Robust and Radial Image Comparison Using Reverse Image Search
Journal Ijmer, M. G. Kavitha, E. Gurumoorthi · 2014
This paper proposed a robust, radial and effective content-based image retrieval (CBIR) or query by image content (QBIC) or content based visual information retrieval (CBVIR) approach, which is based on colour, texture and shape features. Due to the enormous increase in image database sizes, as well as its vast deployment in various applications, the need for CBIR development arose. In this proposed approach, image attributes like image name, keywords and meta data are not used to compute image similarity and image retrieval. So, concept based image retrieval is not used. If an image is given as an input query and the output is based on the input image query, it is called as reverse image search. So, images can be searched based on their contents (pixels) but not by their keywords. It is difficult to measure image content similarity due to visual changes caused by varying viewpoint and environment. In this paper, a simple and efficient method to effectively measure the content similarity from image measurements is proposed. The proposed approach is based on the three well-known algorithms: colour histogram, texture and moment invariants. It ensures that the proposed image retrieval approach produces results which are highly relevant to the content of an image query, by taking into account the three distinct features of the image and similarity metrics based on Euclidean measure. Colour histogram is used to extract the colour features of an image. Gabor filter is used to extract the texture features and the moment invariant is used to extract the