DocumentCode :
3449701
Title :
Combining feature descriptors for efficient classification and recognition of images
Author :
Roy, Kaushik ; Subrahmanya, G. ; Rao, V.R.K.
Author_Institution :
Cognizant Technol. Solutions, Chennai, India
fYear :
2012
fDate :
16-18 Oct. 2012
Firstpage :
420
Lastpage :
424
Abstract :
This work proposes an efficient method for classification and recognition in images based on combination of local feature descriptors and shape descriptors. This method outperforms the existing methods which are based on using only local feature matching or shape descriptors for classification and recognition in images. The proposed method makes use of matching detected local features in images as well as the shape feature within the image.
Keywords :
feature extraction; image recognition; shape recognition; feature descriptors; image classification; image recognition; local feature matching; shape descriptors; shape feature; Computer vision; Databases; Feature extraction; Image color analysis; Image edge detection; Shape; feature; fourier; keypoint; recognition; repeatability; surf;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image and Signal Processing (CISP), 2012 5th International Congress on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4673-0965-3
Type :
conf
DOI :
10.1109/CISP.2012.6470022
Filename :
6470022
Link To Document :
بازگشت