scispace - formally typeset
Search or ask a question
Topic

Content-based image retrieval

About: Content-based image retrieval is a research topic. Over the lifetime, 6916 publications have been published within this topic receiving 150696 citations. The topic is also known as: CBIR.


Papers
More filters
Proceedings ArticleDOI
24 Mar 2008
TL;DR: The goal of this paper is the formation of an image analysis tool to match tattoos and to retrieve similar tattoos from a tattoo database using a new active contour CBIR approach that incorporates vector field convolution active contours for tattoo segmentation.
Abstract: Tattoos provide an important source of biometric information, particularly in gang-related criminal activity. The goal of this paper is the formation of an image analysis tool to match tattoos and to retrieve similar tattoos from a tattoo database. First, an existing content based image retrieval (CBIR) approach for tattoos is reviewed. Then, a new active contour CBIR approach is detailed. This method incorporates vector field convolution active contours for tattoo segmentation, Haar wavelet decomposition for texture analysis, hue-saturation-value histograms for color representation and Fourier shape descriptors for shape characterization. Finally, the glocal (global-local) image feature approach is introduced. Results are provided for two datasets that include both recreational and prison/gang tattoos.

38 citations

Proceedings ArticleDOI
07 Oct 2001
TL;DR: This work presents a novel approach to content-based image retrieval in categorical multimedia databases using relevance feedback to learn the user's intent-query specification and feature-weighting-with minimal user-interface abstraction.
Abstract: This work presents a novel approach to content-based image retrieval in categorical multimedia databases. The images are indexed using a combination of text and content descriptors. The categories are viewed as semantic clusters of images and are used to confine the search space. Keywords are used to identify candidate categories. Content-based retrieval is performed in these categories using multiple image features. Relevance feedback is used to learn the user's intent-query specification and feature-weighting-with minimal user-interface abstraction. The method is applied to a large number of images collected from a popular categorical structure on the World Wide Web. Results show that efficient and accurate performance is achievable by exploiting the semantic classification represented by the categories. The relevance feedback loop allows the content descriptor weightings to be determined without exposing the calculations to the user.

38 citations

Proceedings ArticleDOI
03 Nov 2011
TL;DR: Content based image retrieval (CBIR), a technique which uses the content like color, texture and shape to search images from the large scale databases, is an active research area.
Abstract: Content based image retrieval (CBIR), a technique which uses the content like color, texture and shape to search images from the large scale databases, is an active research area. In this paper, de-duplication process of photographs was implemented using CBIR. The CBIR technique uses color histogram refinement feature. The photograph data was divided into different clusters using k-means clustering algorithm. The clusters count depends on the numbers of photographs in each district of the state. The photo de-duplication exercise was carried out in a large photograph database which contains 22 million (approximately) photograph images. The experimental results shows that there were 0.35 million (approximately) duplicate photographs.

38 citations

Proceedings ArticleDOI
15 Oct 2004
TL;DR: A new framework for characterizing and retrieving objects in cluttered scenes based on a new representation describing every object taking into account the local properties of its parts and their mutual spatial relations, without relying on accurate segmentation.
Abstract: We present a new framework for characterizing and retrieving objects in cluttered scenes. Objects are best represented by characterizing both their parts and the mutual spatial relations among them. This CBIR system is based on a new representation describing every object taking into account the local properties of its parts and their mutual spatial relations, without relying on accurate segmentation. For this purpose, a new multi-dimensional histogram is used that measures the joint distribution of local properties and relative spatial positions. Instead of using a single descriptor for all the image, we represent the image by a set of histograms covering the object from different perspectives. We integrate this representation in a whole framework which has two stages. The first one is to allow an efficient retrieval based on the geometric properties (shape) of objects in images with clutter. This is achieved by i) using a contextual descriptor that incorporates the distribution of local structures, and ii) taking a proper distance that disregards the clutter of the images. At a second stage, we introduce a more discriminative descriptor that characterizes the parts of the objects by their color and their local tructure. By sing relevant-feedback and boosting as a feature selection algorithm, the system is able to learn simultaneously the information that characterize each part of the object along with their mutual spatial relations. Results are reported on two known databases and are quantitatively compared to other successful approaches

38 citations

Journal ArticleDOI
TL;DR: The information-theoretic measures of entropy and mutual information are suggested to evaluate the compactness of a distribution and the independence of two distributions in the context of the content-based image retrieval system PicSOM.

38 citations


Network Information
Related Topics (5)
Feature extraction
111.8K papers, 2.1M citations
90% related
Feature (computer vision)
128.2K papers, 1.7M citations
88% related
Image segmentation
79.6K papers, 1.8M citations
87% related
Convolutional neural network
74.7K papers, 2M citations
87% related
Deep learning
79.8K papers, 2.1M citations
86% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202358
2022141
2021180
2020163
2019224
2018270