An effectual method for extraction of ROI of palmprints

Abstract

Extraction of region of interest (ROI) from a palmprint considerably improves the efficiency of identification systems as ROI extracted palmprint images have more entropy and require less processing and storage. In this paper we have extracted the ROI of palmprints of two sets of databases, Hongkong Polytechnic University low resolution palmprint Database and high resolution indigenous database. The method used here employs image processing techniques including dynamic thresholding for binarization, centroid determination, boundary extraction using morphological operations, Euclidean distance calculations from the centroid, valley points determination after smoothening the Euclidean distance plot, from which finally the ROI is extracted.For the above mentioned datasets, the ROI of size 128 × 128 and 256 × 256 respectively have been extracted using this technique.