Derivative code and its pattern for object recognition

摘要

This paper proposes new methods, named Derivative Code (DerivativeCode) and Derivative Code Pattern (DCP), for object recognition. The derivative code is computed to capture the local relationship by using the binary result of the mathematical derivative value. Gabor based DerivativeCode is directly used on palmprint recognition, which achieves a much better performance than the state-of-art result on the PolyU palmprint database. Derivative Code Pattern (DCP) based on Dervativecode is further proposed to calculate the local pattern feature to extract directional texture for object recognition. Similar to Local Binary Pattern (LBP), DCP can be modeled by spatial histogram. To evaluate the performance of DCP, we test it on the FERET face database, and experimental results show that the proposed method achieves a better result than LBP.