• N.Rajasekhar

Texture content plays a prominent role in classification of the image. In this paper we use local line binary patterns for the texture analysis which has high tolerance against illumination variation. Steerable decomposition, a new rotation-invariant and scale-invariant texture representation is used to filter image in four orientations sub bands of the images for feature extraction. Finally, a classifier like SVM, KNN is used for the classification. The experimental results are evaluated for different binary patterns like local binary pattern (LBP), simplified binary pattern (SLBP) and local line binary pattern (LLBP).Comparative analysis shows that LLBP outperforms than the other two binary patterns.

Local binary pattern, steerable filter decomposition, feature extraction, SVM, KNN

"SCALE IN VARIANT TEXTURE CLASSIFICATION USING LOCAL LINE BINARY PATTERN AND SVM ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.3, Issue 12, page no.678-684, December-2016, Available :http://www.jetir.org/papers/JETIR1701794.pdf

"SCALE IN VARIANT TEXTURE CLASSIFICATION USING LOCAL LINE BINARY PATTERN AND SVM ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.3, Issue 12, page no. pp678-684, December-2016, Available at : http://www.jetir.org/papers/JETIR1701794.pdf