Evaluation methods are the paradigm to determine the accuracy and performance of the illumination invariant face recognition algorithms. Performance evaluation methods are used to differentiate, compare and elucidate various aspects of face recognition such as features of subjects, location and illumination. Changing illumination severely affects the recognition accuracy of various existing face recognition algorithms. To address the illumination problem various illumination insensitive face

more »

... ognition methods are developed. This paper presents a hybrid approach of illumination invariant face recognition using Local Binary Pattern and Local Ternary Pattern fusion with illumination normalization and compares the performance of the proposed algorithm and traditional algorithms using the Receiver Operating characteristics(ROC).