DocumentCode :
2144169
Title :
A New Data Transformation Method Based on Adaptive Binarization for Bag-of-Features Model
Author :
Cheng, Gang ; Wang, Chunheng ; Xiao, Baihua ; Jiang, Aiwen
Author_Institution :
Key Lab. of Complex Syst. & Intell., Chinese Acad. of Sci., Beijing, China
fYear :
2009
fDate :
17-19 Oct. 2009
Firstpage :
1
Lastpage :
5
Abstract :
Visual object categorization has gained more and more attention in computer vision and bag-of-features model has become an important approach to form an object categorization system. As for image feature representation, "continuous valued" histogram that records frequency of each visual word and "binarized value" histogram that records only absence/presence of each visual word are commonly used in bag-of-features model. In this paper, we utilize the merits of both representations and propose a scheme to use adaptive binarization method to transform "continuous valued" histogram to "binarized value" histogram. Experiments on "The PASCAL Visual Object Classes Challenge 2006" show that this data transformation approach improves the performance of object categorization system.
Keywords :
computer vision; image classification; PASCAL Visual Object Classes Challenge 2006; adaptive binarization; bag-of-features model; binarized value histogram; computer vision; continuous valued histogram; data transformation method; image feature representation; visual object categorization; Binary codes; Computer vision; Detectors; Feature extraction; Frequency; Histograms; Image segmentation; Lighting; Object detection; Vocabulary;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image and Signal Processing, 2009. CISP '09. 2nd International Congress on
Conference_Location :
Tianjin
Print_ISBN :
978-1-4244-4129-7
Electronic_ISBN :
978-1-4244-4131-0
Type :
conf
DOI :
10.1109/CISP.2009.5303676
Filename :
5303676
Link To Document :
بازگشت