A genetic programming framework for content-based image retrieval

The effectiveness of content-based image retrieval (CBIR) systems can be improved by combining image features or by weighting image similarities, as computed from multiple feature vectors. However, feature combination do not make sense always and the combined similarity function can be more complex than weight-based functions to better satisfy the users’ expectations. We address this problem by presenting a Genetic Programming framework to the design of combined similarity functions. Our method allows nonlinear combination of image similarities and is validated through several experiments, where the images are retrieved based on the shape of their objects. Experimental results demonstrate that the GP framework is suitable for the design of effective combinations functions.     

A hybrid probabilistic framework for content-based image retrieval with feature weighting

In this paper, we propose a probabilistic framework for efficient retrieval and indexing of image collections. This framework uncovers the hierarchical structure underlying the collection from image features based on a hybrid model that combines both generative and discriminative learning. We adopt the generalized Dirichlet mixture and maximum likelihood for the generative learning in order to estimate accurately the statistical model of the data. Then, the resulting model is refined by a new discriminative likelihood that enhances the power of relevant features. Consequently, this new model is suitable for modeling high-dimensional data described by both semantic and low-level (visual) features. The semantic features are defined according to a known ontology while visual features represent the visual appearance such as color, shape, and texture. For validation purposes, we propose a new visual feature which has nice invariance properties to image transformations. Experiments on the Microsoft's collection (MSRCID) show clearly the merits of our approach in both retrieval and indexing.     

Web-based image indexing and retrieval in JPEG compressed domain

As the majority of content-based image retrieval systems operate on full images in pixel domain, decompression is a prerequisite for the retrieval of compressed images. To provide a possible on-line indexing and retrieval technique for those jpg image files, we propose a novel pseudo-pixel extraction algorithm to bridge the gap between the existing image indexing technology, developed in the pixel domain, and the fact that an increasing number of images stored on the Web are already compressed by JPEG at the source. Further, we describe our Web-based image retrieval system, WEBimager, by using the proposed algorithm to provide a prototype visual information system toward automatic management, indexing, and retrieval of compressed images available on the Internet. This provides users with efficient tools to search the Web for compressed images and establish a database or a collection of special images to their interests. Experiments using texture- and colour-based indexing techniques support the idea that the proposed algorithm achieves significantly better results in terms of computing cost than their full decompression or partial decompression counterparts. This technology will help control the explosion of media-rich content by offering users a powerful automated image indexing and retrieval tool for compressed images on the Web.J. Jiang: Contacting author     

Robust content-based image indexing using contextual clues and automatic pseudofeedback

In this paper we present a robust information integration approach to identifying images of persons in large collections such as the Web. The underlying system relies on combining content analysis, which involves face detection and recognition, with context analysis, which involves extraction of text or HTML features. Two aspects are explored to test the robustness of this approach: sensitivity of the retrieval performance to the context analysis parameters and automatic construction of a facial image database via automatic pseudofeedback. For the sensitivity testing, we reevaluate system performance while varying context analysis parameters. This is compared with a learning approach where association rules among textual feature values and image relevance are learned via the CN2 algorithm. A face database is constructed by clustering after an initial retrieval relying on face detection and context analysis alone. Experimental results indicate that the approach is robust for identifying and indexing person images.Y. Alp Aslandogan: Correspondence to:     

A survey of content-based image retrieval with high-level semantics

In order to improve the retrieval accuracy of content-based image retrieval systems, research focus has been shifted from designing sophisticated low-level feature extraction algorithms to reducing the ‘semantic gap’ between the visual features and the richness of human semantics. This paper attempts to provide a comprehensive survey of the recent technical achievements in high-level semantic-based image retrieval. Major recent publications are included in this survey covering different aspects of the research in this area, including low-level image feature extraction, similarity measurement, and deriving high-level semantic features. We identify five major categories of the state-of-the-art techniques in narrowing down the ‘semantic gap’: (1) using object ontology to define high-level concepts; (2) using machine learning methods to associate low-level features with query concepts; (3) using relevance feedback to learn users’ intention; (4) generating semantic template to support high-level image retrieval; (5) fusing the evidences from HTML text and the visual content of images for WWW image retrieval. In addition, some other related issues such as image test bed and retrieval performance evaluation are also discussed. Finally, based on existing technology and the demand from real-world applications, a few promising future research directions are suggested.     

Indexing chromatic and achromatic patterns for content-based colour image retrieval

In this paper, we present a method to represent achromatic and chromatic image signals independently for content-based image indexing and retrieval for image database applications. Starting from an opponent colour representation, human colour vision theories and modern digital signal processing technologies are applied to develop a compact and computationally efficient visual appearance model for coloured image patterns. We use the model to compute the statistics of achromatic and chromatic spatial patterns of colour images for indexing and content-based retrieval. Two types of colour images databases, one colour texture database and another photography colour image database are used to evaluate the performance of the developed method in content-based image indexing and retrieval. Experimental results are presented to show that the new method is superior or competitive to state-of-the-art content-based image indexing and retrieval techniques.     

A framework for linguistic relevance feedback in content-based image retrieval using fuzzy logic

We describe a new approach for exploiting relevance feedback in content-based image retrieval (CBIR). In our approach to relevance feedback we try to capture more of the users’ relevance judgments by allowing the use of natural language like comments on the retrieved images. Using methods from fuzzy logic and computational intelligence we are able to reflect these comments into new targets for searching the image database. Such enhanced information is utilized to develop a system that can provide more effective and efficient retrieval.     

Adaptive indexing for content-based search in P2P systems

One of the major challenges in Peer-to-Peer (P2P) file sharing systems is to support content-based search. Although there have been some proposals to address this challenge, they share the same weakness of using either servers or super-peers to keep global knowledge, which is required to identify importance of terms to avoid popular terms in query processing. As a result, they are not scalable and are prone to the bottleneck problem, which is caused by the high visiting load at the global knowledge maintainers. To that end, in this paper, we propose a novel adaptive indexing approach for content-based search in P2P systems, which can identify importance of terms without keeping global knowledge. Our method is based on an adaptive indexing structure that combines a Chord ring and a balanced tree. The tree is used to aggregate and classify terms adaptively, while the Chord ring is used to index terms of nodes in the tree. Specifically, at each node of the tree, the system classifies terms as either important or unimportant. Important terms, which can distinguish the node from its neighbor nodes, are indexed in the Chord ring. On the other hand, unimportant terms, which are either popular or rare terms, are aggregated to higher level nodes. Such classification enables the system to process queries on the fly without the need for global knowledge. Besides, compared to the methods that index terms separately, term aggregation reduces the indexing cost significantly. Taking advantage of the tree structure, we also develop an efficient search algorithm to tackle the bottleneck problem near the root. Finally, our extensive experiments on both benchmark and Wikipedia datasets validated the effectiveness and efficiency of the proposed method.     

PicSOM – content-based image retrieval with self-organizing maps

We have developed a novel system for content-based image retrieval in large, unannotated databases. The system is called PicSOM, and it is based on tree structured self-organizing maps (TS-SOMs). Given a set of reference images, PicSOM is able to retrieve another set of images which are similar to the given ones. Each TS-SOM is formed with a different image feature representation like color, texture, or shape. A new technique introduced in PicSOM facilitates automatic combination of responses from multiple TS-SOMs and their hierarchical levels. This mechanism adapts to the user's preferences in selecting which images resemble each other. Thus, the mechanism implements a relevance feedback technique on content-based image retrieval. The image queries are performed through the World Wide Web and the queries are iteratively refined as the system exposes more images to the user.     

Support vector description of clusters for content-based image annotation

Continual progress in the fields of computer vision and machine learning has provided opportunities to develop automatic tools for tagging images; this facilitates searching and retrieving. However, due to the complexity of real-world image systems, effective and efficient image annotation is still a challenging problem. In this paper, we present an annotation technique based on the use of image content and word correlations. Clusters of images with manually tagged words are used as training instances. Images within each cluster are modeled using a kernel method, in which the image vectors are mapped to a higher-dimensional space and the vectors identified as support vectors are used to describe the cluster. To measure the extent of the association between an image and a model described by support vectors, the distance from the image to the model is computed. A closer distance indicates a stronger association. Moreover, word-to-word correlations are also considered in the annotation framework. To tag an image, the system predicts the annotation words by using the distances from the image to the models and the word-to-word correlations in a unified probabilistic framework. Simulated experiments were conducted on three benchmark image data sets. The results demonstrate the performance of the proposed technique, and compare it to the performance of other recently reported techniques.     

Independent query refinement and feature re-weighting using positive and negative examples for content-based image retrieval

Query refinement and feature re-weighting are the two core techniques underlying the relevance feedback of content-based image retrieval. Most existing relevance feedback mechanisms generally model the user’s query target with a single query point and weight each extracted feature with a single importance factor. A designed estimation procedure then estimates the best query point and all importance factors by optimizing a formulated criterion which measures the goodness of the estimation. This formulated criterion simultaneously encapsulates all positive and negative examples supplied from the user’s feedback. Under such formulation, the positive and negative examples may contribute contradictorily to the criterion and sometimes may introduce higher difficulty in attaining a good estimation. In this paper, we propose a different statistical formulation to estimate independently two pairs of query points and feature weights from the positive examples and negative examples, respectively. These two pairs then define the likelihood ratio, a criterion term used to rank the relevance of all database images. This approach simplifies the criterion formulation and also avoids the mutual impeditive influence between positive examples and negative examples. The experimental results demonstrate that the proposed approach outperforms some other related approaches.

An adaptive technique for content-based image retrieval

We discuss an adaptive approach towards Content-Based Image Retrieval. It is based on the Ostensive Model of developing information needs—a special kind of relevance feedback model that learns from implicit user feedback and adds a temporal notion to relevance. The ostensive approach supports content-assisted browsing through visualising the interaction by adding user-selected images to a browsing path, which ends with a set of system recommendations. The suggestions are based on an adaptive query learning scheme, in which the query is learnt from previously selected images. Our approach is an adaptation of the original Ostensive Model based on textual features only, to include content-based features to characterise images. In the proposed scheme textual and colour features are combined using the Dempster-Shafer theory of evidence combination. Results from a user-centred, work-task oriented evaluation show that the ostensive interface is preferred over a traditional interface with manual query facilities. This is due to its ability to adapt to the user's need, its intuitiveness and the fluid way in which it operates. Studying and comparing the nature of the underlying information need, it emerges that our approach elicits changes in the user's need based on the interaction, and is successful in adapting the retrieval to match the changes. In addition, a preliminary study of the retrieval performance of the ostensive relevance feedback scheme shows that it can outperform a standard relevance feedback strategy in terms of image recall in category search.     

An efficient iconic indexing strategy for image rotation and reflection in image databases

Spatial relationships are important issues for similarity-based retrieval in many image database applications. With the popularity of digital cameras and the related image processing software, a sequence of images are often rotated or flipped. That is, those images are transformed in the rotation orientation or the reflection direction. However, many iconic indexing strategies based on symbolic projection are sensitive to rotation or reflection. Therefore, these strategies may miss the qualified images, when the query is issued in the orientation different from the orientation of the database images. To solve this problem, some researchers proposed a function to map the spatial relationship to its transformed one. However, this mapping consists of several conditional statements, which is time-consuming. Thus, in this paper, we propose an efficient iconic indexing strategy, in which we carefully assign a unique bit pattern to each spatial relationship and record the spatial information based on the bit patterns in a matrix. Without generating the rotated or flipped image, we can directly derive the index of the rotated or flipped image from the index of the original one by bit operations and matrix manipulation. In our performance study, we analyze the time complexity of our proposed strategy and show the efficiency of our proposed strategy according to the simulation results. Moreover, we implement a prototype to validate our proposed strategy.     

Series feature aggregation for content-based image retrieval

Feature aggregation is a critical technique in content-based image retrieval (CBIR) systems that employs multiple visual features to characterize image content. Most previous feature aggregation schemes apply parallel topology, e.g., the linear combination scheme, which suffer from two problems. First, the function of individual visual feature is limited since the ranks of the retrieved images are determined only by the combined similarity. Second, the irrelevant images seriously affect the retrieval performance of feature aggregation scheme since all images in a collection will be ranked. To address these problems, we propose a new feature aggregation scheme, series feature aggregation (SFA). SFA selects relevant images using visual features one by one in series from the images highly ranked by the previous visual feature. The irrelevant images will be effectively filtered out by individual visual features in each stage, and the remaining images are collectively described by all visual features. Experiments, conducted with IAPR TC-12 benchmark image collection (ImageCLEF2006) that contains over 20,000 photographic images and defined queries, have shown that the proposed SFA can outperform conventional parallel feature aggregation schemes.     

Integrated probability function and its application to content-based image retrieval by relevance feedback

In the last few years, we have seen an upsurge of interest in content-based image retrieval (CBIR)—the selection of images from a collection via features extracted from images themselves. Often, a single image attribute may not have enough discriminative information for successful retrieval. On the other hand when multiple features are used, it is hard to determine the suitable weighing factors for various features for optimal retrieval. In this paper, we present a relevance feedback framework with Integrated Probability Function (IPF) which combines multiple features for optimal retrieval. The IPF is based on a new posterior probability estimator and a novel weight updating approach. We perform experiments on 1400 monochromatic trademark images have been performed. The proposed IPF is shown to be more effective and efficient to retrieve deformed trademark images than the commonly used integrated dissimilarity function. The new posterior probability estimator is shown to be generally better than the existing one. The proposed novel weight updating approach by relevance feedback is shown to be better than both the existing scoring approach and the existing ratio approach. In experiments, 95% of the targets are ranked at the top five positions. By two iterations of relevance feedback, retrieval performance can be improved from 75% to over 95%. The IPF and its relevance feedback framework proposed in this paper can be effectively and efficiently used in content-based image retrieval.