To Present Method for Rice Variety Identification with Fuzzy- imperialist Competitive Algorithm

Digital image processing in recent decades has made considerable progress intheoretical and practical aspects. Nowadays, machine vision techniques haveimportant application in the field of agriculture. One of these applications isdetection of different varieties of rice from the bulk sample of rice image. Thesetechniques also have high speed, accuracy and reliability. Texture feature selectionis one of the important characteristics used in pattern recognition. The betterfeature selection of a feature set usually results in better performance in aclassification problem. In This work we try to extract features by usingco_occurrence matrix and select the best feature set for classification of ricevarieties based on image of bulk samples using hybrid algorithm which iscalled fuzzy_ imperialist competition and then classify the best features usingsupport vector machine(SVM). Results of the proposed method showed, theclassification accuracy is improved to 96/79%. The feature set which is selected bythe fuzzy-Ica provides the better classification performance compared to that obtained by Imperialist competition algorithm.

Keywords:

Fuzzy-Imperialist Competition Algorithm , Texture Feature , Co_Occurrence Matrix Support Vector Machine