I
Ishwar K. Sethi
Researcher at University of Rochester
Publications - 154
Citations - 5178
Ishwar K. Sethi is an academic researcher from University of Rochester. The author has contributed to research in topics: Feature detection (computer vision) & Artificial neural network. The author has an hindex of 33, co-authored 153 publications receiving 5012 citations. Previous affiliations of Ishwar K. Sethi include Oakland University & Wayne State University.
Papers
More filters
Proceedings ArticleDOI
Direct feature extraction from compressed images
Bo Shen,Ishwar K. Sethi +1 more
TL;DR: This paper considers the detection of areas of interest and edges in images compressed using the discrete cosine transform (DCT) and shows how a measure based on certain DCT coefficients of a block can provide an indication of underlying activity.
Journal ArticleDOI
Machine recognition of constrained hand printed devanagari
Ishwar K. Sethi,B. Chatterjee +1 more
TL;DR: A method is presented for the machine recognition of constrained, hand printed Devanagari characters, where each stage of decision making narrows down the choice regarding the class membership of the input token.
Journal ArticleDOI
Thresholding based on histogram approximation
TL;DR: The authors propose two automatic threshold-selection schemes, based on functional approximation of the histogram, which give better results than the former one, at a small extra computational cost.
Proceedings ArticleDOI
Audio characterization for video indexing
Nilesh V. Patel,Ishwar K. Sethi +1 more
TL;DR: The potential of audio information for content characterization is examined by demonstrating the extraction of widely used features in audio processing directly from compressed data stream and their application to video clip classification.
Proceedings ArticleDOI
Mining association rules between low-level image features and high-level concepts
TL;DR: In this paper, the authors present two approaches to automatic image annotation, by finding those rules underlying the links between the low-level features and the high-level concepts associated with images One scheme uses global color image information and classification tree based techniques through this supervised learning approach they are able to identify relationships between global color-based image features and some textual decriptors.