Title :
CH-SIFT: A local kernel color histogram SIFT based descriptor
Author :
Jalilvand, Ali ; Boroujeni, Hamidreza Shayegh ; Charkari, Masrollah Moghadam
Author_Institution :
Fac. of Electr. & Comput. Eng., Tarbiat Modares Univ., Tehran, Iran
Abstract :
This paper presents a novel method for extracting distinctive invariant features from color images that can be used to perform reliable matching between different views of an object or scene. The features are invariant to image scale and rotation, and also to illumination changes because of using a color kernel histogram descriptor incorporating with a classic SIFT descriptor. The method is compared with SIFT, SURF and CSIFT and is shown that the accuracy of proposed method is better than others by testing all of them on the ALOI database.
Keywords :
feature extraction; image colour analysis; image matching; ALOI database; CH-SIFT descriptor; color image; feature extraction; illumination change; image rotation; image scale; local kernel color histogram descriptor; object matching; scene matching; Color; Colored noise; Detectors; Feature extraction; Histograms; Image color analysis; Kernel; SIFT descriptor; color image matching; key point matching; local kernel hostogram;
Conference_Titel :
Multimedia Technology (ICMT), 2011 International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-61284-771-9
DOI :
10.1109/ICMT.2011.6001949
