期刊名称：Signal & Image Processing : An International Journal (SIPIJ)
印刷版ISSN：2229-3922
电子版ISSN：0976-710X
出版年度：2013
卷号：4
期号：6
页码：103
出版社：Academy & Industry Research Collaboration Center (AIRCC)
摘要：This paper proposes a new method for image/object retrieval. A pre-processing technique is applied todescribe the object, in one dimensional representation, as a pseudo time series. The proposed algorithmdevelops the modified versions of the SAX representation: applies an approach called Extended SAX(ESAX) in order to realize efficient and accurate discovering of important patterns, necessary for retrievingthe most plausible similar objects. Our approach depends upon a table contains the break-points thatdivide a Gaussian distribution in an arbitrary number of equiprobable regions. Each breakpoint has morethan one cardinality. A distance measure is used to decide the most plausible matching between strings ofsymbolic words. The experimental results have shown that our approach improves detection accuracy.
关键词：1-D representation of objects; Symbolic Aggregate approXimation(SAX); Shape number; Time series;Extended SAX representation
