Reduction of semantic gap using relevance feedback technique in image retrieval system

2014 ◽  
Author(s):  
Ansa Saju ◽  
I. Thusnavis Bella Mary ◽  
A. Vasuki ◽  
P. S. Lakshmi
Keyword(s):  
Image Retrieval ◽  
Relevance Feedback ◽  
Retrieval System ◽  
Semantic Gap ◽  
Image Retrieval System

scholarly journals CONTENT BASED IMAGE RETRIEVAL SYSTEM BY FUSION OF COLOR, TEXTURE AND EDGE FEATURES WITH SVM CLASSIFIER AND RELEVANCE FEEDBACK

2018 ◽  
Vol 6 (9) ◽  
pp. 259-273
Author(s):  
Priyanka Saxena ◽  
Shefali
Keyword(s):  
Image Retrieval ◽  
Relevance Feedback ◽  
Retrieval System ◽  
Semantic Gap ◽  
Content Based Image Retrieval ◽  
Visual Features ◽  
Image Retrieval System ◽  
Combined Features ◽  
Edge Features ◽  
Color Texture

Content Based Image Retrieval system automatically retrieves the most relevant images to the query image by extracting the visual features instead of keywords from images. Over the years, several researches have been conducted in this field but the system still faces the challenge of semantic gap and subjectivity of human perception. This paper proposes the extraction of low-level visual features by employing color moment, Local Binary Pattern and Canny Edge Detection techniques for extracting color, texture and edge features respectively. The combination of these features is used in conjunction with Support Vector Machine to reduce the retrieval time and improve the overall precision. Also, the challenge of semantic gap between low and high level features is addressed by incorporating Relevance Feedback. Average precision value of 0.782 was obtained by combining the color, texture and edge features, 0.896 was obtained by using combined features with SVM, 0.882 was obtained by using combined features with Relevance Feedback to overcome the challenge of semantic gap. Experimental results exhibit improved performance than other state of the art techniques.

A Content-Based Image Retrieval System with Image Semantic

2010 ◽  
Vol 159 ◽  
pp. 638-643
Author(s):  
Ying Ma ◽  
Lao Mo Zhang ◽  
Jin Xing Ma
Keyword(s):  
Image Retrieval ◽  
Relevance Feedback ◽  
Retrieval System ◽  
Fingerprint Recognition ◽  
Semantic Gap ◽  
Visual Features ◽  
Multimedia Technology ◽  
Retrieval Systems ◽  
Image Retrieval System ◽  
Object Ontology

With the development of information technology and multimedia technology, more and more images appear and have become a part of our daily life. Efficient image searching, storing, retrieval and browsing tools are in high need in various domains, including face and fingerprint recognition, publishing, medicine, architecture, remote sensing, fashion etc. Thus, many image retrieval systems have been developed to meet the need. The aim of content-based retrieval systems is to provide maximum support in bridging the semantic gap between the simplicity of available visual features and the richness of the user semantics. In this paper, we discuss the main technologies for reducing the semantic gap, namely, object-ontology, machine learning, relevance feedback.

Fuzzy Relevance Feedback in Image Retrieval for Color Feature Using Query Vector Modification Method

2010 ◽  
Vol 14 (1) ◽  
pp. 34-38 ◽  
Author(s):  
M. Rahmat Widyanto ◽  
◽  
Tatik Maftukhah ◽  
Keyword(s):  
Image Retrieval ◽  
Relevance Feedback ◽  
Euclidean Distance ◽  
Retrieval System ◽  
User Feedback ◽  
Image Similarity ◽  
Modification Method ◽  
Image Retrieval System ◽  
Membership Value ◽  
Image Computation

Fuzzy relevance feedback using Query Vector Modification (QVM) method in image retrieval is proposed. For feedback, the proposed six relevance levels are: “very relevant”, “relevant”, “few relevant”, “vague”, “not relevant”, and “very non relevant”. For computation of user feedback result, QVM method is proposed. The QVM method repeatedly reformulates the query vector through user feedback. The system derives the image similarity by computing the Euclidean distance, and computation of color parameter value by Red, Green, and Blue (RGB) color model. Five steps for fuzzy relevance feedback are: image similarity, output image, computation of membership value, feedback computation, and feedback result. Experiments used QVM method for six relevance levels. Fuzzy relevance feedback using QVM method gives higher precision value than conventional relevance feedback method. Experimental results show that the precision value improved by 28.56% and recall value improved 3.2% of conventional relevance feedback. That indicated performance Image Retrieval System can be improved by fuzzy relevance feedback using QVM method.

Sign in / Sign up

Export Citation Format

Share Document