Application of Convolutional Neural Network for Content Based Image Retrieval
Rahul M.Bhutada
Department of Computer Science & Engineering, Shri Sant Gajanan Maharaj College of Engineering, SGBAU University, Shegaon,India , IN
Prof.V. S.Mahalle
Department of Computer Science & Engineering, Shri Sant Gajanan Maharaj College of Engineering, SGBAU University, Shegaon,India , IN
Keywords: CBIR, CNN, Features, Image Retrieval, Classification, Neural Network
Abstract
The problem is to extract the image features that represent the image contents in a database. Such kind of extraction requires a evaluation of retrieval performance of features of image. Related work is the foundation for understanding and improving more knowledge regarding precise field. This paper proposes Content Based Image Retrieval via Convolutional neural network. Content Based Image Retrieval is a technique for extracting features of images like color, shape, texture, blob detection, edge detection, contour detection and etc. That sort of work of extracting features from image will be done by convolutional neural network here. Once features are extracted from a query image then same procedure will be used for extracting features of database images. For comparing features of both images Euclidian distance can be used to produce the best result. The key part of retrieval system is feature extraction. Until now, the only way of penetrating these collections was based on keyword indexing, text, or just by browsing. In this paper we survey some practical aspect of current CBIR texture, and shape for exact and efficient CBIR after doing the study of related works.
How to Cite
References
NA