Edge direction matrixes-based local binary patterns descriptor for invariant pattern recognition

Invariant descriptor for shape and texture image recognition usage is an essential branch of pattern recognition. It is made up of techniques that aim at extracting information from shape images via human knowledge and works. The descriptors need to have strong Local Binary Pattern (LBP) in order to encode the information distinguishing them. Local Binary Pattern (LBP) ensures encoding global and local information and scaling invariance by introducing a look-up table to reflect the uniformity structure of an object. It is needed as the edge direction matrices (EDMS) only apply global invariant descriptor which employs first and secondary order relationships. The main objective of this paper is the need of improved recognition capabilities which achieved by the combining LBP and EDMS. Working together, these two descriptors will add advantages to the program and enable the researcher to investigate the weaknesses of each one. Two classifiers are used: multi-layer neural network and random forest. The techniques used in this paper are compared with Gray-Level Co-occurrence matrices (GLCM-EDMS) and Scale Invariant Feature Transform (SIFT) by using two benchmark dataset: MPEG-7 CE-Shape-1 for shape and Arabic calligraphy for texture. The experiments have shown the superiority of the introduced descriptor over the GLCM-EDMS and the SIFT.