Skip to content

Recognition of different material using its texture feature out of the video file

Notifications You must be signed in to change notification settings

KsanaKhomiak/material_recognition_through_glcm_texture

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

material_recognition_through_glcm_texture

Theory behind

These statistics can characterize the texture of an image as they provide information about the local variability of pixels intensity values in an image. For example:

  • in areas with smooth texture, the range of values in the neighborhood around a pixel is a small;
  • in areas of rough texture, the range is larger.

Grey level co-occurrence matrix (GLCM) is a statistical method for deriving texture features considering the relationship between groups of two pixels in the image at certain distance and at certain angle.

GLCM Correlation

estimate deformities in the textural image.

GLCM Dissimilarity

estimate heterogeneity in the image texture.

Use example

Current project can be used in various study fields, from medical to geological.

Project initially was created to recognize different soil material using its texture feature out of the recorder video file.

This is the efficient way to speed up the data exploration as within the minutes of analysis it provides clear recognition of the material, estimation of its structure and distinct thresholds where material type is changing.

material_recognition_performance

Note: Input video data was provided by Royal Eijkelkamp.

About

Recognition of different material using its texture feature out of the video file

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published