UNIVERSITY
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