Shape Recognition and Retrieval Using String of Symbols

Author

Daliri, Mohammad Reza ; Torre, Vincent

Author_Institution

SISSA, Trieste

fYear

2006

fDate

Dec. 2006

Firstpage

101

Lastpage

108

Abstract

In this paper we present two algorithms for shape recognition. Both algorithms map the contour of the shape to be recognized into a string of symbols. The first algorithm is based on supervised learning using string kernels as often used for text categorization and classification. The second algorithm is very weakly supervised and is based on the procrustes analysis and on the edit distance used for computing the similarity between strings of symbols. The second algorithm correctly recognizes 98.29% of shapes from the MPEG-7 database, i.e. better than any previous algorithms. The second algorithm is able also to retrieve similar shapes from a database

Keywords

computer vision; image classification; image retrieval; learning (artificial intelligence); object recognition; visual databases; MPEG-7 database; edit distance; procrustes analysis; shape recognition; shape retrieval; string kernel; supervised learning; text categorization; text classification; Algorithm design and analysis; Classification algorithms; Kernel; MPEG 7 Standard; Object recognition; Shape measurement; Supervised learning; Testing; Text categorization; Visual databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Applications, 2006. ICMLA '06. 5th International Conference on

Conference_Location

Orlando, FL

Print_ISBN

0-7695-2735-3

Type

conf

DOI

10.1109/ICMLA.2006.48

Filename

4041477