Mridul Ghosh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Mridul Ghosh has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Sk Md Obaidullah
Aliah University
13 shared publications - Kaushik Roy
West Bengal State University
11 shared publications - Himadri Mukherjee
West Bengal State University
5 shared publications Sk Md Obaidullah
Aliah University
5 shared publicationsKaushik Roy
West Bengal State University
4 shared publications- Mária Ždímalová
Department of Mathematics and Descriptive Geometry , Slovak University of Technology in Bratislava , Bratislava , Slovakia
4 shared publications
Latest Publications
- 2 July 2026
- Published by Springer Nature
- p. 144-159
Bio-Physical Representation Learning for Plant Disease Classification
- 2 July 2026
- Published by Springer Nature
- p. 144-159
Bio-Physical Representation Learning for Plant Disease Classification
- Open Access
- 22 April 2026
- Published by Walter de Gruyter GmbH in Tatra Mountains Mathematical Publications
Langevin Resonance Transformer for Cross-Script Writer Identification
Vision Transformers (ViTs) have emerged as a powerful architecture for various computer vision tasks, including writer identification. However, like their CNN counterparts, they are susceptible to performance degradation in cross-script scenarios because their standard self-attention mechanism learns script-specific visual correlations. To overcome this, we propose a novel architecture, the Langevin Resonance Transformer (LRT). The LRT fundamentally redefines self-attention by replacing the abstract mathematical operation with a physically-grounded dynamic simulation. Each image patch is treated as a particle. The core of the LRT is a novel Langevin Attention Layer, where the interaction between pairs of particles is governed by a learnable potential energy function. The net force on each particle is aggregated from all other particles, and its state is evolved according to the Langevin equation, which models motion under both deterministic and stochastic forces. The LRT treats a writer’s style as a physical system defined by an energy landscape. Because it models biomechanics rather than just visual shapes, the resulting representation works regardless of the script. We tested this on the BRS-ID dataset using a custom augmentation strategy. The results show that LRT achieves higher accuracy than standard Vision Transformers and other top-tier models on the cross-script identification task.
- 22 April 2026
- Published by Walter de Gruyter GmbH in Tatra Mountains Mathematical Publications
Open AccessLangevin Resonance Transformer for Cross-Script Writer Identification
Vision Transformers (ViTs) have emerged as a powerful architecture for various computer vision tasks, including writer identification. However, like their CNN counterparts, they are susceptible to performance degradation in cross-script scenarios because their standard self-attention mechanism learns script-specific visual correlations. To overcome this, we propose a novel architecture, the Langevin Resonance Transformer (LRT). The LRT fundamentally redefines self-attention by replacing the abstract mathematical operation with a physically-grounded dynamic simulation. Each image patch is treated as a particle. The core of the LRT is a novel Langevin Attention Layer, where the interaction between pairs of particles is governed by a learnable potential energy function. The net force on each particle is aggregated from all other particles, and its state is evolved according to the Langevin equation, which models motion under both deterministic and stochastic forces. The LRT treats a writer’s style as a physical system defined by an energy landscape. Because it models biomechanics rather than just visual shapes, the resulting representation works regardless of the script. We tested this on the BRS-ID dataset using a custom augmentation strategy. The results show that LRT achieves higher accuracy than standard Vision Transformers and other top-tier models on the cross-script identification task.
- Open Access
- 17 March 2026
- Published by Walter de Gruyter GmbH in Tatra Mountains Mathematical Publications
Contextualized Vision Transformers (CVT): Adaptive Spectral Embedding and Feature Gating for Precise Text-Graphics Classification
The accurate classification of images into graphics-only, text-only, and mixed-content categories is a critical prerequisite for building efficient, content-aware processing pipelines. This initial triage prevents the unnecessary application of computationally expensive operations, such as Optical Character Recognition (OCR), to irrelevant graphical data. To address this challenge, we introduce the Contextualized Vision Transformer (CVT), a novel architecture designed specifically for this nuanced classification task. The CVT addresses the limitations of standard Vision Transformers (ViTs) through three synergistic components. It employs a Learnable Patch Decomposition (LPD) strategy that efficiently extracts patch embeddings. To model complex spatial arrangements, it introduces an Adaptive Spectral Embedding (ASE) module, which replaces static positional encodings with a dynamic, learnable representation. Crucially, a Contextual Feature Gating (CFG) module enhances feature discriminability by adaptively recalibrating patch-level features, selectively amplifying the salient text or graphic regions. Comprehensive K-fold cross-validation demonstrates the robustness and generalizability of the proposed model. The CVT achieves statistically significant improvements in accuracy, precision, and recall compared to state-of-the-art Vision Transformer baselines. Experimental results highlight the effectiveness of this architecture in providing a fast and accurate solution for the vital task of content triage in large-scale visual processing systems.
- 17 March 2026
- Published by Walter de Gruyter GmbH in Tatra Mountains Mathematical Publications
Open AccessContextualized Vision Transformers (CVT): Adaptive Spectral Embedding and Feature Gating for Precise Text-Graphics Classification
The accurate classification of images into graphics-only, text-only, and mixed-content categories is a critical prerequisite for building efficient, content-aware processing pipelines. This initial triage prevents the unnecessary application of computationally expensive operations, such as Optical Character Recognition (OCR), to irrelevant graphical data. To address this challenge, we introduce the Contextualized Vision Transformer (CVT), a novel architecture designed specifically for this nuanced classification task. The CVT addresses the limitations of standard Vision Transformers (ViTs) through three synergistic components. It employs a Learnable Patch Decomposition (LPD) strategy that efficiently extracts patch embeddings. To model complex spatial arrangements, it introduces an Adaptive Spectral Embedding (ASE) module, which replaces static positional encodings with a dynamic, learnable representation. Crucially, a Contextual Feature Gating (CFG) module enhances feature discriminability by adaptively recalibrating patch-level features, selectively amplifying the salient text or graphic regions. Comprehensive K-fold cross-validation demonstrates the robustness and generalizability of the proposed model. The CVT achieves statistically significant improvements in accuracy, precision, and recall compared to state-of-the-art Vision Transformer baselines. Experimental results highlight the effectiveness of this architecture in providing a fast and accurate solution for the vital task of content triage in large-scale visual processing systems.
- 13 July 2025
- Published by Springer Nature
- p. 45-55
Writer Identification Using Cross-Script Signature Images
- 13 July 2025
- Published by Springer Nature
- p. 45-55
Writer Identification Using Cross-Script Signature Images
- 27 February 2025
- Published by Springer Nature
- p. 173-184
SWFEM: Sparse Weighted Fine-Tuned Ensemble Model for Leaf Disease Detection
- 27 February 2025
- Published by Springer Nature
- p. 173-184
SWFEM: Sparse Weighted Fine-Tuned Ensemble Model for Leaf Disease Detection
- Open Access
- 13 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 8189-8202
BrownViTNet: Hybrid CNN-Vision Transformer Model for the Classification of Brownfields in Aerial Imagery
The identification of brownfield sites through satellite imagery is a crucial yet challenging classification problem in the field of remote sensing applications. In this study, we leverage aerial images sourced from Google Maps, Bing Maps, and national aerial and satellite imagery (DOP20), focusing on three distinct land use classes: active areas, construction sites, and brownfields, all matched across the same geographical coordinates. Our dataset initially includes images set against a 1000 × 1000 pixel blank canvas, often resulting in a significant portion of unused black space. To optimize this, images were cropped based on a threshold ensuring a minimum height and width of 400 pixels, resulting in a substantial reduction of the dataset by 42.8% for active areas, 65.93% for construction areas, and 75.86% for brownfield images. Given the reduced size of our usable dataset, we employed single-image super-resolution to enhance image quality and effectively double our dataset size as a augmentation part of training data. For model architecture, the initial four layers consist of a convolutional neural network (CNN), followed by intermediate layers using a vision transformer with a patch size of 16. This novel hybrid architecture of brownfield vision transformer network demonstrated impressive accuracy in the classification of brownfields from satellite imagery, presenting a significant advance in the use of machine learning for environmental monitoring and urban planning.
- 13 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 8189-8202
Open AccessBrownViTNet: Hybrid CNN-Vision Transformer Model for the Classification of Brownfields in Aerial Imagery
The identification of brownfield sites through satellite imagery is a crucial yet challenging classification problem in the field of remote sensing applications. In this study, we leverage aerial images sourced from Google Maps, Bing Maps, and national aerial and satellite imagery (DOP20), focusing on three distinct land use classes: active areas, construction sites, and brownfields, all matched across the same geographical coordinates. Our dataset initially includes images set against a 1000 × 1000 pixel blank canvas, often resulting in a significant portion of unused black space. To optimize this, images were cropped based on a threshold ensuring a minimum height and width of 400 pixels, resulting in a substantial reduction of the dataset by 42.8% for active areas, 65.93% for construction areas, and 75.86% for brownfield images. Given the reduced size of our usable dataset, we employed single-image super-resolution to enhance image quality and effectively double our dataset size as a augmentation part of training data. For model architecture, the initial four layers consist of a convolutional neural network (CNN), followed by intermediate layers using a vision transformer with a patch size of 16. This novel hybrid architecture of brownfield vision transformer network demonstrated impressive accuracy in the classification of brownfields from satellite imagery, presenting a significant advance in the use of machine learning for environmental monitoring and urban planning.
- 12 February 2025
- Published by Springer Nature
- p. 107-119
Skin Cancer Detection Using a Deep-Learning Based Framework
- 12 February 2025
- Published by Springer Nature
- p. 107-119
Skin Cancer Detection Using a Deep-Learning Based Framework
- 6 December 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (18) , 54545-54568
MOPO-HBT: A movie poster dataset for title extraction and recognition
- 6 December 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (18) , 54545-54568
MOPO-HBT: A movie poster dataset for title extraction and recognition
- 15 November 2023
- Published by Springer Nature
- p. 39-50
Plant Disease Detection and Classification Using a Deep Learning-Based Framework
- 15 November 2023
- Published by Springer Nature
- p. 39-50
Plant Disease Detection and Classification Using a Deep Learning-Based Framework
- 18 June 2023
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 56 (12) , 15301-15373
Scene text understanding: recapitulating the past decade
- 18 June 2023
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 56 (12) , 15301-15373
Scene text understanding: recapitulating the past decade