سال انتشار: ۱۳۹۰

محل انتشار: هفتمین کنفرانس ماشین بینایی و پردازش تصویر

تعداد صفحات: ۵

نویسنده(ها):

Hassan nikoo – Department of Electrical and Computer EngineeringIsfahan University of TechnologyIsfahan, Iran
Hossein Talebi – Department of Electrical and Computer EngineeringIsfahan University of TechnologyIsfahan, Iran
Abdolreza Mirzaei – Department of Electrical and Computer EngineeringIsfahan University of TechnologyIsfahan, Iran

چکیده:

Gray Level Co-occurrence Matrix (GLCM) is one ofthe most powerful methods for extracting texture information.GLCM extracts occurrence probability of intensities with aspecific displacement between pair pixels. Most applications ofGLCM use a single displacement or a distinct number ofdisplacements. Maximum displacement between pair pixels isdependent on Texel size. So approaches that use distinctdisplacements for all textures taken from different distances fromtexture surface do not classify textures properly. This paperintroduces a supervised method for determining Texel size of atexture. Texel size can be used as the maximum displacement forconstructing gray-level co-occurrence matrix. This method usesvariances of intensifies in scale space levels to extract features.The proposed method calculates Texel size of 91.9% of testtextures correctly.