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
Book ChapterDOI
01 Jun 2007
TL;DR: This chapter discusses an approach to computer vision using automated image classification and similarity measurement based on a large set of general image descriptors for several diverse applications.
Abstract: The tremendous growth in digital imagery has introduced the need for accurate image analysis and classification. The applications include content based image retrieval in the World Wide Web and digital libraries (Dong & Yang, 2002; Heidmann, 2005; Smeulders et al., 2000; Veltkamp et al., 2001) scene classification (Huang et al., 2005; Jiebo et al., 2005), face recognition (Jing & Zhang, 2006; Pentland & Choudhury, 2000; Shen & Bai, 2006) and biological and medical image classification (Awate et al., 2006; Boland & Murphy, 2001; Cocosco et al., 2004; Ranzato et al., 2007). Although attracting considerable attention in the past few years, image classification is still considered a challenging problem in machine learning due to the complexity of real-life images. This chapter discusses an approach to computer vision using automated image classification and similarity measurement based on a large set of general image descriptors. Classification results as well as image similarity measurements are presented for several diverse applications.

36 citations

Journal ArticleDOI
TL;DR: This paper presents an efficient two-stage image retrieval system with high performance of efficacy based on two novel texture features, the composite sub-band gradient (CSG) vector and the energy distribution pattern (EDP)-string.
Abstract: Efficacy and efficiency are two important issues in designing content-based image retrieval systems. In this paper, we present an efficient two-stage image retrieval system with high performance of efficacy based on two novel texture features, the composite sub-band gradient (CSG) vector and the energy distribution pattern (EDP)-string. Both features are generated from the sub-images of a wavelet decomposition of the original image. At the first stage, a fuzzy matching process based on EDP-strings is performed and serves as a signature filter to quickly remove a large number of non-promising database images from further consideration. At the second stage, the images passing through the filter will be compared with the query image based on their CSG vectors for detailed feature inspection. By exercising a database of 2400 images obtained from the Brodatz album, we demonstrated that both high efficacy and high efficiency can be achieved simultaneously by our proposed system.

36 citations

Proceedings ArticleDOI
01 Dec 2014
TL;DR: This paper has proposed a content based image retrieval integrated technique which extracts both the color and texture feature and provides accurate, efficient, less complex retrieval system.
Abstract: Content based image retrieval, in the last few years has received a wide attention. Content Based Image Retrieval (CBIR) basically is a technique to perform retrieval of the images from a large database which are similar to image given as query. CBIR is closer to human semantics, in the context of image retrieval process. CBIR technique has its application in different domains such as crime prevention, medical images, weather forecasting, surveillance, historical research and remote sensing Here content refers to the visual information of images such as texture, shape and color. Contents of image are richer in information for an efficient retrieval in comparison to text based image retrieval. In this paper, we have proposed a content based image retrieval integrated technique which extracts both the color and texture feature. To extract the color feature, color moment (CM) is used on color images and to extract the texture feature, local binary pattern (LBP) is performed on the grayscale image. Then both color and texture feature of image are combined to form a single feature vector. In the end similarity matching is performed by Euclidian distance which compares feature vector of database images with query images. LBP mainly used for face recognition. But we are going to use LBP for natural images. This combined approach provides accurate, efficient, less complex retrieval system.

36 citations

01 Jan 2010
TL;DR: From the average precision and average recall values obtained by firing 55 queries on the image database it is found that use of row mean and column mean with image fragmentation improves the performance resulting in better image retrieval.
Abstract: Always the thrust for better and faster image retrieval techniques has nourished the research in content based image retrieval. The paper presents 32 novel image retrieval techniques using the feature vectors obtained by applying Walsh transform on row mean and column mean of full image, four fragments, sixteen fragments and 64 fragments of image. All the proposed CBIR techniques are tested on generic image database of size 1000 with 11 image classes. From the average precision and average recall values obtained by firing 55 queries on the image database it is found that use of row mean and column mean with image fragmentation improves the performance resulting in better image retrieval. In all these techniques to speed up the image retrieval process notion of energy compaction is introduced and tested for 100%, 95%, 90% and 85% of energy of feature vectors using Walsh transform.

36 citations

Proceedings ArticleDOI
16 Jun 2000
TL;DR: It is shown that the ability to access images at the level of objects is essential for CBIR, and the superiority of the approach over the global histogram approach is shown.
Abstract: We propose a content based image retrieval system based on object extraction through image segmentation. A general and powerful multiscale segmentation algorithm automates the segmentation process, the output of which is assigned novel colour and texture descriptors which are both efficient and effective. Query strategies consisting of a semi-automated and a fully automated mode are developed which are shown to produce good results. We then show the superiority of our approach over the global histogram approach which proves that the ability to access images at the level of objects is essential for CBIR.

36 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