Local primitive code mining for fast and accurate face recognition

This paper proposes a new feature descriptor named as Local Primitive Code (LPC), which exhibits impressively discriminative capability on various face datasets. Essentially, LPC descriptors are somewhat like filter banks of Gaussian derivatives to capture multi-scale and multi-orientation image local textures but meanwhile enables faster feature extraction. It employs a framework composed of two stages: Firstly facial images are preprocessed by the pool of differential and quotient filters to generate numerous filtered images with various textures, and then directional binary encoding (DBE) operates on filtered images for primitive code mining. With such stages, feature maps with complementary discriminative information will be generated, and the fusion of them can greatly improve face recognition performance. Experimental results verify its performance even on some challenging databases. The algorithm is transplanted into mobile platform and achieves real-time performance on Nokia N82.