In this paper we describe a computer aided detection (CAD) algorithm for robust detection of polyps in computed tomography (CT) colonography. The devised algorithm identifies suspicious polyp candidate surfaces using the surface normal intersection, Hough transform, 3D histogram analysis, region growing and a convexity test. From these detected surfaces we extract statistical and morphological features in order to evaluate if the surface in question is a polyp or fold. In order to devise the optimal classification scheme the performance of two different classifiers are evaluated when the algorithm is applied to synthetic and real patient data. The experimental results indicate that the overall polyp detection performance shows sensitivity higher than 92% for polyps larger than 5mm with an average of 4.7 to 6.0 false positives per dataset View full abstract»

One important step in the process of colour image segmentation is to reduce the errors caused by image noise and local colour inhomogeneities. This can be achieved by filtering the data with a smoothing operator that eliminates the noise and the weak textures. In this regard, the aim of this paper is to evaluate the performance of two image smoothing techniques designed for colour images, namely bilateral filtering for edge preserving smoothing and coupled forward and backward anisotropic diffusion scheme (FAB). Both techniques are non-linear and have the purpose of eliminating the image noise, reduce weak textures and artefacts and improve the coherence of colour information. A quantitative comparison between them will be evaluated and also the ability of such techniques to preserve the edge information will be investigated. View full abstract»

Accurate segmentation of the myocardium in cardiac magnetic resonance images can be restricted by image noise and low discrimination between the epi-cardium boundary and other organs. Segmentation of the epi-cardium is important for the calculation of left ventricle mass. In this paper we propose a novel method of epi-cardium segmentation, which firstly segments the left ventricle cavity. The epi-cardium boundary is found using the edge information in the image, and where such information is lacking it enhances the shape with the best fitting scaled segment, taken from a database of expertly assisted hand segmented images. In the final stage the segments are connected using a natural closed spline. The method was evaluated using a leave-one-out strategy on 24 volumes and calculates the coefficient of determination as 0.93 and a root mean square of the point to curve error of 1.54 mm when compared to manually segmented images. View full abstract»

An efficient method for real-time periodic interference suppression on telephone lines is proposed. The periodicity of the interference Is exploited by an adaptive phase-locked buffer (APLB), which is used to create the antiphase noise replica. Computer simulations are used to compare the APLB approach with the traditional least mean squares (LMS) algorithm in an adaptive noise cancellation configuration. The new technique outperforms the LMS noise canceller and proves to be a very efficient solution to the power line interference problem View full abstract»

An overview of our recent work on fibre optic sensor systems for structural element characterisation and monitoring is presented. The initial aim has been to explore the feasibility and utility of such fibre optic sensors, and to use them to improve measurements and to obtain results unobtainable by other means in application areas of interest. Two particular applications areas currently under study are the characterisation and testing of pultruded composite beams, and the shape reconstruction of composite panels. The motivation for these projects and their theoretical and experimental status are described. Fibre optic sensor systems to suit these applications have been developed; the main aspects of the development of an all-fibre passive demodulation scheme for in-fibre Bragg grating sensors are presented View full abstract»

Computed tomography colonography (CTC) is a rapidly evolving noninvasive medical investigation that is viewed by radiologists as a potential screening technique for the detection of colorectal polyps. Due to the technical advances in CT system design, the volume of data required to be processed by radiologists has increased significantly, and as a consequence the manual analysis of this information has become an increasingly time consuming process whose results can be affected by inter- and intrauser variability. The aim of this paper is to detail the implementation of a fully integrated CAD-CTC system that is able to robustly identify the clinically significant polyps in the CT data. The CAD-CTC system described in this paper is a multistage implementation whose main system components are: 1) automatic colon segmentation; 2) candidate surface extraction; 3) feature extraction; and 4) classification. Our CAD-CTC system performs at 100% sensitivity for polyps larger than 10 mm, 92% sensitivity for polyps in the range 5 to 10 mm, and 57.14% sensitivity for polyps smaller than 5 mm with an average of 3.38 false positives per dataset. The developed system has been evaluated on synthetic and real patient CT data acquired with standard and low-dose radiation levels. View full abstract»

The accurate identification and recognition of the traffic signs is a challenging problem as the developed systems have to address a large number of imaging problems such as motion artifacts, various weather conditions, shadows and partial occlusion, issues that are often encountered in video traffic sequences that are captured from a moving vehicle. These factors substantially degrade the performance of the existing traffic sign recognition (TSR) systems and in this paper we detail the implementation of a new strategy that entails three distinct computational stages. The first component addresses the robust identification of the candidate traffic signs in each frame of the video sequence. The second component discards the traffic sign candidates that do not comply with stringent shape constraints, and the last component implements the classification of the traffic signs using Support Vector Machines (SVMs). The main novel elements of our TSR algorithm are given by the approach that has been developed for traffic sign classification and by the experimental evaluation that was employed to identify the optimal image attributes that are able to maximize the traffic sign classification performance. The TSR algorithm has been validated using video sequences that include the most important categories of signs that are used to regulate the traffic on the Irish and UK roads, and it achieved 87.6% sign detection, 99.2% traffic sign classification accuracy and 86.7% overall traffic sign recognition. View full abstract»

We will present a cost-effective and flexible realization of high performance computing (HPC) clustering and its potential in solving computationally intensive problems in computer vision. The featured software foundation to support the parallel programming is the GNU parallel Knoppix package with message passing interface (MPI) based Octave, Python and C interface capabilities. The implementation is especially of interest in applications where the main objective is to reuse the existing hardware infrastructure and to maintain the overall budget cost. We will present the benchmark results and compare and contrast the performances of Octave and MATLAB. View full abstract»

In this paper we describe the development of a computationally efficient computer-aided detection (CAD) algorithm based on the statistical features derived from the local colonic surface that are used for the detection of colonic polyps in computed tomography (CT) colonography. The candidate surface voxels were detected and clustered using the surface normal intersection, convexity test, region growing and Hough transform. The main objective of this paper is the selection of the statistical features that optimally capture the convexity of the candidate surface and consequently provide a high discrimination between local surfaces defined by polyps and folds. The developed polyp detection scheme is computationally efficient (typically takes 3.9 minute per dataset) and shows 100% sensitivity for phantom polyps greater than 5 mm and 87.5% sensitivity for real polyps greater than 5 mm with an average of 4.05 false positives per dataset View full abstract»

Hyperspectral data allows the construction of more elaborate models to sample the properties of the nonferrous materials than the standard RGB color representation. In this paper, the nonferrous waste materials are studied as they cannot be sorted by classical procedures due to their color, weight and shape similarities. The experimental results presented in this paper reveal that factors such as the various levels of oxidization of the waste materials and the slight differences in their chemical composition preclude the use of the spectral features in a simplistic manner for robust material classification. To address these problems, the proposed FUSSER (fuzzy spectral and spatial classifier) algorithm detailed in this paper merges the spectral and spatial features to obtain a combined feature vector that is able to better sample the properties of the nonferrous materials than the single pixel spectral features when applied to the construction of multivariate Gaussian distributions. This approach allows the implementation of statistical region merging techniques in order to increase the performance of the classification process. To achieve an efficient implementation, the dimensionality of the hyperspectral data is reduced by constructing bio-inspired spectral fuzzy sets that minimize the amount of redundant information contained in adjacent hyperspectral bands. The experimental results indicate that the proposed algorithm increased the overall classification rate from 44% using RGB data up to 98% when the spectral-spatial features are used for nonferrous material classification. View full abstract»

The author presents key features from an information model for a CAM (computer-aided manufacturing) database that supports flexible manufacture of printed circuit boards and other selected components and products. This model incorporates information from several sources: shop orders, CAD (computer-aided design), bill of materials, and process setup. The essential activities of manufacturing can be subdivided into several information categories. These categories include products, processes, factory structure, factory operations, and factory inventory. The information model identifies the entities and data elements that are associated with each of these categories, as well as the relationships among the entities. Appropriate levels of abstraction enable this model to support a wide variety of products and processes. The resulting relational database implementation is integrated with multiple manufacturing software applications to assist with the operation of a manufacturing facility View full abstract»

The ability to manipulate previously unseen objects under visual control is one of the key tasks in the successful implementation of robotic, automated assembly and adaptive material handling systems. The automation of such complex industrial environments will require the development of machine vision systems that are highly adaptable and capable of dealing with a wide range of variable products. An important group of applications of this type is found in the automated packing and nesting of arbitrary shapes. The aim of this work has been to produce an efficient packing strategy that is flexible enough for a wide variety of industrial uses and which can be implemented using fast moderately priced hardware. A systems approach, as distinct from a purely algorithmic one, has been deliberately adopted since the work is concerned with industrial vision applications in which significant problem constraints exist. This paper also outlines the background to this research, and reviews a selection of industrial packing applications. The packing procedure that has been devised, consists of two major components. The first is a geometric packing technique that is based on morphological image processing operations. This is used in conjunction with a prolog based heuristic packing procedure. Some of the factors considered at the heuristic level include shape ordering and shape orientation, both of which must be carried out prior to the implementation of the geometric packer. The heuristic procedures deal with problem constraints that are specific to a given application View full abstract»

In this paper we present a parameter optimisation procedure that is designed to automatically initialise the number of clusters and the initial colour prototypes required by data space partitioning techniques. The proposed optimisation approach involves a colour saliency measure used in conjunction with a SOM classification procedure. For evaluation purposes, we have integrated the proposed initialisation technique in an unsupervised colour segmentation scheme based on K-Means clustering and the evaluation has been carried out in the context of the unsupervised segmentation of natural images. View full abstract»

This paper considers two design strategies: 1) maximising the use of the context information available from a given task, by the application of a systems engineering approach to the packing problem, and 2) the development of an adaptive packing strategy for random shapes, using morphological and heuristic techniques. The characteristics required in a flexible packing system are summarised. Such a system will consist of two main components. The first will provide a means of manipulating the shape and scene image at a geometric level. The second component will consist of a rule based geometric reasoning unit capable of deciding the ordering and orientation of the shapes to be packed. The heuristic component must also be capable of dealing with the system issues arising from a specific application demand View full abstract»

Histogram transformation defines a class of image processing operations that are widely applied in the implementation of data normalisation algorithms. In this paper we present a new variational approach for image enhancement that has been constructed to alleviate the intensity saturation effects that are introduced by standard contrast enhancement methods based on histogram equalisation. In our work we initially apply total variation (TV) minimisation with a L1 fidelity term to decompose the input image with respect to cartoon and texture components. Contrary to previous works that rely solely on the information encompassed in the distribution of the intensity information, in our approach the texture information is also employed to emphasize the contribution of the local textural features in the contrast enhancement process. This is achieved by implementing a non-linear histogram warping contrast enhancement strategy that is able to maximise the information content in the transformed image. Our experimental study addressed the contrast enhancement of a wide variety of image data and comparative evaluations are provided to illustrate that our method produces better results than conventional contrast enhancement strategies. View full abstract»

Common carotid intima-media thickness (IMT) is a reliable measure of early atherosclerosis - its accurate measurement can be used in the process of evaluating the presence and tracking the progression of disease. The aim of this study is to introduce a novel unsupervised Computer Aided Detection (CAD) algorithm that is able to identify and measure the IMT in 2D ultrasound carotid images. The developed technique relies on a suite of image processing algorithms that embeds a statistical model to identify the two interfaces that form the IMT without any user intervention. The proposed image segmentation scheme is based on a spatially continuous vascular model and consists of several steps including data preprocessing, edge filtering, model selection, edge reconstruction and data refinement. To conduct a quantitative evaluation each image was manually segmented by clinical experts and performance metrics between the segmentation results obtained by the proposed method and the ground truth data were calculated. The experimental results show that the proposed CAD system is robust in accurately estimating the IMT in ultrasound carotid data. View full abstract»

Data smoothing algorithms are commonly applied to reduce the level of noise and eliminate the weak textures contained in digital images. Anisotropic diffusion algorithms form a distinct category of noise removal approaches that implement the smoothing process locally in agreement with image features such as edges that are typically determined by applying diverse partial differential equation (PDE) models. While this approach is opportune since it allows the implementation of feature-preserving data smoothing strategies, the inclusion of the PDE models in the formulation of the data smoothing process compromises the performance of the anisotropic diffusion schemes when applied to data corrupted by non-Gaussian and multimodal image noise. In this study the authors first evaluate the positive aspects related to the inclusion of a multi-scale edge detector based on the generalisation of the Di Zenzo operator into the formulation of the anisotropic diffusion process. Then, a new approach that embeds vector median filtering into discrete implementation of the anisotropic diffusion is introduced to improve the performance of the noise removal algorithm when applied to multimodal noise suppression. To evaluate the performance of the proposed data smoothing strategy, a large number of experiments on various types of digital images corrupted by multimodal noise were conducted. View full abstract»

We present a preprocessing and segmentation scheme designed to address the particular difficulties encountered in the analysis of magnetic resonance cholangiopancreatography (MRCP) data, as a precursor to the application of computer assisted diagnosis (CAD) techniques. MRCP generates noisy, low resolution, non-isometric data which often exhibits significant greylevel inhomogeneities. This combination of characteristics results in data volumes in which reliable segmentation and analysis are difficult to achieve. In this paper we describe a data processing approach developed to overcome these difficulties and allow for the effective application of automated CAD procedures in the analysis of the biliary tree and pancreatic duct in MRCP examinations. View full abstract»

The robust identification and measurement of the intima media thickness (IMT) has a high clinical relevance because it represents one of the most precise predictors used in the assessment of potential future cardiovascular events. To facilitate the analysis of arterial wall thickening in serial clinical investigations, in this paper we have developed a novel fully automatic algorithm for the segmentation, measurement, and tracking of the intima media complex (IMC) in B-mode ultrasound video sequences. The proposed algorithm entails a two-stage image analysis process that initially addresses the segmentation of the IMC in the first frame of the ultrasound video sequence using a model-based approach; in the second step, a novel customized tracking procedure is applied to robustly detect the IMC in the subsequent frames. For the video tracking procedure, we introduce a spatially coherent algorithm called adaptive normalized correlation that prevents the tracking process from converging to wrong arterial interfaces. This represents the main contribution of this paper and was developed to deal with inconsistencies in the appearance of the IMC over the cardiac cycle. The quantitative evaluation has been carried out on 40 ultrasound video sequences of the common carotid artery (CCA) by comparing the results returned by the developed algorithm with respect to ground truth data that has been manually annotated by clinical experts. The measured IMT_mean ± standard deviation recorded by the proposed algorithm is 0.60 mm ± 0.10, with a mean coefficient of variation (CV) of 2.05%, whereas the corresponding result obtained for the manually annotated ground truth data is 0.60 mm ± 0.11 with a mean CV equal to 5.60%. The numerical results reported in this paper indicate that the proposed algorithm is able to correctly segment and track the IMC in ultrasound CCA video sequences, and we were encouraged by the stability of our technique when applied - o data captured under different imaging conditions. Future clinical studies will focus on the evaluation of patients that are affected by advanced cardiovascular conditions such as focal thickening and arterial plaques. View full abstract»

In this paper, we propose a new manifold representation for visual speech recognition. The developed system consists of three main steps: a) lip extraction from input video data, b) generate the expectation-maximization PCA (EMPCA) manifolds for the entire image sequence and perform manifold interpolation and re-sampling, c) classify the manifolds using a HMM classifier to identify the words described by the lips motions in the input video sequence. View full abstract»

This paper discusses the issues involved with the development and implementation of an on-line postgraduate course for remote-access students. This is especially relevant for students who wish to pursue postgraduate qualifications, or to update their skill base, while continuing with their career. Although remote-access education would not be considered by the author as the delivery method of choice for the majority of an engineering student's educational needs, there will always be niche educational demands that can be addressed by such an approach. Although the electronic presentation of course notes via the Internet is becoming more commonplace, the ideas outlined in this paper go beyond this basic concept. The emphasis of any remote-access-based educational strategy has to be on the interaction between the tutor and the students, and not on note presentation View full abstract»

This paper describes a method of visual tracking using an `active-mesh' that is automatically created and configured directly from a single frame of an image sequence. The aim of this approach is to perform visual tracking in unconstrained motion environments, allowing movement of the camera, the scene and even the inclusion of background-independent moving objects View full abstract»

The aim of this paper is to detail the development of a novel tracking framework that is able to extract the cell motility indicators and to determine the cellular division (mitosis) events in large time-lapse phase-contrast image sequences. To address the challenges induced by nonstructured (random) motion, cellular agglomeration, and cellular mitosis, the process of automatic (unsupervised) cell tracking is carried out in a sequential manner, where the interframe cell association is achieved by assessing the variation in the local cellular structures in consecutive frames of the image sequence. In our study, a strong emphasis has been placed on the robust use of the topological information in the cellular tracking process and in the development of targeted pattern recognition techniques that were designed to redress the problems caused by segmentation errors, and to precisely identify mitosis using a backward (reversed) tracking strategy. The proposed algorithm has been evaluated on dense phase-contrast cellular data and the experimental results indicate that the proposed algorithm is able to accurately track epithelial and endothelial cells in time-lapse image sequences that are characterized by low contrast and high level of noise. Our algorithm achieved 86.10% overall tracking accuracy and 90.12% mitosis detection accuracy. View full abstract»

The robust identification of the traffic signs represents the first and one of the most important steps in the development of a traffic sign recognition (TSR) system. Traffic signs detection usually involves a color segmentation process that uses the information related to the chromatic properties of the road signs. Since the traffic video data is captured in diverse road and weather conditions, the problem relating to traffic sign detection is quite challenging. Among several issues that need to be addressed during this processing stage, the problem generated by mutually occluding traffic signs (mutual occlusion occurs when one traffic sign partially occludes the surface of other road signs) that are attached to the same pole require special attention. In these situations the color segmentation process fails to correctly identify the regions that are associated with the traffic signs. These traffic sign detection failures compromise the performance of other stages of the TSR system and in this paper we propose two approaches that address the segmentation of mutually occluding traffic signs. The first approach uses the information associated with the inner parts of the traffic signs, while the second approach applies the watershed transform to identify the signs that have their borders in contact or are mutually occluding. View full abstract»