EXPERIMENTAL APPROACH FOR HUMAN EAR IDENTIFICATION TECHNIQUES
Dr. Bhanu Prakash1, C. Usha Sree2, Department of Pharmacology
DOI : https://doi.org/10.63712/bpsrj-v1i3p003
ABSTRACT:
Biometric authentication systems rely on physiological or behavioral traits to establish personal identity. Among various physiological modalities, the human ear offers consistent structural features that remain stable throughout life. This study explores ear-based identification using preprocessing, feature extraction, and edge-detection techniques. Several edge-detectors Canny, Prewitt, Roberts, Laplacian of Gaussian (LoG), and Approx-Canny—were evaluated to determine their effectiveness in delineating the ear shape. Feature-extraction methods including Harris, FAST, and SURF were applied to classify distinctive keypoints. The experimental findings highlight the comparative performance of these methods and propose an optimized approach for ear-based biometric recognition.