Publication

Abstract : This paper explains an effective approach for designing an adaptive wavelet for each palmprint image through a ring-projection technique. With this technique, Region of Interest (ROI) of 2-D image of palmprint is obtained. Using ring projection technique on the extracted 2-D ROI image, dimensionality reduces to 1-D information. The 1-D information pattern we get through ring projection is constant or not variable to rotation, less memory needed to store data and useful in designing the adaptive wavelet for each input image. The principle for designing a new wavelet is to minimize the error signal of given information and express the resulting information as smoothening signal under constraints leading to an adaptive wavelet. The Indian Institute of Technology, New Delhi palm-print image database is used to examine the superiority of wavelet designing technique. Seven images from each subject, from both of the left and right hand, are acquired in varying hand pose variations. By the designed adaptive wavelet, all the palm-print images of the same subject are decomposed to extract numerous features value which shows the uniqueness of palmprint images for classification.