Venu Govindaraju

TL;DR: This paper presents a modification of correlation matching method, which uses thin-plate spline (TPS) as a model for non-linear transformations between two fingerprints, and shows the improvement when combining TPS deformation model with correlated matching method.

TL;DR: In this paper, a methodology of coarse holistic features and heuristic prediction of ideal features from ASCII is proposed to address the issues of variability at the word level and the paucity of samples for word-level training.

TL;DR: This work proposes an adaptation of the True DTW dynamic programming algorithm for English handwritten documents using the integration of the dissimilarity scores from a word-model word recognizer and Levenshtein distance between the recognized word and lexicon word, as a cost metric in the DTW algorithm leading to a fast and accurate alignment.

TL;DR: A combination method utilizing the dependencies between these scores and showing better performance than comparable traditional combination method using only matching scores related to the claimed identity is presented.