Coke microscopic image classification algorithm based on run-length texture features
Abstract：After analyzing texture characteristics of graphite and fibrous subclass in coke optical texture micrograpl~ classification algorithm, combining run-length textural features and Support Vector Machine （SVM）, was propose Firstly, the run-length matrix and a series of related texture features of coke optical texture micrograph were calcul ed, validities of these features for subclasses classifition were analyzed. Then Support Vector Machine based classi｜ was trained with those valid features and their combination. Experimental results show that with the proposed alt rithm, some subclasses among different optical textures of anisotropic, such as fibrous and graphite, can be classif more reasonably and effectively.
Keywords：coke optical texturetexture featurerun-lengthSVMclassifier
Publication Date：2012-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1051-1055 )