r-Theta and orientation invariant transform and signal combining for fingerprint recognition

摘要

To cope with the image-shifting problem, this study uses the smaller image to compare with the larger target image to perform the image-match searching. The “vector magnitude invariant transform” technique is used to transfer the ring-circle-signal quantities to an invariant vector magnitude quantity. By the invariant vector magnitude quantity, one can perform the object-identification. The “vector magnitude invariant transform” technique can solve the image rotation problem. In this study, several vector magnitude quantities are combined to one quantity and this combined quantity is saved inside one specific pixel. By this approach, one pixel will possess more fingerprint geometry-features. The comparison approaching in this study is by the basis of one-pixel-to-one-pixel-comparison and by this scheme one can find the maximum matching points of two objects. In this study, one hundred and five comparisons are conducted to find the accuracy-rate of the developed algorithm. Within those 105 comparisons, 15 comparisons are conducted for self-comparison. The other 90 comparisons are conducted for comparisons between two different object images. The algorithm developed in this study can precisely classify the object image.