Biological inspired pose-invariant face recognition

A small change in image will cause a dramatic change in signals. Visual system needs to ignore these changes, yet specific enough to perform recognition. Problem intended to be solved is on 2D translation and scaling invariances and 3D pose invariance without imposing strain on memory and with biological justification. In this paper, we propose a novel biologically inspired vision model for pose-invariant face recognition. The model can be divided into lower and higher visual stages. Lower visual stage models the visual pathway from retina to the striate cortex (V1), whereas the modeling of higher visual stage mainly based on current psychophysical. The feasibility of the proposed model is evidenced by the evaluation study using FERRET face database.