Co-occurrence context of the data-driven quantized local ternary patterns for visual recognition

In this paper, we describe a novel local descriptor of image texture representation for visual recognition. The image features based on micro-descriptors such as local binary patterns (LBP) and local ternary patterns (LTP) have been very successful in number of applications including face recognition and texture analysis. Instead of binary quantization in LBP, LTP thresholds the differential values between a focused pixel and its neighborhood pixels into three graylevel, which can be explained as the active status (i.e., positively activated, negatively activated and not activated) of the neighborhood pixels compared to the focused pixel. However, regardless to the magnitude of the focused pixel, the thresholding strategy remains fixed, which would violate the principle of human perception. Therefore, in this study, we design LTP with a data-driven threshold according to Weber´s law, a human perception principle; further, our approach incorporates the contexts of spatial and orientation co-occurrences (i.e., co-occurrence context) among adjacent Weber-based local ternary patterns (WLTPs) for texture representation. In order to validate efficiency of our proposed strategy, we apply to three different visual recognition applications including two texture datasets and one food image dataset, and prove the promising performance can be achieved compared with the state-of-the-art approaches.