DocumentCode :
599038
Title :
An experimental comparison of localization accuracy of affine region detectors
Author :
Xiaoming Li ; Yunying Yang
Author_Institution :
Dept. of Comput. Sci. & Technol., Taiyuan Univ. of Sci. & Technol., Taiyuan, China
fYear :
2012
fDate :
16-18 Oct. 2012
Firstpage :
411
Lastpage :
414
Abstract :
Previous comparison about localization accuracy of affine region detectors is focused on the overlap error between corresponding regions, which is not sufficient for some applications such as wide baseline matching, registration, structure from motion etc., in which localization accuracy in position is especially important. In this paper, we make a experimental comparison about the localization accuracy of position of CGR(Center of Gravity of Region) of the detected corresponding regions on a set of test images under varying conditions. Three methods of the state of the art in affine region detectors are included: MSER, Hessians Affine and Harris Affine. This comparison is complementary with previous similar work. The performance is measured against changes in viewpoint, scale, illumination, defocus and image compression.
Keywords :
computer vision; data compression; feature extraction; image coding; image matching; image registration; lighting; object detection; CGR; Harris affine; Hessians affine; MSER; affine region detectors; center-of-gravity-of-region; computer vision; defocus; feature detection; illumination; image compression; localization accuracy; overlap error; pattern recognition; scale; structure-from-motion; viewpoint; wide baseline matching; wide baseline registration; Accuracy; Computer vision; Detectors; Educational institutions; Feature extraction; Image coding; Lighting; affine region detectors; invariant feature; localization accuracy; performance;
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.2012.6470015
Filename :
6470015
Link To Document :
بازگشت