In this paper, we study the feasibility of scene attributes as the intermediate scene representation for automatic image captioning, tag predicting and semantic image search. we show that when used as features for these tasks, low dimensional scene attributes can compete with or improve on the state of art performance. In particular, we propose a new method of content-based image retrieval, whi...

The principles of content-based image retrieval (CBIR) are now well-established, with a continuing flow of publications exploring various aspects of the technology. Practical applications receive rather less attention and few fully-developed instances have been described. In this paper, we review the remarks made by other authors that led us to believe that it was important to investigate what ...

Scene content understanding facilitates a large number of applications, ranging from content-based image retrieval to other multimedia applications. Material detection refers to the problem of identifying key semantic material types (such as sky, grass, foliage, water, and snow in images. In this paper, we present a holistic approach to determining scene content, based on a set of individual ma...

Visual information is becoming more important and at a rapid rate. However, creators and users are reluctant to annotate visual content making it difficult to search these collections. Content-based image retrieval (CBIR) techniques extract visual descriptors directly from image data and can hence be used in situations where textual information is not available. In this paper, we give a brief i...

In a color-spatial retrieval technique, the color information is integrated with the knowledge of the colors’ spatial distribution to facilitate content-based image retrieval. Several techniques have been proposed in the literature, but these works have been developed independently without much comparison. In this paper, we present a preliminary evaluation of three such colorspatial retrieval t...

In a typical content-based image retrieval (CBIR) system, query result is a set of images sorted by feature similarities with respect to the query. We introduce a new approach to CBIR result representation. We propose that CBIR system should retrieve image clusters, which elements should be sorted by the most meaningful feature similarities. Actually, this paper does not present a full approach...

In this paper we describe the problem of content-based image retrieval (CBIR) and apply Bayesian and decision theory methodology to develop a CBIR system. This is evaluated using the idea of target testing. Comments on the performance of the system, and how it might be extended, are given. Then we propose a decision theory solution to the problem of identifying sets of images to show the user o...

We study solutions to the problem of evaluating image similarity in the context of content-based image retrieval (CBIR). Retrieval is formulated as a classification problem, where the goal is to minimize probability of retrieval error. It is shown that this formulation establishes a common ground for comparing similarity functions, exposes assumptions hidden behind most of the ones in common us...

One of the content based image retrieval techniques is the shape based technique which allows users to ask for objects similar in shape to a query object. We propose a novel method for shape representation and similarity measure which we call the grid based method and evaluate its performance by comparing it with two popular methods, namely, the Fourier descriptors method and the moment invaria...

Content-based image retrieval has become one of the most active research areas in the past few years. In this paper various methodologies used in the research area of Content Based Image Retrieval techniques using Relevance Feedback are discussed. The comparison and analysis of these methods is done. Relevance feedback techniques were incorporated into Content-based image retrieval for obtainin...