Online Signature Verification using SVD Method

• Main Author: Rahmat, Roushanak
• Format: Final Year Project
• Language: English
• Published: Universiti Teknologi Petronas 2009
• Subjects: TK Electrical engineering. Electronics Nuclear engineering
• Online Access: http://utpedia.utp.edu.my/8809/1/2009%20-%20Online%20Signure%20Verification%20using%20SVD%20Method.pdf; http://utpedia.utp.edu.my/8809/

Online signature verification rests on hypothesis which any writer has similarity among signature samples, with scale variability and small distortion. This is a dynamic method in which users sign and then biometric system recognizes the signature by analyzing its characters such as acceleration, pressure, and orientation. The proposed technique for online signature verification is based on the Singular Value Decomposition (SVD) technique which involves four aspects: I) data acquisition and preprocessing 2) feature extraction 3) matching (classification), 4) decision making. The SVD is used to find r-singular vectors sensing the maximal energy of the signature data matrix A, called principle subspace thus account for most of the variation in the original data. Having modeled the signature through its r-th principal subspace, the authenticity of the tried signature can be determined by calculating the average distance between its principal subspace and the template signature. The input device used for this signature verification system is 5DT Data Glove 14 Ultra which is originally design for virtual reality application. The output of the data glove, which captures the dynamic process in the signing action, is the data matrix, A to be processed for feature extraction and matching. This work is divided into two parts. In part I, we investigate the performance of the SVD-based signature verification system using a new matching technique, that is, by calculating the average distance between the different subspaces. In part IJ, we investigate the performance of the signature verification with reducedsensor data glove. To select the 7-most prominent sensors of the data glove, we calculate the F-value for each sensor and choose 7 sensors that gives the highest Fvalue.