Semantic-based image retrieval is the desired target of Content-based image retrieval (CBIR). In this paper, we proposed a new method to extract semantic information for CBIR using the relevance feedback results. Firstly it is assumed that positive and negative examples in relevant feedback are containing semantic content added by users. Then image internal semantic model (IISM) is proposed to ...

In this paper we present image data representation, similarity image retrieval, the architecture of a generic content-based image retrieval system, and different content-based image retrieval systems.

We present a framework for active learning in the multiple-instance (MI) setting. In an MI learning problem, instances are naturally organized into bags and it is the bags, instead of individual instances, that are labeled for training. MI learners assume that every instance in a bag labeled negative is actually negative, whereas at least one instance in a bag labeled positive is actually posit...

Content-based image retrieval from large multimedia databases effectively and efficiently is a challenging task. In this paper, we propose a retrieval technique that utilizes the regional properties of the images. After image segmentation, each region is represented by its colour, shape, size, and spatial position. Regions of different images are matched and a distance measure between the whole...

In this paper a prototype system is described for the management and content-based retrieval of defect images in huge image databases. This is a real problem in surface inspection applications, since modern inspection systems may produce up to thousands of defect images in a day. The retrieval is based on shape and internal structure characteristics of defects, so no manual labeling nor annotat...

This article provides a framework to describe and compare content-based image retrieval systems. Sixteen contemporary systems are described in detail, in terms of the following technical aspects: querying, relevance feedback, result presentation, features, and matching. For a total of 44 systems we list the features that are used. Of these systems, 35 use any kind of color features, 28 use text...

CWI’s experiments investigate the usefulness of clickthrough data for improving the diversity of image retrieval results. We use the search logs provided to us by Belga to find relevant images; we consider that these correspond to images clicked for queries exactly matching or best matching a topic’s title and cluster titles. To reduce the noise, we also filter these results and only consider t...

Relevance feedback methods for content-based image retrieval have shown promise in a variety of image database applications. These techniques assume two-class relevance feedback: relevant and irrelevant classes. While simple computationally, two-class relevance feedback often becomes inadequate in providing sufficient information to help rapidly improve retrieval performance. In this paper we p...

A new method for content-based image retrieval is being presented. This method uses a vector-space model to represent images in a multi-dimensional space. This model allows the use of multiple attributes in the retrieval process and also identiies the most selective values for each attribute. Therefore by ignoring the less signiicant values the user can reduce the dimensionality of the feature ...

This paper considered performance of content based image retrieval system using image representation nonparametric algorithms. Performance comparison of Epanechnikov, Gaussian and Histogram non-parametric algorithms was done in a generic image retrieval system. Chan & Vese and Cosine Angle Distance algorithms were used for segmentation and similarity matching respectively. The performance of th...