Natural object classification using artificial neural networks

Author

Singh, Sameer ; Markou, Markos ; Haddon, John

Author_Institution

PANN Res., Exeter Univ., UK

Volume

3

fYear

2000

fDate

2000

Firstpage

139

Abstract

In this paper we apply artificial neural networks for classifying texture data of various natural objects found in FLIR images. Hermite functions are used for texture feature extraction from segmented regions of interest in natural scenes taken as a video sequence. A total of 2680 samples for a total of twelve different classes are used for object recognition. The results on correctly identifying twelve natural objects in scenes are compared across ten folds of the cross-validation study. Neural networks are found to be extremely effective in robust classification of our data giving an average recognition rate of 91.8%

Keywords

Hermitian matrices; image classification; image sequences; image texture; infrared imaging; neural nets; object recognition; video signal processing; FLIR images; Hermite functions; artificial neural networks; natural object classification; object recognition; segmented regions; texture data classification; texture feature extraction; video sequence; Artificial neural networks; Feature extraction; Image analysis; Image segmentation; Image texture analysis; Layout; Neural networks; Object recognition; Performance analysis; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on

Conference_Location

Como

ISSN

1098-7576

Print_ISBN

0-7695-0619-4

Type

conf

DOI

10.1109/IJCNN.2000.861294

Filename

861294