Content Based Image Retrieval System Using Relevance Feedback

Abstract

Content based image retrieval (CBIR) is the basis of image retrieval systems. Image retrieval based on image content has become an interesting topic in the field of image processing. To be more profitable, relevance feedback techniques were introduced into CBIR such that more precise results can be obtained by taking user’s feedbacks. However, existing relevance feedback based CBIR methods usually request a number of iterative feedbacks to produce refined search results, especially in a large-scale image database. To achieve the high efficiency and effectiveness of CBIR we are using two type of methods for feature extraction like SVM (support vector machine) and NPRF (navigation-pattern based relevance feedback). By using SVM classifier as a category predictor of query and database images, they are exploited at first to filter out irrelevant images by its different low-level, concept and key point-based features. In terms of effectiveness, the search algorithm makes use of the discovered navigation patterns and three kinds of query refinement strategies, Query Point Movement (QPM), Query Reweighting (QR), and Query Expansion (QEX) to convert the search space toward the user’s intention effectively. By using these methods, high quality of image retrieval on RF can be achieved in a small number of feedbacks.

Authors and Affiliations

Aboli U. Deshmukh

Keywords

Related Articles

The Prevelence of Dyslipidemia among Postmenopausal Women in Bangalore (Urban Area)

Objectives: Dyslipidemia is a key independent modifiable risk factor for Cardiovascular Disease. This study was designed to investigate the current epidemiological features of dyslipidemia among postmenopausal women in B...

Analyzing Vernacular Sustainable Design Principles- A Case Study of a Vernacular Dwelling in Godavari Region of Andhra Pradesh, India

Hundreds of years of experience, self-learning and traditional wisdom has led to the development of contextual based traditional architecture. Vernacular style of architecture developed using locally available material,...

Web Operating System

Web based operating system consists of some improved set of applications needed for the future enhancement. We aim on the current attention towards the web operating systems. As we know that the existing operating system...

Simulation and Speed Control of Induction Motor Using Fuzzy Logic PID Controller

Three phase induction motor drives have various industrial applications. In this thesis work indirect vector control technique is used which is based upon the Fuzzy PID speed controller. This method of speed control usin...

The Holocaust in the Making: A theoretical Treatise of the Nazi Pogrom and its Relation with Rationality, Modernity and Bureaucracy

The paper is basically a review of the relation between the Nazi pogrom during the Second World War and the foundational elements of modernity, namely rationality and bureaucracy through three scholars. The materialisati...

Download PDF file
  • EP ID EP241032
  • DOI -
  • Views 112
  • Downloads 0

How To Cite

Aboli U. Deshmukh (2015). Content Based Image Retrieval System Using Relevance Feedback. International journal of Emerging Trends in Science and Technology, 2(6), 2689-2693. https://www.europub.co.uk/articles/-A-241032