Privacy Protecting Trademark Identification System Using Cloud

2101 Words9 Pages
Privacy Preserving Trademark Identification System using Cloud 1. Introduction Content-Based Information Retrieval (CBIR) is the field that constitutes representation of images, organizing and searching of images based on their content rather than annotations of image. CBIR, also known as query by image content and content-based visual information retrieval (CBVIR) is the application of computer vision techniques to the image retrieval problem, that is, the matter of checking out digital pictures in massive databases. "Content-based" implies that the search analyzes the contents of the image based not on keywords, descriptions related to image, tags or annotations but based on features extracted directly from the image data. The term…show more content…
Images with higher similarity than threshold are returned as an output. System which uses the content of the object for Information Retrieval is the CBIR. There are many applications of Content Based Information Retrieval. Image retrieval is one of the applications of CBIR. Few applications of CBIR are art collections, architectural and engineering design, crime prevention, Defense, Face detection etc. Mostly CBIR is applied on the Multimedia data. CBIR faces some problems. The trouble with the technique is the issue of high dimensionality. With the increase in the dimensionality CBIR becomes time consuming system and highly computation bound. Also with variety of applications of CBIR, there is need to preserve the privacy of user interest. A. Need of the Privacy Preservation in CBIR Privacy can be outlined as “The quality of being secluded from the presence or view of others”. In CBIR user provides some Multimedia object (e.g. an image of trademark to check whether the same trademark is already exist or not) as query and system provides required results. During this process system must realize the similarity between user query and objects in the database. At this time system gets the user query and query reveals the content and interest of the user and here is the privacy leak in the system. Here the original trademark can be compromised or can be copied. Generally CBIR is multi-party system, in which there are minimum 2 parties, User and
Open Document