Abstract:The light intensity variation may bring some differences among vehicle face images which are captured at different times such as vehicle color difference, headlight status difference, etc. To make the recognition method universal to multiple lightingconditions, a novel siamese nonnegative matrixfactorization (NMF)model isformulated. First,theoriginal featuresofeachpairof vehicle face trainingimagesare split andtakingas theinputoftwo NMF models.Then, asiameseNMFmodelisestablishedbyfusingtheerrorloss,the intraclass loss and the interclass loss. The same feature basis vectors are shared by these two NMF models. Finally, the model is solved by using the gradient descent algorithm. Thus, the shared feature basis vectors can be acquired, and the reidentification of vehicle face images can be achieved based on the cosine distance. Experimental results show that the proposed algorithm can achieve accurate reidentification results even when two vehicle face images are captured under different lighting conditions. Both the false accept rate and the false reject rate can be reduced to be below 6%.