A FRAMEWORK OF CONTENT-BASED WEB IMAGE SEARCH ENGINE USING MAPREDUCE

Image-R3 is an enabled content based image retrieval system. It also can be used to web based large-scale image search by integrating with Google Hadoop project. With the development and popularization of cloud computing, more and more researchers from different research areas do research with the help of cloud computing. Nowadays content-based image retrieval as one of the challenging and emerging technologies is high computation task because of the algorithm computation complexity and web based large-scale data from internet. As based on Hadoop infrastructure, IMAGE-R3 is easy to extent and flexible for deployment. As an open source project, Image-R3 can be improved on demand and integrated to other existing systems. In this paper global descriptors from MPEG7, local descriptor SIFT and Compact Composite Descriptors are used for image retrieval from the Wang data collection for our Image-R3 search engine system evaluation.