Discriminative Embedded Oriented Local Pattern (D-EOLP): a new feature based image descriptor

This paper presents an image descriptor based on local texture and orientation patterns. The texture information is embedded in the orientation component. Each pixel gradient orientation is considered for extracting the D-EOLP features. The image is divided into several blocks, from each of which the D-EOLP features are extracted and concatenated. For redundancy reduction, local mean-based nearest neighbor discriminant analysis (LM-NNDA) is employed and a low-dimensional potential, enhanced image descriptor is obtained. The performance of the proposed approach is evaluated on two prominent application areas namely, handwritten recognition and facial expression recognition(FER). The robustness of this approach is analyzed in terms of accuracy and computational time by comparing it with state-of-the-art algorithms. Results of handwritten numeral recognition on standard numeral datasets like ISI Kolkata, CMaterdb3, and MNIST and of FER on CK+ and Jaffe show better performance with the proposed approach.