Image Interpretation Based On Similarity Measures of Visual Content Descriptors
An Insight, Mungamuru Nirmala, Sreedhar Appalabatla, Raja Adeel Ahmed · 2011
Efficient and effective retrieval techniques of images are desired because of the explosive growth of digital images. Content based image retrieval is promising approach because of its automatic indexing and retrieval based on their semantic features and visual appearance. Interest in the potential of digital images has increased enormously over the last few years. Content-Based Image Retrieval (CBIR) is desirable because most webs based image search engines rely purely on the meta-data which produces lot of garbage in the result. In the content-based image retrieval, the search is based on the similarity of the content of the images such as color, texture and shape. However, a picture is worth thousand words. Image contents are much more versatile compared with text, and the amount of visual data is already enormous and still expanding very rapidly. Most content based image retrieval systems focus on overall and qualitative similarity of scenes. Conventional information retrieval is based solely on text, and these approaches to textual information retrieval have been transplanted into image retrieval in variety of ways, including the representation of an image as vector of feature values. By measuring the similarity between image in the database and the query image using similarity measure, one can retrieve the image. This paper describes Content-Based Image Retrieval methods using visual content descriptors.