Deep learning approaches to scene text detection: a comprehensive review

T Khan, R Sarkar, AF Mollah - Artificial Intelligence Review, 2021 - Springer
In recent times, text detection in the wild has significantly raised its ability due to tremendous
success of deep learning models. Applications of computer vision have emerged and got …

Scene text understanding: recapitulating the past decade

M Ghosh, H Mukherjee, SM Obaidullah, XZ Gao… - Artificial Intelligence …, 2023 - Springer
Computational perception has indeed been dramatically modified and reformed from
handcrafted feature-based techniques to the advent of deep learning. Scene text …

Utilization of relative context for text non-text region classification in offline documents using multi-scale dilated convolutional neural network

S Bhowmik - Multimedia Tools and Applications, 2024 - Springer
Identification of text and non-text regions in a document image is necessary before feeding it
to an Optical character recognition (OCR) engine for the generation of editable version. This …

Text classification using deep learning techniques: A bibliometric analysis and future research directions

G Sarin, P Kumar, M Mukund - Benchmarking: An International …, 2024 - emerald.com
Purpose Text classification is a widely accepted and adopted technique in organizations to
mine and analyze unstructured and semi-structured data. With advancement of …

Application of texture-based features for text non-text classification in printed document images with novel feature selection algorithm

S Ghosh, SKK Hassan, AH Khan, A Manna, S Bhowmik… - Soft Computing, 2022 - Springer
Text non-text separation is one of the most essential pre-processing steps for any optical
character recognition (OCR) system. As an OCR engine can only process texts, the non …

DSANet: dilated spatial attention network for the detection of text, non-text and touching components in unconstrained handwritten documents

S Bhowmik, S Risat, B Sarkar - Neural Computing and Applications, 2024 - Springer
Handwritten documents generated in our day-to-day office work, class room and other
sectors of society carry vital information. Automatic processing of these documents is a …

Understanding contents of filled-in Bangla form images

R Bhattacharya, S Malakar, S Ghosh… - Multimedia Tools and …, 2021 - Springer
With a wide variety of forms being generated in different organizations daily, efficient and
quick retrieval of information from these forms becomes a pressing need. The data on these …

Document region classification

S Bhowmik - Document Layout Analysis, 2023 - Springer
After region segmentation, it is necessary to identify the functional labels of the segmented
regions. This is because OCR engines can only consider text regions. Presence of non-text …

MuSIC: A Novel Multi-Scale Deep Neural Framework for Script Identification in the Wild

T Khan, M Saif, AF Mollah - IEEE Access, 2024 - ieeexplore.ieee.org
Script identification in digital images is crucial for automated text reading in multilingual
contexts. Develo** a robust script-identifier in complex environments is challenging due to …

A novel multi-scale deep neural framework for script invariant text detection

T Khan, AF Mollah - Neural Processing Letters, 2022 - Springer
Text detection in the wild is an active research problem in computer vision. Localizing text in
multi-script and arbitrary–oriented scene images in unconstrained environment is one of the …