The local binary pattern approach, a texture descriptor method proposed by Ojala et al., has gained increased acceptance due to its computational simplicity and more importantly for encoding a powerful signature for describing textures. LBP feature extraction of edge face detection, in the light of with human face discrimination influence different angles test recognition efficiency. The algorithm presents some limitations such as lack of rotational invariance which have led to many proposals or extensions in order to overcome such limitations. In this paper we performed a modified algorithm of the original LBP proposal together with other recently proposed LBP extensions. Experimental results demonstrated the effectiveness and robustness of the described texture descriptors for images that are subjected to geometric or radiometric changes.