Footprint Recognition with Principal Component Analysis and Independent Component Analysis

The finger print recognition, face recognition, hand geometry, iris recognition, voice scan, signature, retina scan and several other biometric patterns are being used for recognition of an individual. Human footprint is one of the relatively new physiological biometrics due to its stable and unique characteristics. The texture and foot shape information of footprint offers one of the powerful means in personal recognition. This work proposes a footprint based biometric identification of an individual by extracting texture and shape based features using Principal Component Analysis (PCA) and Independent Component Analysis (ICA) linear projection techniques. PCA is a commonly used technique for data classification and dimensionality reduction and ICA is one of the most widely used blind source separation technique for revealing hidden factors that underlie sets of random variables, measurements, or signals. In this study PCA and ICA have been compared for footprint recognition using distance classification techniques such as Euclidean distance, city block, cosine and correlation. Experimental results show that ICA performs better than PCA for footprint recognition.