期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2012
卷号：3
期号：6
页码：5326-5330
出版社：TechScience Publications
摘要：Content Based Image Retrieval’s play a dominant role in Image Retrieval’s based on some features specified within the image. Content Based Image Retrieval’s are very much useful in situations like crime detection where the identification of criminal can be done using the contents (Biometric features) of the accused. In this methodology we formulate the features using Generalized Gaussian Mixture Model. K-Means algorithm is utilized to cluster the images basing on criteria. In order to demonstrate the methodology a huge database of images are formulated and the performance of the developed method is measured using metrics like PSNR, MSE. The developed methodology is also tested with the Berkley Images.
关键词：Content Based Image Retrieval’s play a dominant role;in Image Retrieval’s based on some features specified within the;image. Content Based Image Retrieval’s are very much useful in;situations like crime detection where the identification of;criminal can be done using the contents (Biometric features) of;the accused. In this methodology we formulate the features;using Generalized Gaussian Mixture Model. K-Means algorithm;is utilized to cluster the images basing on criteria. In order to;demonstrate the methodology a huge database of images are;formulated and the performance of the developed method is;measured using metrics like PSNR; MSE. The developed;methodology is also tested with the Berkley Images.
