A New Segmentation Algorithm of Finger Crease Based on Wavelet and Radon Projection

This paper presents a new automatic segmentation algorithm based on wavelet multi-resolution and Radon projection. By giving the definition of ROI of finger crease, this algorithm use feature vector and regional growth to produce candidate sub-region set in high frequency sub-images, and then utilize Radon projection in low frequency sub-images to verify the candidate sub-region set. Finally, by adopting straight-line fitting technique, the location of ROI of finger crease is accurately located. Emulation experiment shows that this algorithm can not only resist noise and hand-shape affection but also robust in different situations.