The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off


Objective: To study pattern recognition and retrieval in machine vision system application. Methods/Analysis: Regular and irregular pattern recognition algorithm based on sorting of radii from centre of mass is used and other tools such as Matlab, Neural networks. Findings: The radii from centre of mass to contour of the pattern are computed and sorted in descending order. Few top radii are taken for recognition of the given pattern. As the radii are sorted in descending order, therefore, if the pattern is orientated at any angle, the top order radii are same. This enables the pattern recognition at any orientation. Further, the radii are normalized with respect to their mean radius to make them size invariant. In addition, area, perimeter and euler number are also computed for enhancing the uniqueness degree in features vector set.

Keywords

CBIR, Extraction, Normalization, NN.
User