A unified framework for improving the accuracy of all holistic face identification algorithms

Abstract

Reconstructing the challenging human face identification process as a stability problem, we show that Electoral College can be used as a framework that provides a significantly enhanced face identification process by improving the accuracy of all holistic algorithms. The results are demonstrated by extensive experiments on benchmark face databases applying the Electoral College framework embedded with standard baseline and newly developed face identification algorithms.

Local binary pattern network: a deep learning approach for face recognition

“…Chen et al proposed a unified framework named electoral college [42] which mainly tackle the misalignment problem. In this method , every patches in the images, u , in gallery set allow to shift in a small range s to form a pile of patches which is defined…”

“…This framework is proved to be able to improve all the holistic algorithm [42] together with the original LBP approach [43].…”

Initial investigation into using a two-level regional voting approach for face verification.

“…It has just been proved that the regional voting can be applied into face identification systems, and the face identification system with regional voting scheme has achieved improvements on performance (Chen and Tokuda 2009). So far, the regional voting hasn't been applied into face verification system yet, and the prospective difficulties on finding the "thresholds" for each region keeps people away this research topic.…”

Regional displacement matching scheme for LBP based face recognition.

“…A new category of approaches that arose lately is regional voting approaches, which is more a general scheme [ll, 12, 13, 14] that could apply to many research fields other than face recognition [15,16,9]. The main objective of introducing the regional voting scheme is to create a system that is more stable against noise [14].…”