Offline Signature Verification Based on Spatial Pyramid Image Representation with Taylor Series

Abstract

This paper presents Spatial Pyramid image representation based technique with partial sum of second order Taylor Series Expansion (TSE) for offline signature verification. In this approach, the given signature image is partitioned into sub blocks recursively and the local features in each sub blocks are computed and are represented as histogram. The histograms of the image and subblocks at various levels are concatenated to form a single histogram. This spatial pyramid feature vector is an extension of an orderless bag-of-features consisting of collection of histograms concatenated to form a single histogram. The partial sum of second order Taylor Series Expansion (TSE) is an approximate computation of finite number of terms in a small neighbourhood and hence provides a powerful mechanism to extract the localised structural information from the signature image. We propose kernel structures by extending the sobel operators to compute the higher order derivatives of TSE. Our approach captures both local and global features from the signature. We have used weighted histograms. The weight associated with the histogram is directly proportional to the depth of the level. The Support Vector Machine (SVM) is used for the classification. The classification accuracy of our approach on standard datasets is calculated and the results are compared with a few well known approaches. This shows that the performance of the proposed approach is better than the other approaches in the state of art literature.