Demonstration venue · read-only. Every page can be browsed; the buttons that would change it are switched off. Create an account to run TaxoReview on your own data. A simulation from public publication records: the people listed were not invited and did not agree to review.
? Tutorial for this page

Sadali N. Jayaramamurthy

dblp:27/2894 · DBLP profile ↗
← Back
4ranked-venue papers
0as first author
0since 2021 · last 1988
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 2Systems, architecture and hardware · 2

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
1 paper
Segmentation and scene understanding · 33% Trustworthy machine learning · 33% Knowledge representation and reasoning · 33%
Computer architecture, parallel and distributed computing, and storage systems
1 paper
Parallel and multicore computing · 100%

Topics — the 4 heaviest of 4, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Knowledge, reasoning and agents › Knowledge representation and reasoning › uncertainty reasoning
fuzzy sets
0.011986
Representation of Uncertainty in Computer Vision Using Fuzzy Sets · IEEE Trans. Computers 1986
Computer vision › Segmentation and scene understanding
scene understanding
0.011986
Representation of Uncertainty in Computer Vision Using Fuzzy Sets · IEEE Trans. Computers 1986
Machine learning › Trustworthy machine learning
uncertainty modeling
0.011986
Representation of Uncertainty in Computer Vision Using Fuzzy Sets · IEEE Trans. Computers 1986
Parallel and multicore computing › array processor
parallel array processor
0.011972
Automatic Generation of Texture Feature Detectors · IEEE Trans. Computers 1972

Methods — techniques the papers use, named apart from their topics

fuzzy sets · 0.0mccormick-michalski pattern recognition method · 0.0interval generation · 0.0
YearPublicationVenuePosition
1988 Determination of the optic flow field in the presence of occlusion
Terrance L. Huntsberger, Sadali N. Jayaramamurthy
Pattern Recognit. Lett.2
1987 Determination of the optic flow field using the spatiotemporal deformation of region properties
Terrance L. Huntsberger, Sadali N. Jayaramamurthy
Pattern Recognit. Lett.2
1986 Representation of Uncertainty in Computer Vision Using Fuzzy Sets
abstract
Uncertainty in computer vision can arise at various levels. It can occur in the low level in the raw sensor input, and extends all the way through intermediate and higher levels. Ideally, at any level where decisions are being made on the basis of previous processing steps, a computer vision system must have sufficient flexibility for representation of uncertainty in any of these levels.
Terrance L. Huntsberger, Chandraleka Rangarajan, Sadali N. Jayaramamurthy
IEEE Trans. Computers3
1972 Automatic Generation of Texture Feature Detectors
abstract
This correspondence is an informal exposition on a method of pattern recognition recently introduced by McCormick and Michalski. The method, described here by means of a simple example and a biological application, provides mechanized generation of an optimum set of "intervals" which can be interpreted as local position-invariant digital operations for use in picture filtering with a parallel array processor.
John S. Read, Sadali N. Jayaramamurthy
IEEE Trans. Computers2