Title :
SIFT-based object recognition with fast alphabet creation and reduced curse of dimensionality
Author :
Stommel, Martin ; Herzog, Otthein
Author_Institution :
TZI Center for Comput. & Commun. Technol., Univ. Bremen, Bremen, Germany
Abstract :
This article presents a SIFT-based object recognition method that avoids the typical problems of time-consuming code-book generation and curse of dimensionality in feature comparison. The first problem is solved by using an alphabet of completely synthetic feature vectors. The second problem is solved by using the Hamming-distance on binarised SIFT-features. The method is supported by competitive results on the Graz´02 image data base.
Keywords :
Hamming codes; feature extraction; image coding; object recognition; Hamming-distance; SIFT-based object recognition; fast alphabet creation; time-consuming code-book generation; Books; Boosting; Clustering methods; Communications technology; Computational efficiency; Computer vision; Histograms; Image processing; Object recognition; Prototypes;
Conference_Titel :
Image and Vision Computing New Zealand, 2009. IVCNZ '09. 24th International Conference
Conference_Location :
Wellington
Print_ISBN :
978-1-4244-4697-1
Electronic_ISBN :
2151-2205
DOI :
10.1109/IVCNZ.2009.5378422
