Analyzing images containing multiple sparse patterns with neural networks

Rangachari Anand; Kishan Mehrotra; Chilukuri K. Mohan; Sanjay Ranka

doi:10.1016/0031-3203(93)90026-S

Analyzing images containing multiple sparse patterns with neural networks

Rangachari Anand, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

Department of Electrical Engineering & Computer Science

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

The problem of analyzing images containing multiple sparse overlapped patterns is addressed. This problem arises naturally when analyzing the composition of organic macromolecules using data gathered from their NMR spectra. Using a neural network approach, excellent results are obtained in using NMR data to analyze the presence of various amino acids in protein molecules. High correct classification percentages (about 87%) are achieved for images containing as many as five substantially distorted overlapping patterns.

Original language	English (US)
Pages (from-to)	1717-1724
Number of pages	8
Journal	Pattern Recognition
Volume	26
Issue number	11
DOIs	https://doi.org/10.1016/0031-3203(93)90026-S
State	Published - Nov 1993

Keywords

Clustering
Neural networks
Nuclear Magnetic Resonance
Overlapping patterns
Sparse image analysis

ASJC Scopus subject areas

Software
Signal Processing
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.1016/0031-3203(93)90026-S

Cite this

@article{6ac94167902f43b18402eb96f7d285a4,

title = "Analyzing images containing multiple sparse patterns with neural networks",

abstract = "The problem of analyzing images containing multiple sparse overlapped patterns is addressed. This problem arises naturally when analyzing the composition of organic macromolecules using data gathered from their NMR spectra. Using a neural network approach, excellent results are obtained in using NMR data to analyze the presence of various amino acids in protein molecules. High correct classification percentages (about 87%) are achieved for images containing as many as five substantially distorted overlapping patterns.",

keywords = "Clustering, Neural networks, Nuclear Magnetic Resonance, Overlapping patterns, Sparse image analysis",

author = "Rangachari Anand and Kishan Mehrotra and Mohan, {Chilukuri K.} and Sanjay Ranka",

note = "Funding Information: Acknowledgments--Wthea nk Sandor Szalmaa nd Istvan Pelczeor ft heN MR Data ProcessinLga boratoryC,h emistry DepartmenSty, racusUe niversityf,o rd escribintgh ep roblem and providingd ata.T he researcho f Dr SanjayR ankawas supporteidn part by NSF grantC CR-9110812.",

year = "1993",

month = nov,

doi = "10.1016/0031-3203(93)90026-S",

language = "English (US)",

volume = "26",

pages = "1717--1724",

journal = "Pattern Recognition",

issn = "0031-3203",

publisher = "Elsevier",

number = "11",

}

TY - JOUR

T1 - Analyzing images containing multiple sparse patterns with neural networks

AU - Anand, Rangachari

AU - Mehrotra, Kishan

AU - Mohan, Chilukuri K.

AU - Ranka, Sanjay

N1 - Funding Information: Acknowledgments--Wthea nk Sandor Szalmaa nd Istvan Pelczeor ft heN MR Data ProcessinLga boratoryC,h emistry DepartmenSty, racusUe niversityf,o rd escribintgh ep roblem and providingd ata.T he researcho f Dr SanjayR ankawas supporteidn part by NSF grantC CR-9110812.

PY - 1993/11

Y1 - 1993/11

N2 - The problem of analyzing images containing multiple sparse overlapped patterns is addressed. This problem arises naturally when analyzing the composition of organic macromolecules using data gathered from their NMR spectra. Using a neural network approach, excellent results are obtained in using NMR data to analyze the presence of various amino acids in protein molecules. High correct classification percentages (about 87%) are achieved for images containing as many as five substantially distorted overlapping patterns.

AB - The problem of analyzing images containing multiple sparse overlapped patterns is addressed. This problem arises naturally when analyzing the composition of organic macromolecules using data gathered from their NMR spectra. Using a neural network approach, excellent results are obtained in using NMR data to analyze the presence of various amino acids in protein molecules. High correct classification percentages (about 87%) are achieved for images containing as many as five substantially distorted overlapping patterns.

KW - Clustering

KW - Neural networks

KW - Nuclear Magnetic Resonance

KW - Overlapping patterns

KW - Sparse image analysis

UR - http://www.scopus.com/inward/record.url?scp=0027701266&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027701266&partnerID=8YFLogxK

U2 - 10.1016/0031-3203(93)90026-S

DO - 10.1016/0031-3203(93)90026-S

M3 - Article

AN - SCOPUS:0027701266

SN - 0031-3203

VL - 26

SP - 1717

EP - 1724

JO - Pattern Recognition

JF - Pattern Recognition

IS - 11

ER -

Analyzing images containing multiple sparse patterns with neural networks

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this