DocumentCode
245536
Title
Object recognition using bag of words with kernels for big data
Author
Cheyu Wu ; Ching-Te Chiu ; Yar-Sun Hsu
Author_Institution
Dept. of Electr. Eng., Nat. Tsing Hua Univ., Hsinchu, Taiwan
fYear
2014
fDate
26-28 May 2014
Firstpage
89
Lastpage
90
Abstract
Scale Invariant Feature Transform (SIFT) descriptor can represent the object in detail, and is robust to variations due to image scaling and illumination changes. The challenge of using such descriptor to perform image retrieval in a large scale database is the high computational complexity. In this paper, we present the bag of words model combined with SIFT to reduce the computation cost. The average precision we get is about 30%.
Keywords
Big Data; computational complexity; image retrieval; object recognition; transforms; Big Data; SIFT descriptor; bag-of-words model; computation cost reduction; computational complexity; illumination change; image retrieval; image scaling change; kernels; large scale database; object recognition; object representation; scale invariant feature transform descriptor; Big data; Computational modeling; Feature extraction; Image retrieval; Object recognition; Training; Visualization;
fLanguage
English
Publisher
ieee
Conference_Titel
Consumer Electronics - Taiwan (ICCE-TW), 2014 IEEE International Conference on
Conference_Location
Taipei
Type
conf
DOI
10.1109/ICCE-TW.2014.6904114
Filename
6904114
Link To Document