A Palmprint Feature Extraction and Pattern Classification Based on Hybrid PSO-K-Means Clustering
The paper presents a hybrid Particle Swarm Optimization (PSO) technique for optimally clustering N palm-print data points into K cluster. The cluster center is automatically detected by PSO technique from a set of features obtained by applying geometrical methods to the palm-print data. The image captured by a peg-free scanner, a rectangular Region Of Interest (ROI) containing only the heart line is extracted. Intensity of the ROI image is standardized and image is smoothened. After that soble gradient with a threshold is applied to extract the heart line from the ROI.