Hi am Santai would like to get details on matlab code for ldp in face recognition/Hand recognition ..My friend Anee said matlab code for ldp in face recognition will be available here and now i am living at Chittagong,Bangladesh......... and i last studied in the International Islamic university Chittagong......... ....i need help on matlab code for ldp in face recognition/Hand recognition for our research on hand sign......So Please help me immediately...
Posts: 14,118
Threads: 61
Joined: Oct 2014
The LDP is the LOCAL DIRECTIONAL MODEL. The LDP code is also robust enough to provide consistent representation in the presence of random noise and non-monotonous illumination variation. An LDP characteristic is obtained by calculating the edge response values in the eight directions at each pixel position and generating a code from the relative strength magnitude. Each face is divided into small regions, from where the LDP histograms are extracted and concatenated into a single characteristic vector to effectively represent the facial image. The recognition is done by adapting templates in accordance with the CSU face identification evaluation system and is evaluated with a well-studied FERET database. The performance of the recognition demonstrates the robustness of the proposed LDP descriptor to represent the appearance of the facial image over other existing approaches including the local binary pattern (LBP).
Facial recognition is becoming very popular tools for a successful human interaction system. It seems to be a good compromise between reliability and social acceptance and balances security and privacy. In this article we have presented a new descriptor of the feature based on the appearance, the Local Directional Variant (LDPv), to represent the facial components and analyze their performance for the face. An LDP characteristic is calculated from the relative edge response values in the eight directions at each pixel position, and then the LDPv descriptor of a facial image is generated from the integral projection of each LDP code weighted by Their corresponding variance. The final face representation is described below by the concatenated LDPv histogram of the local regions encoding the global and local texture information. The performance recognition with FERET datasets demonstrates the robustness of the proposed LDPv descriptor to represent the appearance of facial imaging over other existing state of the art approaches.
In recent times, automatic face recognition (AFR) has gained increasing interest in building human human interaction systems. As the AFR system becomes a widely explored research area, clearly defined recognition system steps have already been established that are: detection or location where faces are in an image; Alignment that ensures the alignment of the detected face (s) with a destination face or a model; Representation or description of feature transforms faces aligned in a representation that emphasizes certain facial aspects; And sorting, which determines whether a particular face matches a destination face.