| The objective of this research is to present an efficient method for the verification and classification of the Fingerprints using Haar Wavelet Transform. Fingerprints are imprints formed by friction ridges of the skin in fingers and thumbs. They have long been used for identification because of their immutability and individuality. A fingerprint consists of many ridges and valleys that run next to each other. The Wavelet transform based approach is desirable for on-line verification with accuracy. The features such as Standard Deviation, Mean, Variance as well as higher order statistics like Energy, Entropy and Contrast are obtained. Using these values the fingerprints are classified into classes: Arch, whorl, Right loop, and Left loop. The positive percentage of classification in whorls is 81.8%. It is 83.3% in the case of Arches. As the right loops and the left loops are inverses of each other, the error percentage is more. |
