K
K. P. Soman
Researcher at Amrita Vishwa Vidyapeetham
Publications - 504
Citations - 8779
K. P. Soman is an academic researcher from Amrita Vishwa Vidyapeetham. The author has contributed to research in topics: Deep learning & Support vector machine. The author has an hindex of 32, co-authored 489 publications receiving 5773 citations. Previous affiliations of K. P. Soman include Indian Institute of Technology Kharagpur & Indian Institutes of Technology.
Papers
More filters
Proceedings ArticleDOI
A Comparative Analysis of Total Variation and Least Square Based Hyperspectral Image Denoising Methods
TL;DR: In this article, the spectral least square (LS) weighted regularization in spectral domain with spatial least square and total variation (TV) denoising techniques were compared on real, and noise simulated hyperspectral image datasets.
Journal ArticleDOI
A Data-driven Technique for Harmonics Monitoring in Emerging Power Grids using Noise-aware Dynamic Mode Decomposition
Neethu Mohan,K. P. Soman +1 more
Journal Article
Active Contour based Document Image Segmentation and Restoration using Split-Bregman and Edge Enhancement Diffusion
TL;DR: This paper presents PDE based document image segmentation and restoration approach using active contours, non-linear diffusion and split-bregman algorithm to clean document images, taken from DIBCO 2009 image dataset.
Proceedings Article
AMRITA@ FIRE-2014: Morpheme Extraction for Tamil using Machine Learning (Working notes)
TL;DR: In this article, the authors presented the working methodology of supervised Morpheme Extraction Task for Tamil language in MET Task of FIRE-2014 and extracted Tamil Morphemes are extracted based on supervised machine learning algorithm, Support vector machines.
Book ChapterDOI
A Novel Cyclic Convolution Based Regularization Method for Power-Line Interference Removal in ECG Signal
TL;DR: The present paper proposes a novel PLI removal method that uses a simple optimization method involving a circular convolution based \({\ell _2}\)-norm regularization and is found to be state-of-the-art.