In various areas of government, academia, hospitals and commerce large collections of digital images are produced. Many of these collections are the merchandise of digitizing existing collections of analogue drawings, photographs, paintings and prints. Generally the only way of searching these collections was by basically browsing or keyword indexing. Digital images databases however, open the way to content-based searching. Content Based Image Retrieval (CBIR) is concerned with the retrieval of images similar to a specified image, from an image repository. Content Based Image Retrieval (CBIR) is an efficient retrieval of relevant images from large databases based on features extracted from the image. This paper proposes a system that can be used for retrieving images related to a query image from a large set of distinct images. It follows an image segmentation based approach to extract the different features present in an image. The above features which can be stored in vectors called feature vectors and therefore these are compared to the feature vectors of query image and the image information is sorted in decreasing order of similarity. The processing of the same is done on cloud. The CBIR system is an application built on Windows Azure platform. It is a parallel processing problem where a large set of images have to be operated upon to rank them based on a similarity to a provided query image by the user. Numerous instances of the algorithm run on the virtual machines provided in the Microsoft data centers, which run Windows Azure. Windows Azure Stack is the operating system for the cloud by Microsoft Incorporation. Windows azure Stack is responsible for creating ideal hybrid architecture.
Meena, M., Singh, A. R., & Bharadi, V. A. (2016). Architecture for Software as a Service (SaaS) Model of CBIR on Hybrid Cloud of Microsoft Azure. In Procedia Computer Science (Vol. 79, pp. 569–578). Elsevier B.V. https://doi.org/10.1016/j.procs.2016.03.072