Offline script identification from multilingual indic-script documents: a state-of-the-art

PK Singh, R Sarkar, M Nasipuri - Computer Science Review, 2015 - Elsevier
Abstract Offline Script Identification (OSI) facilitates many important applications such as
automatic archiving of multilingual documents, searching online/offline archives of document …

Script identification of multi-script documents: a survey

K Ubul, G Tursun, A Aysa, D Impedovo, G Pirlo… - IEEE …, 2017 - ieeexplore.ieee.org
In recent years, with the widespread of Internet and digitized processing of multi-script
documents worldwide, script identification techniques have become more important in the …

Understanding NFC-Net: a deep learning approach to word-level handwritten Indic script recognition

S Kundu, S Paul, PK Singh, R Sarkar… - Neural Computing and …, 2020 - Springer
This paper presents a deep learning architecture modified for resource-constrained
environments, called Non-Fully-Connected Network or NFC-Net, based on convolutional …

Word-level script identification for handwritten Indic scripts

PK Singh, R Sarkar, M Nasipuri… - 2015 13th International …, 2015 - ieeexplore.ieee.org
Automatic script identification from handwritten document images facilitates many important
applications such as indexing, sorting and triage. A given Optical Character Recognition …

A comprehensive handwritten Indic script recognition system: a tree-based approach

PK Singh, R Sarkar, V Bhateja, M Nasipuri - Journal of Ambient …, 2024 - Springer
A noteworthy achievement has been accomplished in develo** optical character
recognition (OCR) systems for different Indic scripts handwritten document images. But in a …

A similarity-based two-view multiple instance learning method for classification

Y **ao, Z Yin, B Liu - Knowledge-Based Systems, 2020 - Elsevier
Multiple instance learning (MIL) has been proposed to classify the bag of instances. In
practice, we may meet the problems which have more than one view data. For example, in …