Latest Publications
Unsupervised Ensemble of Experts (EoE) Framework for Automatic Binarization of Document Images
Keywords: automatic binarization, Binarization, Confidentness, Consolidation, Decision making, Document image processing, Educational institutions, Endorsement, endorsement graph, endorsement-dependent weights, Ensemble of Experts, EoE framework, Expert Selection, Feature extraction, graph theory, grid-based Sauvola method, input document image, Laplace equations, PSNR, Robustness, School […]
An Efficient Ground Truthing Tool for Binarization of Historical Manuscripts
Keywords: Binarization, binarization method, Data preprocessing, Degradation, document image degradation type, Document image processing, Feature extraction, Groundtruthing, historical document image, historical manuscript binarization, history, Image edge detection, image ground truthing tool, Ink, learning (artificial intelligence), learning approach, Manuals, Noise, Persian […]
Visual language processing (VLP) of ancient manuscripts: Converting collections to windows on the past
Keywords: Adaptation models, ancient manuscript, computational pattern analysis, cultural heritage, data mining, data-driven mining, Degradation, directed graphical model, Feature extraction, feature vector extraction, graph-based representation, Hidden Markov models, history, HMM, image document restoration, image restoration, natural language processing, social network, […]
W-TSV: Weighted topological signature vector for lexicon reduction in handwritten Arabic documents
Abstract
This paper proposes a holistic lexicon-reduction method for ancient and modern handwritten Arabic documents. The word shape is represented by the weighted topological signature vector (W-TSV), which encodes graph data into a low-dimensional vector […]
