Title :
Matching day and night location images using SIFT and logistic regression
Author :
Tekin, Nazli ; Peker, Kadir A.
Author_Institution :
Bilgisayar Muhendisligi Bolumu, Meliksah Univ., Kayseri, Turkey
Abstract :
SIFT is use for matching images of location and objects or recognizing objects on an image. the method can handle light varying conditions at some points. However the degree of success decreases when we try to match images of locations taken at day to until night time period. Especially matching between day time image and night time image is not successful. We examined how to performance of SIFT method diminish with the change of daylight The other method classification used in matching problem is also examined and compared with SIFT.
Keywords :
image matching; image retrieval; transforms; SIFT; image matching; image recognition; location images; logistic regression; Computer vision; Image matching; Image recognition; Logistics; Robot sensing systems; Transforms; SIFT; day and night image matching; image matching; image retrieval; local descriptors; logistic regression;
Conference_Titel :
Signal Processing and Communications Applications Conference (SIU), 2015 23th
Conference_Location :
Malatya
DOI :
10.1109/SIU.2015.7130159