arXiv subjects

Ratul Chakraborty

Publications and source records attributed to Ratul Chakraborty.

3 recordsLinked to original sources

arXiv2025

Poisson Informed Retinex Network for Extreme Low-Light Image Enhancement

Low-light image denoising and enhancement are challenging, especially when traditional noise assumptions, such as Gaussian noise, do not hold in majority. In many real-world scenarios, such as low-light imaging, noise is signal-dependent and is better represented as Poisson noise. In this work, we address the problem of denoising images degraded by Poisson noise under extreme low-light conditions. We introduce a light-weight deep learning-based method that integrates Retinex based decomposition with Poisson denoising into a unified encoder-decoder network. The model simultaneously enhances illumination and suppresses noise by incorporating a Poisson denoising loss to address signal-dependent noise. Without prior requirement for reflectance and illumination, the network learns an effective decomposition process while ensuring consistent reflectance and smooth illumination without causing any form of color distortion. The experimental results demonstrate the effectiveness and practicality of the proposed low-light illumination enhancement method. Our method significantly improves visibility and brightness in low-light conditions, while preserving image structure and color constancy under ambient illumination.

eess.IV↗

arXiv2024

Knot-detection algorithm to measure viscosity in three-dimensional MHD plasmas

This project explores the mathematical study of knots and links in topology, focusing on differentiating between the two-component Unlink and the Hopf Link using a computational tool named LINKAGE. LINKAGE employs the linking number, calculated through Barycentric Equations, Matrix Algebra, and basic topological principles, to quantify the degree of linking between two closed curves in three-dimensional space. This approach not only distinguishes between different knot structures but also has applications in understanding complex systems such as magnetic field lines in plasma physics. Additionally, this project includes an example where multiple interlinked loops were analyzed over different time stamps using the LINKAGE algorithm. By observing how these links break and evolve, the algorithm demonstrates its ability to track changes in the topological properties of the system. This dynamic analysis shows the versatility of the tool in studying evolving systems, where the topology of the components can change, providing valuable information about the underlying physical processes driving these changes.

physics.plasm-ph↗

arXiv2023

Unsupervised Learning of Molecular Embeddings for Enhanced Clustering and Emergent Properties for Chemical Compounds

The detailed analysis of molecular structures and properties holds great potential for drug development discovery through machine learning. Developing an emergent property in the model to understand molecules would broaden the horizons for development with a new computational tool. We introduce various methods to detect and cluster chemical compounds based on their SMILES data. Our first method, analyzing the graphical structures of chemical compounds using embedding data, employs vector search to meet our threshold value. The results yielded pronounced, concentrated clusters, and the method produced favorable results in querying and understanding the compounds. We also used natural language description embeddings stored in a vector database with GPT3.5, which outperforms the base model. Thus, we introduce a similarity search and clustering algorithm to aid in searching for and interacting with molecules, enhancing efficiency in chemical exploration and enabling future development of emergent properties in molecular property prediction models.

physics.chem-ph↗