An intelligent on-line system for content based image retrieval
23 Sep 1999-pp 273-277
TL;DR: The paper presents the extension of the CBIR system for multiple queries such as "many blue and few green" and a number of experiments using the online system are conducted and the results are included and discussed in the paper.
Abstract: We propose an intelligent content based image retrieval system and it is an extension of a previously published research paper (S. Kulkarni et al., 1999), where a neuro-fuzzy technique was presented. The CBIR system will accept multiple queries as input such as "mostly red and many blue and few green" that can be provided online and the outputs of the system are the images with their confidential values. The system uses fuzzy logic to interpret multiple natural expressions such as mostly, many and few and a neural network to learn the meaning of mostly red, many red and few red. The system has been implemented on the World Wide Web using CGI scripts and C programming language. Previously (S. Kulkarni et al., 1999), we presented some preliminary results using a single query. The paper presents the extension of our online system for multiple queries such as "many blue and few green". A number of experiments using our online system is conducted and the results are included and discussed in the paper.
Citations
More filters
TL;DR: The aim of this research is to highlight the efforts of researchers who have conducted some brilliant work and to provide a proof of concept for intelligent content-based image retrieval techniques.
Abstract: In the current era of digital communication, the use of digital images has increased for expressing, sharing andinterpreting information. While working with digital images, quite often it is necessary to search for a specific image for aparticular situation based on the visual contents of the image. This task looks easy if you are dealing with tens of imagesbut it gets more difficult when the number of images goes from tens to hundreds and thousands, and the same contentbasedsearching task becomes extremely complex when the number of images is in the millions. To deal with thesituation, some intelligent way of content-based searching is required to fulfill the searching request with right visualcontents in a reasonable amount of time. There are some really smart techniques proposed by researchers for efficientand robust content-based image retrieval. In this research, the aim is to highlight the efforts of researchers whoconducted some brilliant work and to provide a proof of concept for intelligent content-based image retrieval techniques.
44 citations
Cites background from "An intelligent on-line system for c..."
...Ideas and researches based upon neural networks in CBIR are presented in [3-21]....
[...]
...An online image retrieval system that supports multiple queries is argued in [14]....
[...]
01 Jan 2009
8 citations
25 Jun 2010
TL;DR: A content-based parallel image retrieval system to achieve high responding ability, developed on cluster architectures, that uses the Symmetrical Color-Spatial Features (SCSF) to represent the content of an image.
Abstract: As we all know, the content-based image retrieval (CBIR) is very time-consuming due to the extraction and matching of high dimensional and complex features. The traditional CBIR systems could not respond to a very large number of retrieval requests at mean time, which are submitted from the Internet. In this paper, we propose a content-based parallel image retrieval system to achieve high responding ability. Our system is developed on cluster architectures. It has several retrieval servers to supply the service of content-based image retrieval. Our system adopts the Browser/Server (B/S) mode. The users could visit our system though web pages. Our system uses the Symmetrical Color-Spatial Features (SCSF)[25] to represent the content of an image. The SCSF is effective and efficient for image matching because it is independent of image distortion such as rotation and flip as well as it increases the matching accuracy. The SCSF was organized by M-tree[16], which could speedup the searching procedure. Our experiments show that the image matching is quickly and efficiently with the use of SCSF. And with the support of several retrieval servers, the system could respond to many users at mean time. (Abstract)
7 citations
12 Mar 2000
TL;DR: In this paper, an image is segmented into "homogeneous" regions using a histogram clustering algorithm and each image is then represented by a set of regions with region descriptors.
Abstract: Representing general images using global features extracted from the entire image may be inappropriate because the images often contain several objects or regions that are totally different from each other in terms of visual image properties. These features cannot adequately represent the variations and hence fail to describe the image content correctly. We advocate the use of features extracted from image regions and represent the images by a set of regional features. In our work, an image is segmented into "homogeneous" regions using a histogram clustering algorithm. Each image is then represented by a set of regions with region descriptors. Region descriptors consist of feature vectors representing color, texture, area and location of regions. Image similarity is measured by a newly proposed Region Match Distance metric for comparing images by region similarity. Comparison of image retrieval using global and regional features is presented and the advantage of using regional representation is demonstrated.
7 citations
22 Jul 2009
TL;DR: In this paper, a color and texture based neural network -fuzzy logic approach for content based image retrieval using 2D-wavelet transform was proposed, which improved the retrieval performance by learning and searching capability of the neural network combined with the fuzzy interpretation.
Abstract: In this paper we introduce the new integrated color and texture based image retrieval technique using neuro-fuzzy approach for content based image retrieval. Most of the image retrieval systems are still incapable of providing retrieval result with high retrieval accuracy and less computational complexity. To address this problem, we developed color and texture based neural network -fuzzy logic approach for content based image retrieval using 2D-wavelet transform. The system performance improved by the learning and searching capability of the neural network combined with the fuzzy interpretation. This overcomes the vagueness and inconsistency due to human subjectivity. Multiresolution analysis using 2D-DWT can decompose the image into components at different scales, so that the coarest scale components carry the global approximation information while the finer scale components contain the detailed information. The empirical results show that the precision improved from 67% to 98% and average recall rate of 67% to 98% for the general purpose database size of 10000 images compared with existing approaches.
1 citations
References
More filters
01 Nov 1995
TL;DR: The use of fuzzy logic techniques are explored for describing image data, inference for retrieval, and inference for adjustment to a new user in terms of fuzzy predicates.
Abstract: We present a flexible retrieval system of face photographs based on their linguistic descriptions in terms of fuzzy predicates. Such expressions are a natural way for describing a (facial) image. However, due to their subjectivity they may lead to a poor performance of the retrieval operation. Regardless of the initial design of a retrieval system its capability ofadjustment to different users becomes very important. This paper explores the use of fuzzy logic techniques, for (i) describing image data, (ii) inference for retrieval, and (iii) inference for adjustment to a new user. The work presented in this paper builds on an earlier image modeling and retrieval system and we demonstrate the feasibility of adjustment to individual users, and the improvement resulting from it.
13 citations
16 Sep 1996
TL;DR: The paper describes the approach to object recognition, which is distinguished by a rich involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts.
Abstract: Retrieving images from very large collections, using image content as a key, is becoming an important problem. Finding objects in image databases is a big challenge in the field. The paper describes our approach to object recognition, which is distinguished by: a rich involvement of early visual primitives, including color and texture; hierarchical grouping and learning strategies in the classification process; the ability to deal with rather general objects in uncontrolled configurations and contexts. We illustrate these properties with three case studies: one demonstrating the use of color and texture descriptors; one learning scenery concepts using grouped features; and one demonstrating a possible application domain in detecting naked people in a scene.
13 citations