PENGENALAN IRIS MATA MENGGUNAKAN PENCIRIAN MATRIKS KO-OKURENSI ARAS KEABUAN

Abstract

Human iris has a very unique pattern which is different for each person so it is possible to use it as a basic of biometric recognition. To identify texture in an image, texture analysis method can be used. For this reason, it is necessary to perform further research on how far this method is able to identify the feature on human iris. In this research, a software which is capable to recognize human iris using texture analysis has been developed. The image of iris is first segmented from eye image then enhanced with histogram equalization. The method used to extract the feature is Gray Level Co-occurrence Matrix (GLCM). The features obtained are energy, entropy, homogeneity, correlation, and contrast. The next step is recognition using normalized euclidean distance. Four experiments are done in the research, those are influence of number of sample in database, influence of GLCM distance, influence of GLCM angle and testing on eye images which are not in database. As the result, the highest accuration is achieved using GLCM angle of (0°+45°+90°+135°) and 2 pixels distance with two samples iris image saved is 90,625%. The lowest accuration is achieved using GLCM angle of 90° and 1 pixel distance is 51,43%. Keywords: biometric, human iris, texture analysis, GLCM, euclidean distance