Skip to content

A image searcher based in three components: color, texture and form.

Notifications You must be signed in to change notification settings

marceloatg/ImageSearcher

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ImageSearcher

A image searcher based in three components: color, texture and form.

The color engine divides an image in 4 parts and then a HSV histogram is generated for each part. This histogram containing 256 levels is stored as a feature vector.

The texture engine divides an image in 4 parts and then the LBP algorithm is applied into the image. For each part of the image, a 256 level histogram is generated and stored as a feature vector.

In order to search an image, the Euclidean distance is applied considering the selected feature vectors.

About

A image searcher based in three components: color, texture and form.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published