Dimitris A. Karras

Computer-aided tumor detection in endoscopic video using color wavelet features

We present an approach to the detection of tumors in colonoscopic video. It is based on a new color feature extraction scheme to represent the different regions in the frame sequence. This scheme is built on the wavelet decomposition. The features named as color wavelet covariance (CWC) are based on the covariances of second-order textural measures and an optimum subset of them is proposed after the application of a selection algorithm. The proposed approach is supported by a linear discriminant analysis (LDA) procedure for the characterization of the image regions along the video frames. The whole methodology has been applied on real data sets of color colonoscopic videos. The performance in the detection of abnormal colonic regions corresponding to adenomatous polyps has been estimated high, reaching 97% specificity and 90% sensitivity.

CoLD: a versatile detection system for colorectal lesions in endoscopy video-frames

In this paper, we present CoLD (colorectal lesions detector) an innovative detection system to support colorectal cancer diagnosis and detection of pre-cancerous polyps, by processing endoscopy images or video frame sequences acquired during colonoscopy. It utilizes second-order statistical features that are calculated on the wavelet transformation of each image to discriminate amongst regions of normal or abnormal tissue. An artificial neural network performs the classification of the features. CoLD integrates the feature extraction and classification algorithms under a graphical user interface, which allows both novice and expert users to utilize effectively all systems functions. It has been developed in close cooperation with gastroenterology specialists and has been tested on various colonoscopy videos. The detection accuracy of the proposed system has been estimated to be more than 95%. As it has been resulted, it can be used as a supplementary diagnostic tool for colorectal lesions.

A new class of Zernike moments for computer vision applications

A Modified Direct Method for the computation of the Zernike moments is presented in this paper. The presence of many factorial terms, in the direct method for computing the Zernike moments, makes their computation process a very time consuming task. Although the computational power of the modern computers is impressively increasing, the calculation of the factorial of a big number is still an inaccurate numerical procedure. The main concept of the present paper is that, by using Stirlings Approximation formula for the factorial and by applying some suitable mathematical properties, a novel, factorial-free direct method can be developed. The resulted moments are not equal to those computed by the original direct method, but they are a sufficiently accurate approximation of them. Besides, their variability does not affect their ability to describe uniquely and distinguish the objects they represent. This is verified by pattern recognition simulation examples.

An efficient constrained training algorithm for feedforward networks

A novel algorithm is presented which supplements the training phase in feedforward networks with various forms of information about desired learning properties. This information is represented by conditions which must be satisfied in addition to the demand for minimization of the usual mean square error cost function. The purpose of these conditions is to improve convergence, learning speed, and generalization properties through prompt activation of the hidden units, optimal alignment of successive weight vector offsets, elimination of excessive hidden nodes, and regulation of the magnitude of search steps in the weight space. The algorithm is applied to several small- and large-scale binary benchmark training tasks, to test its convergence ability and learning speed, as well as to a large-scale OCR problem, to test its generalization capability. Its performance in terms of percentage of local minima, learning speed, and generalization ability is evaluated and found superior to the performance of the backpropagation algorithm and variants thereof taking especially into account the statistical significance of the results.

An efficient constrained learning algorithm with momentum acceleration

An algorithm for efficient learning in feedforward networks is presented. Momentum acceleration is achieved by solving a constrained optimization problem using nonlinear programming techniques. In particular, minimization of the usual mean square error cost function is attempted under an additional condition for which the purpose is to optimize the alignment of the weight update vectors in successive epochs. The algorithm is applied to several benchmark training tasks (exclusive-or, encoder, multiplexer, and counter problems). Its performance, in terms of learning speed and scalability properties, is evaluated and found superior to the performance of reputedly fast variants of the back-propagation algorithm in the above benchmarks.

Fault tree analysis and fuzzy expert systems: Early warning and emergency response of landfill operations

In this paper we argue that Early Warning Systems for engineering facilities can be developed by combining and integrating existing technologies and theories. As example, we present an efficient integration of fuzzy expert systems, fault tree analysis and Worldwide Web technologies to their application in the development of the Landfill Operation Management Advisor (LOMA), a novel early warning and emergency response system for solid waste landfill operations. The aim of LOMA is to provide assistance to landfill managers on their efforts in preventing accidents and operational problems and to help them to develop emergency response plans if these operational problems shall occur. Additional aim is to disseminate information and knowledge to the public on landfill operational problems and their adverse effects. This aim is related to solid waste organizations that have to accord with legislations which are similar to the European Unions EC Directive (2003/4/EC) on Public Access to Environmental Information. When using LOMA, the user first describes the working conditions at the landfill. Then, based on this description, LOMA informs user about the potential operational problems. Afterwards, it analyzes the operational problems in more detail and it estimates the possibility of their occurrence. Finally, it provides advice on how to prevent them and how to respond if any of them occurs. This paper thoroughly investigates LOMA development as well as its integral methodologies and validates it by outlining its performance in test cases that were performed by experts during the operation of a real landfill as well as in test cases extracted from a specially constructed database with synthetic events.

On neural network techniques in the secure management of communication systems through improving and quality assessing pseudorandom stream generators

Random components play an especially important role in the management of secure communication systems, with emphasis on the key management of cryptographic protocols. For this reason, the existence of strong pseudo random number generators is highly required. This paper presents novel techniques, which rely on Artificial Neural Network (ANN) architectures, to strengthen traditional generators such as IDEA and ANSI X.9 based on 3DES and IDEA. Additionally, this paper proposes a non-linear test method for the quality assessment of the required non-predictability property, which relies on feedforward neural networks. This non-predictability test method along with commonly used empirical tests based on statistics is proposed as a methodology for quality assessing strong pseudorandom stream generators. By means of this methodology, traditional and Neural Network based pseudorandom stream generators are evaluated. The results show that the proposed generators behave significantly better than the traditional ones, in particular, in terms of non-predictability.

Detection of lesions in endoscopic video using textural descriptors on wavelet domain supported by artificial neural network architectures

Video processing for classification applications in medical imaging is an area with great importance. In this paper a framework for classification of suspicious lesions using the video produced during an endoscopic session is presented. The proposed approach is based on a feature extraction scheme that uses second order statistical information of the wavelet transformation. These features are used as input to a multilayer feedforward neural network (MFNN) architecture, which has been trained using features of normal and tumor regions. The system uses a limited number of frames with a rather small population of training vectors. The classification results are promising, since the system has been proven to be capable to classify and locate regions, that correspond to lesions with a success of 94 up to 99%, in a sequence of the video-frames. The proposed methodology can be used as a valuable diagnostic tool that may assist physicians to identify possible tumor regions or malignant formations.

Pattern classification by using improved wavelet Compressed Zernike Moments

In this paper, an improved Feature Extraction Method (FEM), which selects discriminative feature sets able to lead to high classification rates in pattern recognition tasks, is presented. The resulted features are the wavelet coefficients of an improved compressed signal, consisting of the Zernike moments amplitudes. By applying a straightforward methodology, it is aimed to construct optimal feature vectors in the sense of vector dimensionality and information content for classification purposes. The resulting surrogate feature vector is of lower dimensionality than the original Zernike moment feature vector and thus more appropriate for pattern recognition tasks. Appropriate validation tests have been arranged, in order to investigate the performance of the proposed algorithm by measuring the discriminative power of the new feature vectors despite the information loss.

2005 Special Issue: Efficient information theoretic strategies for classifier combination, feature extraction and performance evaluation in improving false positives and false negatives for spam e-mail filtering

Spam emails are considered as a serious privacy-related violation, besides being a costly, unsolicited communication. Various spam filtering techniques have been so far proposed, mainly based on Naïve Bayesian algorithms. Other Machine Learning algorithms like Boosting trees, or Support Vector Machines (SVM) have already been used with success. However, the number of False Positives (FP) and False Negatives (FN) resulting through applying various spam e-mail filters still remains too high and the problem of spam e-mail categorization cannot be solved completely from a practical viewpoint. In this paper, we propose a novel approach for spam e-mail filtering based on efficient information theoretic techniques for integrating classifiers, for extracting improved features and for properly evaluating categorization accuracy in terms of FP and FN. The goal of the presented methodology is to empirically but explicitly minimize these FP and FN numbers by combining high-performance FP filters with high-performance FN filters emerging from a previous work of the authors [Zorkadis, V., Panayotou, M., & Karras, D. A. (2005). Improved spam e-mail filtering based on committee machines and information theoretic feature extraction. Proceedings of the International Joint Conference on Neural Networks, July 31-August 4, 2005, Montreal, Canada]. To this end, Random Committee-based filters along with ADTree-based ones are efficiently combined through information theory, respectively. The experiments conducted are of the most extensive ones so far in the literature, exploiting widely accepted benchmarking e-mail data sets and comparing the proposed methodology with the Naive Bayes spam filter as well as with the Boosting tree methodology, the classification via regression and other machine learning models. It is illustrated by means of novel information theoretic measures of FP & FN filtering performance that the proposed approach is very favorably compared to the other rival methods. Finally, it is found that the proposed information theoretic Boolean features present a remarkably high spam categorization performance.