Derek Molloy

A Survey of Computer-Based Deformable Models

This paper presents a survey of the research carried out to date in the area of computer-based deformable modelling. Due to their cross-disciplinary nature, deformable modelling techniques have been the subject of vigorous research over the past three decades and have found numerous applications in the fields of machine vision (image analysis, image segmentation, image matching, and motion tracking), visualisation (shape representation and data fitting), and computer graphics (shape modelling, simulation, and animation). Previous review papers have been field/application specific and have therefore been limited in their coverage of techniques. This survey focuses on general deformable models for computer-based modelling, which can be used for computer graphics, visualisation, and various image processing applications. The paper organizes the various approaches by technique and provides a description, critique, and overview of applications for each. Finally, the state of the art of deformable modelling is discussed, and areas of importance for future research are suggested.

Machine Vision Algorithms in Java

The first € price and the £ and

Screening for Objectionable Images: A Review of Skin Detection Techniques

price are net prices, subject to local VAT. Prices indicated with * include VAT for books; the €(D) includes 7% for Germany, the €(A) includes 10% for Austria. Prices indicated with ** include VAT for electronic products; 19% for Germany, 20% for Austria. All prices exclusive of carriage charges. Prices and other details are subject to change without notice. All errors and omissions excepted. P.F. Whelan, D. Molloy Machine Vision Algorithms in Java

An Introduction to Machine Vision

In recent times advances in data communication technologies, in particular high speed Internet connections and 3G mobile phones, have introduced major concern about the relative ease of access to unsuitable material. This academic and commercial problem of real time detection of unsuitable images communicated by phone and Internet has grown steadily over the last number of years. This review paper is presented in three parts. The first part compares and contrasts the most significant skin detection techniques, feature extraction techniques and classification methods. The second gives an analysis of the significant test results. This review paper examines thirty-three of the most recent techniques along with their specific conditions. Finally, this paper concludes by identifying future challenges and briefly summarizes the proposed features of an optimal system for future implementation with a suggested solution to the affects of lighting variations on the colour of skin pixels.

Colour Image Analysis

The purpose of this chapter is to introduce the reader to the basic principles of machine vision. In this discussion the differences between computer, machine and human vision are highlighted. In doing so, we draw attention to the key elements involved in machine vision systems engineering. While this book concentrates on the software aspects of the design cycle, this task cannot be taken in isolation. Successful application of vision technology to real-world problems requires an appreciation of all the issues involved.

Application of machine vision technology to the development of aids for the visually impaired

Historically, machine vision has been applied to monochromatic objects, or those in which colour’ differences are visible as changes in intensity when they are viewed using a monochrome camera. Despite the obvious importance of colour in manufactured goods, machine vision systems capable of processing coloured images are less common. Three major reasons have been put forward for this (Batchelor & Whelan 1997)

Optic Flow Based Occlusion Analysis for Cell Division Detection

This paper presents an experimental system for the combination of three areas of visual cues to aid recognition. The research is aimed at investigating the possibility of using this combination of information for scene description for the visually impaired. The areas identified as providing suitable visual cues are motion, shape and color. The combination of these provide a significant amount of information for recognition and description purposes by machine vision equipment and also allow the possibility of giving the user a more complete description of their environment. Research and development in the application of machine vision technologies to rehabilitative technologies has generally concentrated on utilizing a single visual cue. A novel method for the combination of techniques and technologies successful in machine vision is being explored. Work to date has concentrated on the integration of shape recognition, motion tracking, color extraction, speech synthesis, symbolic programming and auditory imaging of colors.

A Web-Based Training System for Remote Access Mammography Screening

The computer vision domain has seen increasing attention in the design of automated tools for cellular biology researchers. In addition to quantitative analysis on whole populations of cells, identification of the cell division events is another important topic. In this research, a novel fully automated image-based cell-division-detection approach is proposed. Differing from most of the existing approaches that exploit training-based or image-based segmentation methods, the main idea of the proposed approach is detecting cell divisions using a motion based occlusion analysis process. Testing has been performed on different types of cellular datasets, including fluorescence images and phase-contrast data, and it has confirmed the effectiveness of the proposed method.

Model&Motion based Shape Tracking in Large-Scale Cellular Datasets

Breast cancer is a major cause of cancer related death worldwide. Screening for breast cancer is achieved using mammography. In this research, we propose a web-based training system for remote access mammography in order to train the radiologists for improving their skills and experiences in interpretation of mammograms, so as to reduce the misdiagnosis. At this stage, we have developed a software viewing tool, called Viewer that allows user to teach themselves by displaying the images on it and drawing the overlay on images.

Oriented geodesic distance based non-local regularisation approach for optic flow estimation

This material proposes a model&motion based new cell tracking framework, where two main tasks are targeted, including shape segmentation in low contrast images, and estimation of cell trajectories in clutter environment. To be concrete, the parametric snake model and the optic-flow technique are seamlessly combined to cooperate with each other. By that means, the shortcomings of each side are addressed in the process of simultaneously tracking cell deformation and movement. By experiments on real cellular datasets, the proposed approach has been demonstrated to be well applicable for jointly segmenting and tracking cells, particularly under multiple challenges, such as low quality images, ambiguous cell boundaries, and closely touching cells in high concentration.