Image processing and pattern recognition are one of the most important area of research in computer science. Recently, several studies have been made and efficient approaches have been proposed to provide efficient solutions to many real and industrial problems. Texture analysis is a fundamental field of image processing because all surfaces of objects are textured in nature. Thus, we proposed a new texture analysis method. In this paper, we proposed a novel texture analysis approach based on a recent feature extraction method called neighbor based binary pattern (NBP). The NBP method extract the local micro texture and is robust against rotation, which is a key problem in image processing. The proposed system extract two-reference NBP histograms from the texture in order to calculate a model of the texture. Finally, several models have been constructed to be able to recognize textures even after rotation. Textured images from Brodatz album database were used in the evaluation. Experimental studies have illustrated that the proposed system obtain very encouraging results robust to rotation compared to classical method.