S
S. Valli
Researcher at College of Engineering, Guindy
Publications - 24
Citations - 219
S. Valli is an academic researcher from College of Engineering, Guindy. The author has contributed to research in topics: Rekeying & Multicast. The author has an hindex of 7, co-authored 22 publications receiving 150 citations. Previous affiliations of S. Valli include Anna University.
Papers
More filters
A Survey on Content Based Image Retrieval
TL;DR: This survey covers approaches used for extracting low level features; various distance measures for measuring the similarity of images, the mechanisms for reducing the semantic gap and about invariant image retrieval.
Proceedings ArticleDOI
Findings of the Shared Task on Speech Recognition for Vulnerable Individuals in Tamil
TL;DR: Different results using different pre-trained transformer models are discussed in this overview of the shared task on automatic speech recognition in the Tamillanguage.
Journal ArticleDOI
An algorithm for multi-sensor image fusion using maximum a posteriori and nonsubsampled contourlet transform ☆
D. Anandhi,S. Valli +1 more
TL;DR: The proposed fusion algorithm based on Synthetic Aperture Radar and Panchromatic images in Nonsubsampled Contourlet Transform (NSCT) domain outperforms the existing NSCT methods by preserving maximum features.
Posted Content
Ontology Based Query Expansion Using Word Sense Disambiguation
M. Barathi,S. Valli +1 more
TL;DR: This work is based on Word sense disambiguation, thesaurus WordNet and ontology of any domain for retrieving information in order to capture the context of particular concept(s) and discover semantic relationships between them.
Journal ArticleDOI
An enhanced text detection technique for the visually impaired to read text
S. P. Faustina Joan,S. Valli +1 more
TL;DR: An enhanced text detection technique (ETDT), which is expected to aid the visually impaired to overcome their reading challenges, and a new text feature, Shapeness Score is proposed, which significantly identifies text regions when combined with the other features based on morphology and stroke widths.