Finger shape expansion and recognition by wavelet transform

摘要

This study uses the object extracting technique to extract thumb, index, middle, ring, and small fingers. The developed algorithm can locate the precise locations of fingertips and finger-to-finger-valleys. The extracted fingers contain many useful geometry features. One can use these features to identify different fingers. The geometry descriptor is used to transfer fingers to another straight positions. Finger is scaled and the reverse wavelet transform is performed to cause the finger to possess more salient feature. Image subtraction is used to examine the difference of the two fingers. This study uses fingers and palm to recognize different persons.