Christos Theoharatos

A generic scheme for color image retrieval based on the multivariate Wald-Wolfowitz test

In this study, a conceptually simple, yet flexible and extendable strategy to contrast two different color images is introduced. The proposed approach is based on the multivariate Wald-Wolfowitz test, a nonparametric test that assesses the commonality between two different sets of multivariate observations. It provides an aggregate gauge of the match between color images, taking into consideration all the (selected) low-level characteristics, while alleviating correspondence issues. We show that a powerful measure of similarity between two color images can emerge from the statistical comparison of their representations in a properly formed feature space. For the sake of simplicity, the RGB-space is selected as the feature space, while we are experimenting with different ways to represent the images within this space. By altering the feature-extraction implementation, complementary ways to portray the image content appear. The reported results, from the application on a diverse collection of images, clearly demonstrate the effectiveness of our method, its superiority over previous methods, and suggest that even further improvements can be achieved along the same line of research. It is not only the unifying character that makes our strategy appealing, but also the fact that the retrieval performance does not increase continuously with the amount of details in the image representation. The latter sets an upper limit to the computational demands and reminds of performance plateaus reached by novel approaches in information retrieval.

Multivariate image similarity in the compressed domain using statistical graph matching

We address the problem of image similarity in the compressed domain, using a multivariate statistical test for comparing color distributions. Our approach is based on the multivariate Wald-Wolfowitz test, a nonparametric test that assesses the commonality between two different sets of multivariate observations. Using some pre-selected feature attributes, the similarity measure provides a comprehensive estimate of the match between different images based on graph theory and the notion of minimal spanning tree (MST). Feature extraction is directly provided from the JPEG discrete cosine transform (DCT) domain, without involving full decompression or inverse DCT. Based on the zig-zag scheme, a novel selection technique is introduced that guarantees images enhanced invariance to geometric transformations. To demonstrate the performance of the proposed method, the application on a diverse collection of images has been systematically studied in a query-by-example image retrieval task. Experimental results show that a powerful measure of similarity between compressed images can emerge from the statistical comparison of their pattern representations.

Rapid and brief communication: Color edge detection using the minimal spanning tree

In this study, the edge detection task in vector-valued images is examined as a clustering problem. Using samples within a data window, the minimal spanning tree (MST) provides the ordering of multivariate observations and facilitates the identification of similar classes. The edge detector parameters like edge strength, type and orientation are subsequently determined from the clustered data. Experiments and comparisons are performed, revealing the enhanced performance of the proposed approach.

A framework for gait-based recognition using Kinect

Dynamic characteristics of gait are utilized for identity and gender recognition.A new publicly available dataset for gait recognition is presented.Our algorithm can operate extremely well with a small sample training size.The proposed framework follows a biologicaly inspired human motion analysis.The hierarchy of feature representations results in a high level description. Gait analysis has gained new impetus over the past few years. This is mostly due to the launch of low cost depth cameras accompanied with real time pose estimation algorithms. In this work we focus on the problem of human gait recognition. In particular, we propose a modification of a framework originally designed for the task of action recognition and apply it to gait recognition. The new scheme allows us to achieve complex representations of gait sequences and thus express efficiently the dynamic characteristics of human walking sequences. The representational power of the suggested model is evaluated on a publicly available dataset where we achieved up to 93.29% identification rate, 3.1% EER on the verification task and 99.11% gender recognition rate.

An FPGA-Based Hardware Implementation of Configurable Pixel-Level Color Image Fusion

Image fusion has attracted a lot of interest in recent years. As a result, different fusion methods have been proposed mainly in the fields of remote sensing and computer (e.g., night) vision, while hardware implementations have been also presented to tackle real-time processing in different application domains. In this paper, a linear pixel-level fusion method is employed and implemented on a field-programmable-gate-array-based hardware system that is suitable for remotely sensed data. Our work incorporates a fusion technique (called VTVA) that is a linear transformation based on the Cholesky decomposition of the covariance matrix of the source data. The circuit is composed of different modules, including covariance estimation, Cholesky decomposition, and transformation ones. The resulted compact hardware design can be characterized as a linear configurable implementation since the color properties of the final fused color can be selected by the user in a way of controlling the resulting correlation between color components.

Color image segmentation using Laplacian eigenmaps

The novel technique of Laplacian eigenmaps (LE) is studied as a means of improving the clustering-based segmentation of color images. Taking advantage of the ability of the LE algorithm to learn the actual manifold of the multivariate data, a computationally efficient scheme is introduced. After embedding the local image characteristics, extracted from overlapping regions, in a high-dimensional feature space, the skeleton of the intrinsically low-dimensional manifold is constructed using spectral graph theory. Using the LE-based dimensionality reduction technique, a low-dimensional map is computed in which the variations of the local image characteristics are presented in the context of global image variation. The nonlinear projections on this map serve as inputs to the Fuzzy C-Means (FCM) algorithm, boosting its clustering performance significantly. The final segmentation is produced by a simple labeling scheme. The application of the presented approach to color images is very encouraging and illustrates the effectiveness of the performance over alternative methods.

On the perceptual organization of image databases using cognitive discriminative biplots

A human-centered approach to image database organization is presented in this study. The management of a generic image database is pursued using a standard psychophysical experimental procedure followed by a well-suited data analysis methodology that is based on simple geometrical concepts. The end result is a cognitive discriminative biplot, which is a visualization of the intrinsic organization of the image database best reflecting the users perception. The discriminating power of the introduced cognitive biplot constitutes an appealing tool for image retrieval and a flexible interface for visual data mining tasks. These ideas were evaluated in two ways. First, the separability of semantically distinct image classes was measured according to their reduced representations on the biplot. Then, a nearest-neighbor retrieval scheme was run on the emerged low-dimensional terrain to measure the suitability of the biplot for performing content-based image retrieval (CBIR). The achieved organization performance when compared with the performance of a contemporary system was found superior. This promoted the further discussion of packing these ideas into a realizable algorithmic procedure for an efficient and effective personalized CBIR system.

Combining self-organizing neural nets with multivariate statistics for efficient color image retrieval

An efficient novel strategy for color-based image retrieval is introduced. It is a hybrid approach combining a data compression scheme based on self-organizing neural networks with a nonparametric statistical test for comparing vectorial distributions. First, the color content in each image is summarized by representative RGB-vectors extracted using the Neural-Gas network. The similarity between two images is then assessed as commonality between the corresponding representative color distributions and quantified using the multivariate Wald-Wolfowitz test. Experimental results drawn from the application to a diverse collection of color images show a significantly improved performance (approximately 10-15% higher) relative to both the popular, simplistic approach of color histogram and the sophisticated, computationally demanding technique of Earth Movers Distance.

Distributional-based texture classification using non-parametric statistics

Texture classification is an important problem in image analysis. In the present study, an efficient strategy for classifying texture images is introduced and examined within a distributional-statistical framework. Our approach incorporates the multivariate Wald–Wolfowitz test (WW-test), a non-parametric statistical test that measures the similarity between two different sets of multivariate data, which is utilized here for comparing texture distributions. By summarizing the texture information using standard feature extraction methodologies, the similarity measure provides a comprehensive estimate of the match between different images based on graph theory. The proposed “distributional metric” is shown to handle efficiently the texture-space dimensionality and the limited sample size drawn from a given image. The experimental results, from the application on a typical texture database, clearly demonstrate the effectiveness of our approach and its superiority over other well-established texture distribution (dis)similarity metrics. In addition, its performance is used to evaluate several approaches for texture representation. Even though the classification results are obtained on grayscale images, a direct extension to color-based ones can be straightforward.

Performance Evaluation of Image Fusion Methods

The recent advances in sensor technology, microelectronics and multisensor systems have motivated researchers towards processing techniques that combine the information obtained from different sensors. For this purpose a large number of image fusion techniques [Mukhopadhyay & Chanda, 2001; Pohl & van Genderen, 1998, Tsagaris & Anastassopoulos, 2005; Piella, 2003] have been proposed in the fields of remote sensing, medical diagnostics, military applications, surveillance etc. The main goal of these image fusion techniques is to provide a compact representation of the multiple input images into a single grayscale one that contains all the important original features. Such an image provides improved interpretation capabilities but can also be used for further computer processing tasks, like feature extraction or classification. The performance of image fusion techniques is sometimes assessed subjectively by human visual inspection. The reproduction of subjective tests is often time-consuming and expensive, while the exact same conditions for the test cannot be guaranteed. This has led to a rising demand for objective measures in order to rapidly compare the results obtained with different algorithms or to obtain optimal settings for a specific fusion algorithm. The objective evaluation of the performance of pixel level fusion methods is addressed in this book chapter. The image fusion processes can be classified in grayscale or color methods depending on the resulting fused image. For this purpose the general framework of objective evaluation of image fusion is discussed and different fusion measures are discussed. Moreover, a global measure for grayscale image fusion schemes, IFPM, based on information theory is presented. The measure employs mutual and conditional mutual information in order to assess and represent the amount of information transferred from the source images to the final fused grayscale image. Accordingly, the common information contained in the source images is considered only once in the performance evaluation procedure. The experimental results clarify the applicability of the IFPM measure in comparing different fusion methods or in optimizing the parameters of a specific algorithm. Moreover, a measure for objectively assessing the performance of color image fusion methods, CIFM, is presented in this chapter. Two different aspects are considered in establishing the measure, namely the amount of common information between the source images and the final fused image as well as the distribution of color information in the final