Face Recognition using Co-occurrence Matrix of Local Average Binary Pattern (CMLABP)
Akhtar Hazrati Bishak, Z. Ghandriz, Tayebeh Taheri · 2012
Abstract — The local binary pattern (LBP) operator has been proved to be effective for image representation, but it is too local to be strength. In this paper, we propose Co-occurrence Matrix of Local Average Binary Pattern operator (CMLABP), and apply it to face recognition. In my method, calculation is performed based on average values of P-neighbor values of pixels, instead of individual pixels. In addition instead of histogram; that represents only the occurrences of the patterns without any indication about their locations, we use of Co-occurrence Matrix to extract features.The experimental results on the FERET and ORL face databases validate that the offered algorithm has better performance than or comparable performance with state-of-the-art local feature based methods.