Adjacency Matrix Based Objects Representation for Human Identification in Images

Author

Saravanakumar, S. ; Vadivel, A.

Author_Institution

Dept. of Comput. Applic., Nat. Inst. of Technol., Tiruchirappalli, India

fYear

2009

fDate

27-28 Oct. 2009

Firstpage

172

Lastpage

174

Abstract

In this paper the human object present in images are identified. K-means clustering algorithm is used for segmenting the images and Connected Component Analysis is used as post-processing step. Initially, templates are created from human posture in idle and various angles. The adjacency matrix is constructed from objects and it is matched with templates. A similarity measure has been proposed for estimating the matching.

Keywords

graph theory; image classification; image matching; image representation; image segmentation; matrix algebra; adjacency matrix; adjacency matrix based objects representation; connected component analysis; human images identification; human posture; images matching; images segmentation; k-means clustering algorithm; Algorithm design and analysis; Biological system modeling; Clustering algorithms; Communications technology; Computer applications; Data mining; Humans; Image analysis; Image segmentation; Surveillance;

fLanguage

English

Publisher

ieee

Conference_Titel

Advances in Recent Technologies in Communication and Computing, 2009. ARTCom '09. International Conference on

Conference_Location

Kottayam, Kerala

Print_ISBN

978-1-4244-5104-3

Electronic_ISBN

978-0-7695-3845-7

Type

conf

DOI

10.1109/ARTCom.2009.70

Filename

5327886