Title :
Yet Rapid ICA: Applications to un-indexed image-to-image retrieval
Author :
Yokote, Ryota ; Matsuyama, Yasuo
Author_Institution :
Dept. of Comput. Sci. & Eng., Waseda Univ., Tokyo, Japan
Abstract :
A faster algorithm of ICA is devised. This method utilizes multi-step past information with the existing fixed-point method. The use of past information comes from the idea of surrogate optimization. The speed and implemented software are checked for both simulated and read data. The presented ICA, named Rapid ICA, is applied to image-to-image retrieval without indices. Images judged to be similar reflected user´s opinion well.
Keywords :
image retrieval; independent component analysis; optimisation; fixed-point method; image-to-image retrieval; multistep past information; surrogate optimization; unindexed image-to-image retrieval; yet rapid ICA; Convergence; Data models; Equations; Image processing; Mathematical model; Measurement uncertainty; Oscillators;
Conference_Titel :
Neural Networks (IJCNN), The 2010 International Joint Conference on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-6916-1
DOI :
10.1109/IJCNN.2010.5596895
