Intelligent image analysis using adaptive resource-allocating network

K M Lee; W N Street

doi:10.1109/NNSP.2001.943140

Back

Conference proceeding

Intelligent image analysis using adaptive resource-allocating network

K M Lee and W N Street

NEURAL NETWORKS FOR SIGNAL PROCESSING XI, pp.363-372

01/01/2001

DOI: 10.1109/NNSP.2001.943140

View Online

Abstract

This paper presents a unified image analysis approach for object detection, segmentation, and classification using an adaptive resource-allocating network (ARAN), which is based on using unsupervised learning to cluster shapes and supervised learning to classify objects. The proposed neural network is incrementally grown by adjusting the clusters, and by creating a new cluster whenever an unusual shape is presented. Each hidden node represents a cluster, with centers and widths of the hidden nodes used as templates to provide faster and more accurate object detection and segmentation. On-line learning gives the system improved performance with continued use. The effectiveness of the resulting system is demonstrated on the task of diagnosing breast cancer.

Computer Science

Computer Science, Artificial Intelligence

Engineering

Engineering, Electrical & Electronic

Mathematics

Mathematics, Applied

Physical Sciences

Science & Technology

Statistics & Probability

Technology

Details

Title: Subtitle: Intelligent image analysis using adaptive resource-allocating network
Creators: K M Lee - University of Iowa
W N Street
Contributors: D J Miller (Editor)
T Adali (Editor)
J Larsen (Editor)
M VanHulle (Editor)
S Douglas (Editor)
Resource Type: Conference proceeding
Publication Details: NEURAL NETWORKS FOR SIGNAL PROCESSING XI, pp.363-372
Publisher: IEEE
DOI: 10.1109/NNSP.2001.943140
ISSN: 1089-3555
eISSN: 2379-2329
Number of pages: 10
Language: English
Date published: 01/01/2001
Academic Unit: Bus Admin College; Nursing; Computer Science; Business Analytics
Record Identifier: 9984380380302771

Metrics

3 Record Views