An Unsupervised and Robust Line and Word Segmentation Method for Handwritten and Degraded Printed Document Jayati Mukherjee, Swapan K. Parui, and Utpal Roy Association for Computing Machinery (ACM) Segmentation of text lines and words in an unconstrained handwritten or a machine-printed degraded document is a challenging document analysis problem due to the heterogeneity in the document structure. Often there is un-even skew between the lines and also broken words in a document. In this article, the contribution lies in segmentation of a document page image into lines and words. We have proposed an unsupervised, robust, and simple statistical method to segment a document image that is either handwritten or machine-printed (degraded or otherwise). In our proposed method, the segmentation is treated as a two-class classification problem. The classification is done by considering the distribution of gap size (between lines and between words) in a binary page image. Our method is very simple and easy to implement. Other than the binarization of the input image, no pre-processing is necessary. There is no need of high computational resources. The proposed method is unsupervised in the sense that no annotated document page images are necessary. Thus, the issue of a training database does not arise. In fact, given a document page image, the parameters that are needed for segmentation of text lines and words are learned in an unsupervised manner. We have applied our proposed method on several popular publicly available handwritten and machine-printed datasets (ISIDDI, IAM-Hist, IAM, PBOK) of different Indian and other languages containing different fonts. Several experimental results are presented to show the effectiveness and robustness of our method. We have experimented on ICDAR-2013 handwriting segmentation contest dataset and our method outperforms the winning method. In addition to this, we have suggested a quantitative measure to compute the level of degradation of a document page image.
Recognition of Degraded Bangla Documents Using Hybrid Deep Neural Network Model Jayati Mukherjee and Utpal Roy IEEE Digitization of degraded document by Optical Character Recognition is an active research area in the context of document analysis. This will help to edit document electronically, to perform content based searching and finally to store it for easy document management. Considering the popularity and heritage, in this work degraded printed Bangla document has been considered as a source material to be digitized. The well known ISIDDI database of Bangla degraded document has been exploited in the present research. This database contains 535 images of printed Bengali pages. These pages are of different fonts, sizes, formats together with different levels of degradation, collected from various sources. From these page images character samples have been extracted and 336 character classes are identified which are now ready for classification. In this research work we have developed an CNN-XGBoost hybrid model for better classification. Here CNN extracts the features of the character images automatically and XGBoost technique is responsible for better classification and recognition. The classification accuracy thus obtained is 91.86%, which outperforms the accuracies of the classifiers exercised so far on the ISIDDI datasets.
Gait Identity Verification Using Equipped Smartphone Sensors Debjyoti Ghosh, Soumen Roy, Utpal Roy, and D. D. Sinha IEEE A strong and convenient identity verification method is always demanded. Nowadays, the advanced sensing features like gyroscope, accelerometer and rotation information are easily available through a smartphone. These prominent and hidden features (orientation and force) created simultaneously against any activities on a smartphone that can be used in user identity verification instead of considering morphological features (video and image). Two similarity measure algorithms (Euclidean and Manhattan) have been used on the collected dataset from 63 users in 5 sessions with 4 repetitions and we got 8.7% of EER (Equal Error Rate). This study also explains the data collection tools, data capture procedure and anomaly detection for further development in this topic area.
A novel approach to identify parkinson’s disease and other similar neural stress by analysing keystrokes on modern active devices with ensemble classification S Roy, U Roy, D Sinha, RK Pal Multimedia Tools and Applications, 1-40 2025
Refining the Impact of Quantum Noise: From Chaotic Effects to Contribution in Randomness Generation R Biswas, U Roy 2024
Unsupervised Feature Selection for High-Dimensional Data Using Clustering and Multi-Objective Optimization S Laha, U Roy International Conference on Biologically Inspired Techniques in Many 2024
Advanced Keystroke Dynamics for Secure Smartphone Authentication S Dutta, S Roy, U Roy International Conference on Biologically Inspired Techniques in Many 2024
A Low Resource Multi-lingual Simultaneous Script Identification and Text Recognition Model J Mukherjee, U Roy SN Computer Science 5 (6), 740 2024
Advancing Smartphone Sensor-Based Keystroke Dynamics for Implicit and Active Authentication: Addressing Challenges and Enhancing Usability Control S Roy, U Roy, D Sinha, RK Pal International Symposium on Applied Computing for Software and Smart Systems 2024
Space–time clusters and co-occurrence of Plasmodium vivax and Plasmodium falciparum malaria in West Bengal, India M Maiti, U Roy Malaria Journal 23 (1), 189 2024
Spatial environment and open defecation: in pursuit of social valuation of sanitation ecosystem services S Chakraborty, J Novotn, J Das, PP Patel, I Maity, U Roy The Professional Geographer 76 (3), 303-317 2024
Mimicking Photon Source Measurement with Quantum Digital Twin: A Framework for High-Quality Randomness R Biswas, U Roy International Journal of Information Technology, Research and Applications 3 2024
Exploring the Limits of Classical Random Number Generation and Unveiling Quantum Alternatives R Biswas, DR Talukdar, U Roy International Conference on Network Security and Blockchain Technology, 35-45 2024
Learning from imbalanced data in healthcare: State-of-the-art and research challenges D Roy, A Roy, U Roy Computational Intelligence in Healthcare Informatics, 19-32 2024
Evaluating Space Time Cluster and Co-occurrence of Malaria Vectors of West Bengal in India M Maiti, U Roy 2024
Entry-Point Adaptive Keystroke Dynamics-Based User Authentication for Evolving Passwords S Dutta, S Roy, R Mondal, T Ghosh, U Roy International Conference on Computational Intelligence in Communications and 2024
Verifying the reliability of quantum random number generator: A comprehensive testing approach R Biswas, D Roy Talukdar, U Roy SN Computer Science 5 (1), 140 2024
Lifestyle and the early onset of diabetes mellitus among young adults T Shaw, U Roy Developments in Environmental Science 15, 383-393 2024
A unique approach towards keystroke dynamics-based entry-point user access control S Roy, D Sinha, RK Pal, U Roy International Journal of Biometrics 16 (2), 133-157 2024
Multi-modal Biometric Authentication: Harnessing Human Gait and Keystroke Dynamics for Enhanced Security S Dutta, U Roy, S Roy International Conference on Computational Technologies and Electronics, 311-322 2023
Quantum Measurement and Inherent Randomness: A Study on Modified Hadamard Based Xorshift Pseudorandom Number Generator Algorithm R Biswas, U Roy International Conference on Computational Technologies and Electronics, 228-239 2023
Diversity of Termites from Durgapur Government College Campus, Paschim Bardhaman, West Bengal, India US Roy International Journal of Ecology and Environmental Sciences 49 (6), 651-653 2023
Assessing the climate-disaster-led migration scenario in the Indian Sundarbans S Bandyopadhyay, C Mallik, U Roy International Migration, COVID-19, and Environmental Sustainability, 97-115 2023
MOST CITED SCHOLAR PUBLICATIONS
PANDA Phase One: PANDA collaboration G Barucca, F Dav, G Lancioni, P Mengucci, L Montalto, PP Natali, ... The European Physical Journal A 57, 1-36 2021 Citations: 114
Ecotoxicological Assessment of Tannery Effluent Using Guppy Fish (Poecilia reticulata) as an Experimental Model: A Biomarker Study A Aich, AR Goswami, US Roy, SK Mukhopadhyay Journal of Toxicology and Environmental Health, Part A 78 (4), 278-286 2015 Citations: 72
Feasibility studies of time-like proton electromagnetic form factors at ANDA at FAIR PANDA Collaboration, B Singh, W Erni, B Krusche, M Steinacher, ... The European Physical Journal A 52, 1-23 2016 Citations: 57
Study on avifaunal diversity from three different regions of North Bengal, India US Roy, P Banerjee, SK Mukhopadhyay Asian Journal of Conservation Biology 1 (2), 120-129 2012 Citations: 56
Precision resonance energy scans with the PANDA experiment at FAIR: Sensitivity study for width and line shape measurements of the X (3872) Panda Collaboration, G Barucca, F Davı, G Lancioni, P Mengucci, ... The European Physical Journal A 55, 1-18 2019 Citations: 52
Feasibility study for the measurement of transition distribution amplitudes at in B Singh, W Erni, B Krusche, M Steinacher, N Walford, H Liu, Z Liu, B Liu, ... Physical Review D 95 (3), 032003 2017 Citations: 52
Coalition formation for cooperative service-based message sharing in vehicular ad hoc networks B Das, S Misra, U Roy IEEE Transactions on Parallel and Distributed Systems 27 (1), 144-156 2015 Citations: 50
A novel approach to skew detection and character segmentation for handwritten Bangla words A Roy, TK Bhowmik, SK Parui, U Roy Digital Image Computing: Techniques and Applications (DICTA'05), 30-30 2005 Citations: 47
In pursuit of sustainability–Spatio-temporal pathways of urban growth patterns in the world's largest megacities S Chakraborty, H Dadashpoor, J Novotn, I Maity, A Follmann, PP Patel, ... Cities 131, 103919 2022 Citations: 46
Study of doubly strange systems using stored antiprotons B Singh, W Erni, B Krusche, M Steinacher, N Walford, B Liu, H Liu, Z Liu, ... Nuclear Physics A 954, 323-340 2016 Citations: 44
Coastal dilemma: climate change, public assistance and population displacement S Dasgupta, D Wheeler, S Bandyopadhyay, S Ghosh, U Roy World Development 150, 105707 2022 Citations: 39
Changes in densities of waterbird species in Santragachi Lake, India: potential effects on limnochemical variables US Roy, AR Goswami, A Aich, SK Mukhopadhyay Zoological Studies 50 (1), 76-84 2011 Citations: 38
Design and optimization of parity generator and parity checker based on quantum-dot cellular automata S Santra, U Roy World Academy of Science, Engineering and Technology, International Journal 2014 Citations: 36
Design and implementation of quantum cellular automata based novel adder circuits S Santra, U Roy International Journal of Computer, Electrical, Automation, Control and 2014 Citations: 36
Comparison of avifaunal diversity in and around Neora valley national park, West Bengal, India US Roy, A Pal, P Banerjee, SK Mukhopadhyay Journal of Threatened Taxa, 2136-2142 2011 Citations: 36
Characterization of brinjal (Solanum melongena L.) germplasm P Hazra, A Rout, U Roy, S Nath, T Roy, R Dutta, S Acharya, AK Mondal Veg. Sci 30 (2), 145-149 2003 Citations: 34
A systematic literature review on latest keystroke dynamics based models S Roy, J Pradhan, A Kumar, DRD Adhikary, U Roy, D Sinha, RK Pal IEEE Access 10, 92192-92236 2022 Citations: 30
Discriminative HMM training with GA for handwritten word recognition TK Bhowmik, SK Parui, U Roy 2008 19th International conference on pattern recognition, 1-4 2008 Citations: 30
SWGMM: a semi-wrapped Gaussian mixture model for clustering of circular–linear data A Roy, SK Parui, U Roy Pattern Analysis and Applications 19, 631-645 2016 Citations: 29
Metallothionein as a biomarker to assess the effects of pollution on Indian Major carp species from wastewater-fed fishponds of East Calcutta wetlands (a Ramsar Site) US Roy, B Chattopadhyay, S Datta, SK Mukhopadhyay Environmental Research, Engineering and Management 58 (4), 10-17 2011 Citations: 29