Title :
Image reduction for object recognition
Author :
Shaick, Ben-Zion ; Yaroslavsky, Leonid
Author_Institution :
Fac. of Eng., Tel Aviv Univ., Israel
Abstract :
The problem addressed is that of the fast generation of accurate multiple downscaled copies of an input image, with an arbitrary non-integer reduction factor, for object detection and recognition. Three algorithms that can be implemented in parallel, recursive and hybrid architectures are introduced and compared in terms of their accuracy and computational complexity. It is shown that the recursive algorithm is the most advantageous in terms of computational complexity, while the parallel algorithm performs better in terms of accuracy reduction. The hybrid algorithm combines advantages of both.
Keywords :
image reconstruction; image sampling; object detection; object recognition; parallel architectures; arbitrary reduction factor; computational complexity; hybrid architecture; image reduction; image resampling algorithms; object detection; object recognition; parallel architecture; recursive architecture; Computational complexity; Computer architecture; Image processing; Image recognition; Interpolation; Kernel; Nonlinear filters; Object detection; Object recognition; Table lookup;
Conference_Titel :
Video/Image Processing and Multimedia Communications 4th EURASIP-IEEE Region 8 International Symposium on VIPromCom
Print_ISBN :
953-7044-01-7
DOI :
10.1109/VIPROM.2002.1026678