Discriminative DCT: An Efficient and Accurate Approach for Off-Line Signature Verification

Abstract

In this paper, we proposed to combine the transform based approach with dimensionality reduction technique for off-line signature verification. The proposed approach has four major phases: Preprocessing, Feature extraction, Feature reduction and Classification. In the feature extraction phase, Discrete Cosine Transform (DCT) is employed on the signature image to obtain the upper-left corner block of size mX n as a representative feature vector. These features are subjected to Linear Discriminant Analysis (LDA) for further reduction and representing the signature with optimal set of features. Thus obtained features from all the samples in the dataset form the knowledge base. The Support Vector Machine (SVM), a bilinear classifier is used for classification and the performance is measured through FAR/FRR metric. Experiments have been conducted on standard signature datasets namely CEDAR and GPDS-160, and MUKOS, a regional language (Kannada) dataset. The comparative study is also provided with the well known approaches to exhibit the performance of the proposed approach.