Title :
Feature Extraction and Matching for Plant Images
Author :
Wang, Peizhen ; Shi, Lei ; Dong, Hengzhi
Author_Institution :
Sch. of Electr. Eng. & Inf., Anhui Univ. of Technol., Ma´´an shan, China
Abstract :
In this paper, some improvements, including the pyramid frame in image scale space, key point locating method for the SIFT (scale invariant feature transform) algorithm, are developed. In view of the characteristic of plant images, the calculating strategy is also improved. With the improved SIFT algorithm, features in plant images are effectively extracted, and matched with BBF (Best Bin First) algorithm. By matching features extracted from 70 couples of plant images under different illuminate, shadow and focus, the proposed method has been verified to be efficient, and with the improved algorithm the computing time is saved.
Keywords :
feature extraction; image matching; Best Bin First algorithm; feature extraction; image scale space; key point locating method; plant image matching; pyramid frame; scale invariant feature transform; Computational intelligence; Computer vision; Feature extraction; Image matching; Image recognition; Information security; Layout; Lighting; Physics; Space technology; feature extraction; matching; plant image; scale invariant feature transform;
Conference_Titel :
Computational Intelligence and Security, 2009. CIS '09. International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4244-5411-2
DOI :
10.1109/CIS.2009.247
