Catálogo de publicaciones - libros

In the paper, we proposed a novel feature descriptor using over-complete wavelet transform and wavelet domain based fractal signature for texture image analysis and retrieval. Traditionally, discrete wavelet frame took the first order derivative of smoothing function into account, which is equivalent to Canny edge detection, with the specific case using Gaussian function as smoothing function. The second order derivative Spline Wavelet has more stronger ability to distinguish the variation of the edge width than the first order one. The over-complete B-Spline wavelet scheme is discussed and the finite impulse response of over-complete wavelet transform is also represented in the paper. In feature extraction phase, 56 dimensional statistical features, including means and variances in positive and negative parts of wavelet coefficients, are extracted respectively. At the same time, the fractal signature based on the fractal surface area function in a Besov space is very accurate and robust for gray scale texture classification so that 24 dimensional over-complete wavelet based fractal feature is extracted. Experimental results have shown that the proposed method is reasonable to describe the characteristics of the texture in temporal-frequent and fractal domains and can achieve the highest retrieval rate comparing with Gabor filter, first order derivative over-complete wavelet transformation, and some other pyramid-structured wavelet transformation considered.

This paper presents a region-based image retrieval (RBIR) system in which users can choose specific regions as the query. Our goal is to assist the user to formulate more precise queries with which the retrieval system can focus on the user’s interested part. In this work, images are partitioned into a set of regions by using the watershed segmentation. Color-size histogram and Gabor texture features are extracted from each watershed region. We propose a scheme of region filtering based on individual features, rather than integrating different features, to reduce the computational load of the image retrieval. This paper also defines the dissimilarity measure of images, and therefore relevance feedback is used for improving our retrieval. Finally we describe some experimental results of our RBIR system.

This paper describes an ongoing project which seeks to contribute to a wider understanding of the realities of bridging the semantic gap in visual image retrieval. A comprehensive survey of the means by which real image retrieval transactions are realised is being undertaken. An image taxonomy has been developed, in order to provide a framework within which account may be taken of the plurality of image types, user needs and forms of textual metadata. Significant limitations exhibited by current automatic annotation techniques are discussed, and a possible way forward using ontologically supported automatic content annotation is briefly considered as a potential means of mitigating these limitations.

This paper describes a simple framework for automatically annotating images using non-parametric models of distributions of image features. We show that under this framework quite simple image properties such as global colour and texture distributions provide a strong basis for reliably annotating images. We report results on subsets of two photographic libraries, the Corel Photo Archive and the Getty Image Archive. We also show how the popular Earth Mover’s Distance measure can be effectively incorporated within this framework.

Automatic image annotation has attracted a lot of attention recently as a method for facilitating semantic indexing and text-based retrieval of visual content. In this paper, we propose the use of multiple Self-Organizing Maps in modeling various semantic concepts and annotating new input images automatically. The effect of the semantic gap is compensated by annotating multiple images concurrently, thus enabling more accurate estimation of the semantic concepts’ distributions. The presented method is applied to annotating images from a freely-available database consisting of images of different semantic categories.

Performance of state-of-the-art image retrieval systems is strongly limited due to the difficulty of accurately relating semantics conveyed by images to low-level extracted features. Moreover, dealing with the problem of combining modalities for querying is of huge importance in forthcoming retrieval methodologies and is the only solution for achieving significant retrieval performance on image documents. This paper presents an architecture addressing both of these issues which is based on an expressive formalism handling high-level image descriptions. First, it features a multi-facetted conceptual framework which integrates semantics and signal characterizations and operates on image objects (abstractions of visual entities within a physical image) in an attempt to perform indexing and querying operations beyond trivial low-level processes and region-based frameworks. Then, it features a query-by-example framework based on high-level image descriptions instead of their extracted low-level features and operate both on semantics and signal features. The flexibility of this module and the rich query language it offers, consisting of both boolean and quantification operators, lead to optimized user interaction and increased retrieval performance. Experimental results on a test collection of 2500 images show that our approach gives better results in terms of recall and precision measures than state-of-the-art frameworks which couple loosely keyword-based query modules and relevance feedback processes operating on low-level features.

The vector-space retrieval model and Latent Semantic Indexing approaches to retrieval have been used heavily in the field of text information retrieval over the past years. The use of these approaches in image retrieval, however, has been somewhat limited. In this paper, we present methods for using these techniques in combination with an invariant image representation based on local descriptors of salient regions. The paper also presents an evaluation in which the two techniques are used to find images with similar semantic labels.

Recently many researchers are interested in in an image, which are useful for efficient image matching based on them and bridging the semantic gap between higher concept of users and low-level image features. In this paper, we introduce a computational approach that classifies an object of interest into a natural or a man-made class, which can be of great interest for semantic indexing applications processing very large image databases. We first show that Gabor energy maps for man-made objects tend to have dominant orientation features through analysis of Gabor filtering results for many object images. Then a sum of Gabor orientation energy differences is proposed as a classification measure, which shows a classification accuracy of 82.9% in a test with 2,600 object images.

A new method for image object recognition is proposed. The complicated relation between the visual features and the recognizing result are modeled using evidence theory in the proposed method. Given a recognition task, new method constructs multiple SVMs each for a single feature, and then a modified combination rule is utilized to fuse initial results from multiple SVMs to a more reliable result as the initial results often conflict with each other. In this way, the influence of different features is tuned properly, thus the system may adapt itself to different recognition tasks. Experiments demonstrate the effectiveness of the proposed method.

Principle Component Analysis (PCA) technique is an important and well-developed area of image recognition and to date many linear discrimination methods have been put forward. Despite these efforts, there persist in the traditional PCA some weaknesses. In this paper, we propose new PCA-based methods that can improve the performance of the traditional PCA and two-dimensional PCA (2DPCA) approaches. In face recognition where the training data are labeled, a projection is often required to emphasize the discrimination between the clusters. Both PCA and 2DPCA may fail to accomplish this, no matter how easy the task is, as they are unsupervised techniques. The directions that maximize the scatter of the data might not be as adequate to discriminate between clusters. So we proposed new PCA-based schemes which can straightforwardly take into consideration data labeling, and makes the performance of recognition system better. Experiment results show our method achieves better performance in comparison with the traditional PCA and 2DPCA approaches with the complexity nearly as same as that of PCA and 2DPCA methods.