Improved Parallel Thinning Algorithm to Obtain Unit-width Skeleton

To extract the creditable features in a fingerprint image, many people use a thinning algorithm that plays a very important role in preprocessing. In this paper, we propose a robust parallel thinning algorithm that can preserve the connectivity of the binarized fingerprint image, while making the thinnest skeleton of only 1-pixel wide, which gets extremely close to the medial axis. The proposed thinning method repeats three sub-iterations. The first sub-iteration takes off only the outermost boundary pixel using the inner points. To extract the one-sided skeletons, the second sub-iteration seeks the skeletons with a 2-pixel width. The third sub-iteration prunes the needless pixels with a 2-pixel width existing in the obtained skeletons. The proposed thinning algorithm shows robustness against rotation and noise and makes the balanced medial axis. To evaluate the performance of the proposed thinning algorithm, we compare it with and analyze previous algorithms.