Facial image feature extraction method based on gray level co-occurrence matrix

A gray-level co-occurrence matrix and facial image technology, applied in the field of image processing, can solve the problems that are difficult to meet the needs of practical applications, it is difficult to obtain small change information in texture frequency and direction, and a large number of calculations, so as to achieve easy identification and classification The effect of improved precision and good visual effect

Pending Publication Date: 2020-02-25
QILU UNIV OF TECH
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The size of the Gabor filter transformation window is fixed, it is difficult to obtain the slight change information of the texture in frequency and direction, and it is difficult to meet the needs of practical applications.
In addition, since the texture feature extraction usually uses a filter bank composed of multiple Gabor filters, and the determination of many parameters is required, and there is no effective and fast algorithm for Gabor filtering, so they all require a large number of calculate

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
  • Facial image feature extraction method based on gray level co-occurrence matrix
  • Facial image feature extraction method based on gray level co-occurrence matrix
  • Facial image feature extraction method based on gray level co-occurrence matrix

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] A facial image feature extraction method based on gray level co-occurrence matrix, facial image features include contrast, homogeneity, correlation and energy, comprising steps as follows:

[0077] (1) Use a camera or other equipment to obtain facial images; the pictures used can be downloaded from public databases such as CACD.

[0078] (2) Perform preprocessing operations on facial images, that is, convert facial images into grayscale images; the acquired grayscale images are as follows: figure 1 shown.

[0079] (3) Process grayscale images to obtain texture features of facial images, including contrast, homogeneity, correlation and energy.

Embodiment 2

[0081] According to a kind of facial image feature extraction method based on gray level co-occurrence matrix described in embodiment 1, its difference is:

[0082] Step (3), processing the grayscale image, obtaining the texture features of the facial image, including contrast, homogeneity, correlation and energy, including:

[0083] A. Mask processing to obtain the region of interest:

[0084] For example, if a 5*5 sliding window is used to traverse a facial image of 250*250 pixels, the outermost pixels cannot be made into a 5*5 sliding window. The function of the mask is to remove the images that cannot be used for window traversal , the region of interest is the remaining region.

[0085] Mask processing refers to the use of selected images, graphics or objects to block the image to be processed (all or part) to control the area or process of image processing. The selected image, figure or object for overlay is called a mask or stencil. In optical image processing, a mas...

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 a facial image feature extraction method based on a gray level co-occurrence matrix, facial image features comprise contrast, homogeneity, correlation and energy, and the method comprises the following steps: (1) acquiring a facial image; (2) performing preprocessing operation on the face image, namely converting the face image into a grayscale image; and (3) processing the grayscale image, and obtaining the textural features of the facial image, including contrast, homogeneity, correlation and energy. According to the method, a gray level co-occurrence matrix method is adopted, feature extraction is carried out on the face texture image through MATLAB simulation experiments, the face features are easier to recognize, and therefore the visual effect better than that of an original image is obtained, and the effect on the aspect of classification precision improvement is remarkable.

Description

technical field [0001] The invention relates to a facial image feature extraction method based on a gray level co-occurrence matrix, which belongs to the technical field of image processing. Background technique [0002] Texture feature is an important visual cue, which is ubiquitous and difficult to describe in images. As a basic attribute of the surface of objects, texture exists widely in nature and is an extremely important feature for describing and identifying objects. The texture features of the image describe the local patterns that recur in the image and their arrangement rules, reflecting some rules of grayscale changes in the macro sense. The image can be regarded as a combination of different texture regions. A measure of the relationship between. Texture features can be used to quantitatively describe the information in an image. Texture analysis technology has been an active research field in computer vision, image processing, image analysis, image retrieval...

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
CPCG06V40/168
Inventor 陈维洋王梦杰
Owner QILU UNIV OF TECH
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