期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：11
DOI：10.15680/IJIRCCE.2015.0311042
出版社：S&S Publications
摘要：Content based Image Retrieval (CBIR) has been a widely researched topic over the last decades and theinaccurate retrieval of relevant images with respect to the given query image is one of its main challenges. The implicitform of image retrieval has been receiving much attention in the last few years as it is useful in Human ComputerInteraction (HCI). But its research is limited by the cost effective specialized devices. Thus this paper mainly focuseson a content based image retrieval which avoids the need of those kinds of devices. This is carried out by capturinguser’s gaze using a webcam, followed by a Bag of Words (BoW) methodology for performing the CBIR. The Gazecapturing is done by displaying images in an interface and then the gaze feature is extracted from the captured imagewhich depends on number of times the user’s gaze lies at a particular image. Thus the proposed work constitutes a lesscomplex method for gaze tracking using a webcam. The CBIR is done by extracting low level features from image andrepresenting it using BoW model. The WANG DB, a general purpose database which contains 1000 images is used forthe testing purposes.
