Abstract—Finger print recognition and matching will play a very pivotal role in forensic investigations. In this paper, we propose a novel method for finger print recognition. Its basic idea is to use a course to fine strategy based on Scale Invariant Feature Transform (SIFT) feature. To recognize a test sample, our method contains the three main steps: the first step identifies a certain number of finger prints from training samples, depending on the Horizontal Matching key points. If first steps verified successfully, we perform vertical SIFT Matching based on vertical key points. If first and second methods get verified successfully then it moves on to the third step. Here it verifies the finger prints by Histogram matching method. The first two steps, our method succeeds in greatly reducing the computational complexity, and avoiding the interference of those samples that may cause error recognition to a certain extent. The third step enhances the robustness of our method. This approach uses three way matching method, hence it achieves 98.9% accuracy. Experiments on different finger prints from standard database confirms that our method obtain high recognition accuracy and has a good robustness.

Index Terms—Keywords: Image processing, SIFT algorithm, Euclidean distance, MATLAB

Cite: H S Mohana, Rajithkumar B K, Navya K, H S Prabhakara and G Shivakumar, "FINGER PRINT RECOGNITION USING SCALE INVARIANT FEATURE TRANSFORM," International Journal of Electrical and Electronic Engineering & Telecommunications, Vol. 3, No. 3, pp. 49-60, July 2014.