Title :
Texture direction analysis using edge counts
Author :
Vaidyanathan, G. ; Lynch, P.M.
Author_Institution :
Dept. of Mech. Eng., Tulane Univ., New Orleans, LA, USA
Abstract :
Texture can be modeled as an arrangement of visible edges which in turn amalgamate into patterns. These edges are due to variations in local gray levels. A method for estimating the angular orientation of a texture pattern using these edges is presented. The total number of edge transitions in four different directions, namely, horizontal, vertical, right diagonal, and left diagonal, or an image are counted. A model relating the four directional edge-transition counts is developed and used to determine the predominant orientation of the pattern. The technique is shown to be effective with both regular and random patterns as well as natural textures. The accuracy of the procedure is analyzed and evaluated
Keywords :
picture processing; angular orientation; edge counts; natural textures; picture processing; random patterns; regular patterns; texture direction analysis; texture pattern; Artificial intelligence; Bidirectional control; Detectors; Humans; Image edge detection; Image texture analysis; Layout; Mechanical engineering; Pixel; Surface texture;
Conference_Titel :
Southeastcon '89. Proceedings. Energy and Information Technologies in the Southeast., IEEE
Conference_Location :
Columbia, SC
DOI :
10.1109/SECON.1989.132497