Abstract: In this paper, efforts are focused to develop a compact system that consists of a finger knuckle print sensor (Sony Digital Camera) which acts as a biometric sensor unit with a direct interface to an external PC for storing finger knuckle print. Added to the finger knuckle print sensor discuss the techniques for finger knuckle recognition. Finger knuckle print sensor consists of a set of digital camera that captures the raw image of finger knuckle print. A camera (Sony DSC-W380) is fitted in the small, rectangular notch of acrylic bracket. The image of the finger knuckle print is captured through reflected light by digital camera. The Image is processed through an algorithm to extract the features set and form the finger knuckle print template for biometric authentication. Different algorithms for finger knuckle print recognition are pointed out and future researches about fusion level with correlated modality (Finger Vein) are suggested.

• Publication Date: 12-Mar-2012
• DOI: 10.15224/978-981-07-1847-3-971
• Views: 0
• Downloads: 0

Abstract: In this paper we present results of visual speech recognition using geometric and appearance model. For each of these methods Principal Component Analysis (PCA) is used to compute feature vectors. In this paper visual speech recognition is used for isolated digit utterance. For determination of visual features lip tracking is important. We used localized active contour method for lip tracking which was earlier used for biomedical application. PCA distance methods are used for feature vector comparison. Appearance method is compared with geometrical method for feature extraction. Appearance method is computationally efficient and giving better result as compare to geometrical method. Using appearance method of feature extraction, effect of isolation between two digit utterances is tested.

• Publication Date: 12-Mar-2012
• DOI: 10.15224/978-981-07-1847-3-976
• Views: 0
• Downloads: 0