Disguised face identification using multi-modal features in a quaternionic form

Disguised face recognition is considered as very challenging and important problem in the face recognition field. A disguised face recognition algorithm is proposed using quaternionic representation. The feature extraction module is accomplished with a new method, decomposing each face image into a linear decomposition of a set of localized basis functions. The feature sets, related to Shapelets and Gabor filters, are used to encode the image data. The coefficients of the integral transformations are fused and presented in quaternionic representation to the Classification module. This study shows that the proposed algorithm can achieve high recognition results under disguised conditions.