Video Based Palmprint Recognition

The ability to carry out biometric authentication using generic cameras can be extremely useful for a variety of applications, especially in mobile devices. Palmprint based authentication is appropriate in such cases due to its discrimination power, ease of presentation and scale and size of texture information that is easily captured by commodity cameras. However, the unconstrained nature of pose and lighting in such applications introduces several challenges in recognition process. Even minor changes in pose of the palm can induce significant changes in the visibility of the lines. We turn this property to our advantage by capturing a one second video, where the natural motion of the palm induces minor pose variations, providing additional texture information. We propose a method to register multiple frames of the video without requiring correspondence, while being efficient for practical use. Experimental results on a set of different 100 palms show that the use of multiple frame...

• Type: Conference
• Year: 2010
• Where: ICPR
• Authors: Chhaya Methani, Anoop Namboodiri
• Keywords: Computer Vision, ICPR 2010, Multiple Frames, Palmprint Based Authentication, Texture Information