Despite recent advances in face recognition systems, they suffer from serious problems because of the extensive types of changes in human face (changes like light, glasses, head tilt, different emotional modes). Each one of these factors can significantly reduce the face recognition accuracy. Several methods have been proposed by researchers to overcome these problems. Nonetheless, in recent years, using thermal images has gain more attention among the introduced solutions as an effective and unique solution. This article studies the performance of sparse processing techniques when facing with challenges of face recognition problem in thermal images. Also, the potential of the sparse classifier algorithm to receive information directly from input images without using any feature extraction algorithms was studied. The obtained results indicated that the sparse processing techniques outperform the Eigenface and KNN algorithms in terms of addressing the challenges of thermal images. In this work, USTC NVIN and CBSR NIR face datasets were used for simulation purposes. These datasets include the images with different emotional states (sad, happy, etc.) captured in different light conditions; also the images are captured both with and without wearing glasses. Simulation results have shown that sparse classifier can be an effective algorithm for the face recognition problem in thermal images.