This paper presents a robust face matching algorithm for gray intensity images. We have used feature based approach named Speed-Up Robust Features (SURF) suggested by Herbert Bay to match faces up to certain accuracy level. Firstly, after the locations of face regions are detected, a feature based method will be used to detect ROI points on the faces. Then a matching algorithm will be used to match the interest points to take the decision. Results of experiments to the faces without spectacles show that the proposed approach is not only robust but also quite efficient.