Showing papers on "Content-based image retrieval published in 2009"

CoPhIR: a Test Collection for Content-Based Image Retrieval

Abstract: The scalability, as well as the effectiveness, of the different Content-based Image Retrieval (CBIR) approaches proposed in literature, is today an important research issue. Given the wealth of images on the Web, CBIR systems must in fact leap towards Web-scale datasets. In this paper, we report on our experience in building a test collection of 100 million images, with the corresponding descriptive features, to be used in experimenting new scalable techniques for similarity searching, and comparing their results. In the context of the SAPIR (Search on Audio-visual content using Peer-to-peer Information Retrieval) European project, we had to experiment our distributed similarity searching technology on a realistic data set. Therefore, since no large-scale collection was available for research purposes, we had to tackle the non-trivial process of image crawling and descriptive feature extraction (we used five MPEG-7 features) using the European EGEE computer GRID. The result of this effort is CoPhIR, the first CBIR test collection of such scale. CoPhIR is now open to the research community for experiments and comparisons, and access to the collection was already granted to more than 50 research groups worldwide.

Semisupervised SVM batch mode active learning with applications to image retrieval

Abstract: Support vector machine (SVM) active learning is one popular and successful technique for relevance feedback in content-based image retrieval (CBIR). Despite the success, conventional SVM active learning has two main drawbacks. First, the performance of SVM is usually limited by the number of labeled examples. It often suffers a poor performance for the small-sized labeled examples, which is the case in relevance feedback. Second, conventional approaches do not take into account the redundancy among examples, and could select multiple examples that are similar (or even identical). In this work, we propose a novel scheme for explicitly addressing the drawbacks. It first learns a kernel function from a mixture of labeled and unlabeled data, and therefore alleviates the problem of small-sized training data. The kernel will then be used for a batch mode active learning method to identify the most informative and diverse examples via a min-max framework. Two novel algorithms are proposed to solve the related combinatorial optimization: the first approach approximates the problem into a quadratic program, and the second solves the combinatorial optimization approximately by a greedy algorithm that exploits the merits of submodular functions. Extensive experiments with image retrieval using both natural photo images and medical images show that the proposed algorithms are significantly more effective than the state-of-the-art approaches. A demo is available at http://msm.cais.ntu.edu.sg/LSCBIR/.

Secure image retrieval through feature protection

Abstract: This paper addresses the problem of image retrieval from an encrypted database, where data confidentiality is preserved both in the storage and retrieval process. The paper focuses on image feature protection techniques which enable similarity comparison among protected features. By utilizing both signal processing and cryptographic techniques, three schemes are investigated and compared, including bit-plane randomization, random projection, and randomized unary encoding. Experimental results show that secure image retrieval can achieve comparable retrieval performance to conventional image retrieval techniques without revealing information about image content. This work enriches the area of secure information retrieval and can find applications in secure online services for images and videos.

Ontology of gaps in content-based image retrieval.

Abstract: Content-based image retrieval (CBIR) is a promising technology to enrich the core functionality of picture archiving and communication systems (PACS). CBIR has a potential for making a strong impact in diagnostics, research, and education. Research as reported in the scientific literature, however, has not made significant inroads as medical CBIR applications incorporated into routine clinical medicine or medical research. The cause is often attributed (without supporting analysis) to the inability of these applications in overcoming the “semantic gap.” The semantic gap divides the high-level scene understanding and interpretation available with human cognitive capabilities from the low-level pixel analysis of computers, based on mathematical processing and artificial intelligence methods. In this paper, we suggest a more systematic and comprehensive view of the concept of “gaps” in medical CBIR research. In particular, we define an ontology of 14 gaps that addresses the image content and features, as well as system performance and usability. In addition to these gaps, we identify seven system characteristics that impact CBIR applicability and performance. The framework we have created can be used a posteriori to compare medical CBIR systems and approaches for specific biomedical image domains and goals and a priori during the design phase of a medical CBIR application, as the systematic analysis of gaps provides detailed insight in system comparison and helps to direct future research.

Color and Texture Features for Image Indexing and Retrieval

Abstract: The novel approach combines color and texture features for content based image retrieval (CBIR). The color and texture features are obtained by computing the mean and standard deviation on each color band of image and sub-band of different wavelets. The standard Wavelet and Gabor wavelet transforms are used for decomposing the image into sub-bands. The retrieval results obtained by applying color histogram (CH) + Gabor wavelet transform(GWT) to a 1000 image database demonstrated significant improvement in precision and recall, compared to the color histogram (CH), wavelet transform (WT), wavelet transform + color histogram (WT + CH) and Gabor wavelet transform (GWT).

A Study of Color Histogram Based Image Retrieval

Abstract: This paper describes a project that implements and tests a simple color histogram based search and retrieve algorithm for images. The study finds the technique to be effective as shown by analysis using the RankPower measurement. The testing also highlights the weaknesses and strengths of the model, concluding that the technique would have to be augmented and modified in order for practical use.

Image retrieval using augmented block truncation coding techniques

Abstract: With the tremendous growth of ICT (Information and Communication Technology), we are able to generate, store, share and transfer enormous amount of information. World Wide Web have further made is easy to access the information anytime, anywhere in the world. With the advent of high capacity communication links and storage devices even most of the information generated is of multimedia in nature. Images have major share in this information and the number of image achieves are growing with the jet speed Just having the tremendous amount of information is not useful unless we do not have the methodologies to effectively search the related data from it in minimum possible duration. The relativity of the image data is application specific. Here to search and retrieve the expected images from the database we need Content Based Image Retrieval (CBIR) system. CBIR extracts the features of query image and try to match them with the extracted features of images in the database. Then based on the similarity measures and threshold the best possible candidate matches are given as result. There have been many approaches to decide and extract the features of images in the database. Binary truncation Coding based features is one of the CBIR methods proposed using color features of image. The approach basically considers red, green and blue planes of image together to compute feature vector. Here we have augmented this BTC based CBIR as BTC-RGB and Spatial BTC-RGB. In BTC-RGB feature vector is computed by considering red, green and blue planes of the image independently. While in Spatial BTC-RGB, the feature vector is composed of four parts. Each part is representing the features extracted from one of the four non overlapping quadrants of the image. The new proposed methods are tested on the 1000 images database and the results show that the precession is improved in BTC-RGB and is even better in Spatial BTC-RGB.

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.

Content-based image retrieval: An application to tattoo images

Abstract: Tattoo images on human body have been routinely collected and used in law enforcement to assist in suspect and victim identification. However, the current practice of matching tattoos is based on keywords. Assigning keywords to individual tattoo images is both tedious and subjective. We have developed a content-based image retrieval system for a tattoo image database. The system automatically extracts image features based on the Scale Invariant Feature Transform (SIFT). Side information, i.e., body location of tattoos and tattoo classes, is utilized to improve the retrieval time and retrieval accuracy. Geometrical constraints are also introduced in SIFT keypoint matching to reduce false retrievals. Experimental results on 1,000 queries against an operational database of 63,593 tattoo images show a rank-20 accuracy of 94.2%; the average matching time per query is 2.9 sec. on Intel Core 2, 2.66 GHz, 3 GB RAM processor.

Content-Based Image Retrieval in Medicine: Retrospective Assessment, State of the Art, and Future Directions

Abstract: Content-based image retrieval (CBIR) technology has been proposed to benefit not only the management of increasingly large image collections, but also to aid clinical care, biomedical research, and education. Based on a literature review, we conclude that there is widespread enthusiasm for CBIR in the engineering research community, but the application of this technology to solve practical medical problems is a goal yet to be realized. Furthermore, we highlight “gaps” between desired CBIR system functionality and what has been achieved to date, present for illustration a comparative analysis of four state-of-the-art CBIR implementations using the gap approach, and suggest that high-priority gaps to be overcome lie in CBIR interfaces and functionality that better serve the clinical and biomedical research communities.

A query-by-example content-based image retrieval system of non-melanoma skin lesions

Abstract: This paper proposes a content-based image retrieval system for skin lesion images as a diagnostic aid. The aim is to support decision making by retrieving and displaying relevant past cases visually similar to the one under examination. Skin lesions of five common classes, including two non-melanoma cancer types are used. Colour and texture features are extracted from lesions. Feature selection is achieved by optimising a similarity matching function. Experiments on our database of 208 images are performed and results evaluated.

Color Image Clustering using Block Truncation Algorithm

Abstract: With the advancement in image capturing device, the image data been generated at high volume. If images are analyzed properly, they can reveal useful information to the human users. Content based image retrieval address the problem of retrieving images relevant to the user needs from image databases on the basis of low-level visual features that can be derived from the images. Grouping images into meaningful categories to reveal useful information is a challenging and important problem. Clustering is a data mining technique to group a set of unsupervised data based on the conceptual clustering principal: maximizing the intraclass similarity and minimizing the interclass similarity. Proposed framework focuses on color as feature. Color Moment and Block Truncation Coding (BTC) are used to extract features for image dataset. Experimental study using K-Means clustering algorithm is conducted to group the image dataset into various clusters.

Detecting objects in large image collections and videos by efficient subimage retrieval

Abstract: We study the task of detecting the occurrence of objects in large image collections or in videos, a problem that combines aspects of content based image retrieval and object localization. While most previous approaches are either limited to special kinds of queries, or do not scale to large image sets, we propose a new method, efficient subimage retrieval (ESR), that is at the same time very flexible and very efficient. Relying on a two-layered branch-and-bound setup, ESR performs object-based image retrieval in sets of 100,000 or more images within seconds. An extensive evaluation on several datasets shows that ESR is not only very fast, but it also achieves excellent detection accuracies thereby improving over previous systems for object-based image retrieval.

Location coding for mobile image retrieval

Abstract: For mobile image retrieval, efficient data transmission can be achieved by sending only the query features. Each query feature is composed of a descriptor and a location in the image. The former is used to find candidate matching images using a "bag-of-words" approach while the latter is used in a geometric consistency check to map features in the query image to corresponding features in the database image. We investigate how to compress the location information and how lossy compression affects the geometric consistency check. The location information is converted into a location histogram and a context-based arithmetic coding with location refinement method is then proposed to code the histogram. The effects of lossily compressing the location information are evaluated empirically in terms of the errors in corresponding features and the error of the estimated geometric transformation model. From our experiments, rates at ~5.1 bits per feature can achieve errors comparable to lossless coding. The proposed scheme achieves a 12.5x rate reduction compared to the floating point representation, and 2.8x rate reduction compared to a fixed point representation.

Content-Based Image Retrieval with HSV Color Space and Texture Features

Abstract: An image retrieval system is presented, which used HSV color space and wavelet transform approach for feature extraction Firstly, we quantified the color space in non-equal intervals, then constructed one dimension feature vector and represented the color feature Similarly, the work of texture feature extraction is obtained by using wavelet Finally, we combine color feature and texture feature based on wavelet transform A method of multi features retrieval is provided The image retrieval experiments indicated that visual features were sensitive for different type images The color features opted to the rich color image with simple variety Texture feature opted to the complex images At the same time, experiments reveal that texture feature based on wavelet transform has better effective performance and stability

A new approach in content-based image retrieval using fuzzy

Abstract: Finding an image from a large set of images is an extremely difficult problem. One solution is to label images manually, but this is very expensive, time consuming and infeasible for many applications. Furthermore, the labeling process depends on the semantic accuracy in describing the image. Therefore many Content based Image Retrieval (CBIR) systems are developed to extract low-level features for describing the image content. However, this approach decreases the human interaction with the system due to the semantic gap between low-level features and high-level concepts. In this study we make use of fuzzy logic to improve CBIR by allowing users to express their requirements in words, the natural way of human communication. In our system the image is represented by a Fuzzy Attributed Relational Graph (FARG) that describes each object in the image, its attributes and spatial relation. The texture and color attributes are computed in a way that model the Human Vision System (HSV). We proposed a new approach for graph matching that resemble the human thinking process. The proposed system is evaluated by different users with different perspectives and is found to match users' satisfaction to a high degree.

Content-based image retrieval methods

Abstract: Creation of a content-based image retrieval system implies solving a number of difficult problems, including analysis of low-level image features and construction of feature vectors, multidimensional indexing, design of user interface, and data visualization Quality of a retrieval system depends, first of all, on the feature vectors used, which describe image content The paper presents a survey of common feature extraction and representation techniques and metrics of the corresponding feature spaces Color, texture, and shape features are considered A detailed classification of the currently known features' representations is given Experimental results on efficiency comparison of various methods for representing and comparing image content as applied to the retrieval and classification tasks are presented

Caliph & Emir: MPEG-7 photo annotation and retrieval

Abstract: Caliph & Emir are Java-based applications for image annotation and retrieval. They implement a large part of MPEG-7 descriptors and support annotation and retrieval based on the descriptors. Manual annotation is based on text and the MPEG-7 semantic description scheme. Automatic extraction of low level features and existing metadata is also supported. Retrieval features include: linear search, content based image retrieval, textual metadata and graph indexing, and two-dimensional repository visualization.

Fast Query Point Movement Techniques for Large CBIR Systems

Abstract: Target search in content-based image retrieval (CBIR) systems refers to finding a specific (target) image such as a particular registered logo or a specific historical photograph. Existing techniques, designed around query refinement based on relevance feedback, suffer from slow convergence, and do not guarantee to find intended targets. To address these limitations, we propose several efficient query point movement methods. We prove that our approach is able to reach any given target image with fewer iterations in the worst and average cases. We propose a new index structure and query processing technique to improve retrieval effectiveness and efficiency. We also consider strategies to minimize the effects of users' inaccurate relevance feedback. Extensive experiments in simulated and realistic environments show that our approach significantly reduces the number of required iterations and improves overall retrieval performance. The experimental results also confirm that our approach can always retrieve intended targets even with poor selection of initial query points.

Morphological Description of Color Images for Content-Based Image Retrieval

Abstract: Placed within the context of content-based image retrieval, we study in this paper the potential of morphological operators as far as color description is concerned, a booming field to which the morphological framework, however, has only recently started to be applied. More precisely, we present three morphology-based approaches, one making use of granulometries independently computed for each subquantized color and two employing the principle of multiresolution histograms for describing color, using respectively morphological levelings and watersheds. These new morphological color descriptors are subsequently compared against known alternatives in a series of experiments, the results of which assert the practical interest of the proposed methods.

Scale-Invariant Visual Language Modeling for Object Categorization

Abstract: In recent years, ldquobag-of-wordsrdquo models, which treat an image as a collection of unordered visual words, have been widely applied in the multimedia and computer vision fields. However, their ignorance of the spatial structure among visual words makes them indiscriminative for objects with similar word frequencies but different word spatial distributions. In this paper, we propose a visual language modeling method (VLM), which incorporates the spatial context of the local appearance features into the statistical language model. To represent the object categories, models with different orders of statistical dependencies have been exploited. In addition, the multilayer extension to the VLM makes it more resistant to scale variations of objects. The model is effective and applicable to large scale image categorization. We train scale invariant visual language models based on the images which are grouped by Flickr tags, and use these models for object categorization. Experimental results show they achieve better performance than single layer visual language models and ldquobag-of-wordsrdquo models. They also achieve comparable performance with 2-D MHMM and SVM-based methods, while costing much less computational time.