Hybrid Wavelet Based CBIR System Using Software as a Service (SaaS) Model on Public Cloud

摘要

CBIR system is widely used for various commercial and official purposes, where image comparison is required, to fulfill business requirements like geographical information, medical diagnosis, security, authenticity, etc. The main functionality of the CBIR application, in which the image is inserted as query, is to extract the visual property of image and save it for future comparison. The problem involved with the standalone architecture is that the system has to perform multiple operations of feature vector extraction, enrollment and verification. Also any failure occur at any point may cause the whole system down. With the increase in the number of users for such application, we need a scalable solution for such application so the system can be modified based on the user requirements. In this paper, we are going to propose a highly scalable, pluggable and faster cloud based CBIR system, which is capable to store, process and extract and operate large number of images. System can be scalable based on the storage and processing requirements.