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.

Content-based image retrieval by integrating color and texture features

Abstract: Content-based image retrieval (CBIR) has been an active research topic in the last decade. Feature extraction and representation is one of the most important issues in the CBIR. In this paper, we propose a content-based image retrieval method based on an efficient integration of color and texture features. As its color features, pseudo-Zernike chromaticity distribution moments in opponent chromaticity space are used. As its texture features, rotation-invariant and scale-invariant image descriptor in steerable pyramid domain are adopted, which offers an efficient and flexible approximation of early processing in the human visual system. The integration of color and texture information provides a robust feature set for color image retrieval. Experimental results show that the proposed method yields higher retrieval accuracy than some conventional methods even though its feature vector dimension is not higher than those of the latter for different test DBs.

Image retrieval using color-texture features from dct on vq code vectors obtained by kekres fast codebook generation

Abstract: novel technique for image retrieval using the color- texture features extracted from images based on vector quantization with Kekre's fast codebook generation is proposed. This gives better discrimination capability for Content Based Image Retrieval (CBIR). Here the database image is divided into 2x2 pixel windows to obtain 12 color descriptors per window (Red, Green and Blue per pixel) to form a vector. Collection of all such vectors is a training set. Then the Kekre's Fast Codebook Generation (KFCG) is applied on this set to get 16 codevectors. The Discrete Cosine Transform (DCT) is applied on these codevectors by converting them to column vector. This transform vector is used as the image signature (feature vector) for image retrieval. The method takes lesser computations as compared to conventional DCT applied on complete image. The method gives the color-texture features of the image database at reduced feature set size. Proposed method avoids resizing of images which is required for any transform based feature extraction method.

Color clustering techniques for color-content-based image retrieval from image databases

Abstract: Image retrieval based on color content is an auxiliary function for traditional text-annotated image databases. Most color-based image retrieval systems adopt color histograms as the feature of color content. One of the most important steps in these systems is to reduce histogram dimensions with the least loss in color content. A good clustering technique is vital for this purpose. This paper examines the color conservation property by applying different clustering techniques in perceptually uniform color spaces and different images. For studying color spaces, the perceptual uniform spaces, such as Mathematical Transformation to Munsell system (MTM) and C.I.E. L*a*b*, are investigated. For evaluating clustering techniques, the equalized quantization approach, the hierarchical clustering approach, and the Color-Naming-System (CNS) supervised clustering approach are studied. For analyzing color loss, the error bound, the quantized error in color space conversion, and the average quantized error of 400 color images are explored. An image retrieval application based on color content is shown to demonstrate the difference in applying these clustering techniques. These simulation results suggest that good clustering techniques usually lead to more effective retrieval.

EMR: A Scalable Graph-Based Ranking Model for Content-Based Image Retrieval

Abstract: Graph-based ranking models have been widely applied in information retrieval area In this paper, we focus on a well known graph-based model - the Ranking on Data Manifold model, or Manifold Ranking (MR) Particularly, it has been successfully applied to content-based image retrieval, because of its outstanding ability to discover underlying geometrical structure of the given image database However, manifold ranking is computationally very expensive, which significantly limits its applicability to large databases especially for the cases that the queries are out of the database (new samples) We propose a novel scalable graph-based ranking model called Efficient Manifold Ranking (EMR), trying to address the shortcomings of MR from two main perspectives: scalable graph construction and efficient ranking computation Specifically, we build an anchor graph on the database instead of a traditional $k$ -nearest neighbor graph, and design a new form of adjacency matrix utilized to speed up the ranking An approximate method is adopted for efficient out-of-sample retrieval Experimental results on some large scale image databases demonstrate that EMR is a promising method for real world retrieval applications