期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2011
卷号：2
期号：3
页码：1336-1341
出版社：TechScience Publications
摘要：Image processing is any form of signal processing for which the input is an image, such as a photograph or video frame; the output of image processing may be either an image or, a set of characteristics or parameters related to the image.In this paper, symbolic images are represented in the form of symbolic image database (SID) which is an invariant to image transformations and this SID is used for advanced match retrieval of queried images. The conventional pair-wise spatial relationships (9DLT matrix) approach is not robust as that of image invariant transformations. For invariant image transformations, a new concept called advanced direction of reference is introduced which preserved by a set of triples and they are represented by using principal component analysis (PCA). The problem of using principal component transformation is that it produces identical principal component vectors (PCV)s even for different images which consumes additional memory. In our methodology a distinct and unique key is computed for each distinct triple. The mean and standard deviation of the set of keys are computed for a symbolic image and stored along with the total number of keys as the representatives of the same object image. The proposed advanced match retrieval design is based on a binary search technique and, thus, requires O(log n) search time in the worst case, where n is the total number of symbolic images in the symbolic image database. Images acquired through any modern sensors consist of variety of noises, resulting from stochastic variations and deterministic distortions or shading. In order to extract image data, smoothing algorithms should be applied initially to reduce noises before further analysis and processing. We empirically analyzed with our software tool and also got the favorable results.
