Cover Image

Shape matching and object recognition using dissimilarity measures with Hungarian algorithm

Organized by School of Mechatronic Engineering (UniMAP) & co-organized by The Institution of Engineering Malaysia (IEM), 11th - 13th October 2009 at Batu Feringhi, Penang, Malaysia.

Saved in:
Bibliographic Details
Main Authors: Chitra, D., Manigandan, T., Devarajan, N.
Other Authors: chitram@kongu.ac.in
Format: Working Paper
Language:English
Published: Universiti Malaysia Perlis 2009
Subjects:
Shape
Object recognition
Euclidean
Hungarian Algorithm
MPEG
Image processing > Digital techniques
Image processing
Online Access:http://dspace.unimap.edu.my/xmlui/handle/123456789/7270
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-7270
record_format dspace
spelling my.unimap-72702010-01-18T07:48:23Z Shape matching and object recognition using dissimilarity measures with Hungarian algorithm Chitra, D. Manigandan, T. Devarajan, N. chitram@kongu.ac.in Shape Object recognition Euclidean Hungarian Algorithm MPEG Image processing -- Digital techniques Image processing Organized by School of Mechatronic Engineering (UniMAP) & co-organized by The Institution of Engineering Malaysia (IEM), 11th - 13th October 2009 at Batu Feringhi, Penang, Malaysia. The shape of an object is very important in object recognition. Shape matching is a challenging problem, especially when articulation and deformation of a part occur. These variations may be insignificant for human recognition but often cause a matching algorithm to give results that are inconsistent with our perception. In this paper, we propose an approach to measure similarity between shapes using dissimilarity measures with Hungarian algorithm. In our framework, the measurement of similarity is preceded by (1) forming the shapes from the images using canny edge detection (2) finding correspondence between shapes of the two images using Euclidean distance and cost matrix (3) reducing the cost by using bipartite graph matching with Hungarian algorithm. Corresponding points on two dissimilar shapes will have similar distance, enabling us to solve an optimal assignment problem using the correspondence points. Given the point correspondence, we estimate the transformation that best aligns the two shapes; regularized thin plate splines provide a flexible class of transformation maps for this purpose. The dissimilarity between the two shapes is computed as a sum of matching error between corresponding points, together with a term measuring the magnitude of the aligning transform. By using this matching error, we can classify different objects. Results are presented and compared with existing methods using MATLAB for MNIST hand written digits and MPEG7 images. 2009-11-13T01:58:21Z 2009-11-13T01:58:21Z 2009-10-11 Working Paper p.1B7 1 - 1B7 6 http://hdl.handle.net/123456789/7270 en Proceedings of the International Conference on Man-Machine Systems (ICoMMS 2009) Universiti Malaysia Perlis
institution Universiti Malaysia Perlis
building UniMAP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Perlis
content_source UniMAP Library Digital Repository
url_provider http://dspace.unimap.edu.my/
language English
topic Shape
Object recognition
Euclidean
Hungarian Algorithm
MPEG
Image processing -- Digital techniques
Image processing
spellingShingle Shape
Object recognition
Euclidean
Hungarian Algorithm
MPEG
Image processing -- Digital techniques
Image processing
Chitra, D.
Manigandan, T.
Devarajan, N.
Shape matching and object recognition using dissimilarity measures with Hungarian algorithm
description Organized by School of Mechatronic Engineering (UniMAP) & co-organized by The Institution of Engineering Malaysia (IEM), 11th - 13th October 2009 at Batu Feringhi, Penang, Malaysia.
author2 chitram@kongu.ac.in
author_facet chitram@kongu.ac.in
Chitra, D.
Manigandan, T.
Devarajan, N.
format Working Paper
author Chitra, D.
Manigandan, T.
Devarajan, N.
author_sort Chitra, D.
title Shape matching and object recognition using dissimilarity measures with Hungarian algorithm
title_short Shape matching and object recognition using dissimilarity measures with Hungarian algorithm
title_full Shape matching and object recognition using dissimilarity measures with Hungarian algorithm
title_fullStr Shape matching and object recognition using dissimilarity measures with Hungarian algorithm
title_full_unstemmed Shape matching and object recognition using dissimilarity measures with Hungarian algorithm
title_sort shape matching and object recognition using dissimilarity measures with hungarian algorithm
publisher Universiti Malaysia Perlis
publishDate 2009
url http://dspace.unimap.edu.my/xmlui/handle/123456789/7270
_version_ 1643788743955447808
score 13.226497

Similar Items