A neural-network-based approach to detecting rectangular objects

Mu Chun Su, Chao Hsin Hung

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

Many man-made objects are composed of a number of some simple geometric shapes such as lines, circles, rectangles, etc. Therefore, the detection of rectangular objects is an important issue to some practical applications such as the detection of buildings and vehicles in aerial imagery, the detection of license plates in car images, etc. Several methods have been proposed for solving the problem of the detection of rectangular objects. While some approaches are based on the detecting lines, some approaches are based on the Hough transform. Each approach has its own advantages and disadvantages (e.g., computational load). In this paper, we propose a class of neural networks with a special type of neural junctions for the detection of rectangular objects. The proposed neural networks can be trained in either an unsupervised mode or a batch mode. In contrast to some popular clustering algorithms such as the fuzzy c-means algorithm and the fuzzy c-rectangular shells algorithm, our approach is not based on minimizing an objective function but based on the idea of competitive learning. Based on the idea of competitive learning, the computational load can be decreased. Several data sets were tested to illustrate the effectiveness of our proposed approach.

Original languageEnglish
Pages (from-to)270-283
Number of pages14
JournalNeurocomputing
Volume71
Issue number1-3
DOIs
StatePublished - Dec 2007

Keywords

  • Cluster analysis
  • Clustering algorithm
  • Detection of rectangles
  • Neural networks

Fingerprint

Dive into the research topics of 'A neural-network-based approach to detecting rectangular objects'. Together they form a unique fingerprint.

Cite this