Browsing by Author "de Jager, Gerhard"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Open Access
    A machine vision-based approach to measuring the size distribution of rocks on a conveyor belt
    (2004) Mkwelo, Simphiwe; de Jager, Gerhard
    This work involves the development of a vision-based system for measuring the size distribution of rocks on a conveyor belt. The system has applications in automatic control and optimization of milling machines, and the selection of optimal blasting methods in the mining industry. Rock size is initially assumed to be the projected rock surface area due to the constraint imposed by the 2D nature of images. This measurement is facilitated by locating connected rock-edge pixels. Rock edge detection is achieved using a watershed-based segmentation process. This process involves image pre-filtering with edge preserving filters at various degrees of filtering. The output of each filtering stage is retained and marker-driven watersheds are applied on each output resulting to traces of detected rock boundaries. Watershed boundary selection is then applied to select boundaries which are most likely to be rock edges based on rock features. Finally, rock recognition using feature classification is applied to remove non-rock watershed boundaries. The projected rock area distribution of a test-set is measured and compared to corresponding projected areas of manually segmented images. The obtained distributions are found to be similar with an RMS error of 2.37% on the test-set. Finally, sieve data is collected in the form of actual rock size distributions and a quantitative comparison between the actual and machine measured distributions is performed. The overall quantitative result is that the two rock size distributions are significantly different. However, after incorporating a stereology-based correction, hypothesis tests on a 3m belt-cut test-set show that the obtained distributions are similar.
  • Thumbnail Image
    Item
    Open Access
    Computer-assisted detection of lung cancer nudules in medical chest X-rays
    (1992) Borchardt, Wayne Grant; de Jager, Gerhard
    Diagnostic medicine was revolutionized in 1895 with Rontgen's discovery of x-rays. X-ray photography has played a very prominent role in diagnostics of all kinds since then and continues to do so. It is true that more sophisticated and successful medical imaging systems are available. These include Magnetic Resonance Imaging (MRI), Computerized Tomography (CT) and Positron Emission Tomography (PET). However, the hardware instalment and operation costs of these systems remain considerably higher than x-ray systems. Conventional x-ray photography also has the advantage of producing an image in significantly less time than MRI, CT and PET. X-ray photography is still used extensively, especially in third world countries. The routine diagnostic tool for chest complaints is the x-ray. Lung cancer may be diagnosed by the identification of a lung cancer nodule in a chest x-ray. The cure of lung cancer depends upon detection and diagnosis at an early stage. Presently the five-year survival rate of lung cancer patients is approximately 10%. If lung cancer can be detected when the tumour is still small and localized, the five-year survival rate increases to about 40%. However, currently only 20% of lung cancer cases are diagnosed at this early stage. Giger et al wrote that "detection and diagnosis of cancerous lung nodules in chest radiographs are among the most important and difficult tasks performed by radiologists".
  • Thumbnail Image
    Item
    Restricted
    The epistemic properties in a typical engineering science course and its relation to student success: a case study
    (2018) Awodele, Williams Abayomi; Smit, Rene; de Jager, Gerhard
    One of the problems facing South African higher education is the low throughput rates, in particular for students who are educationally disadvantaged. Research studies point to various factors that impact student success, such as educational background and various socio-economic factors. Universities have attempted to address the problem by making available various academic support programmes for entering students. This research project looks at the nature of the knowledge content of the various engineering courses in a university curriculum and its potential impact on students’ performance which might result into low throughput rate. The study, therefore, investigates the epistemic properties of a typical third-year engineering science course in the department of electrical engineering at the University of Cape Town, as a case study. The researcher used the annual departmental results between 2005 and 2013 to identify a specific engineering science course that had repeated high failure rates for ex-ASPECT students compared to the rest of the class. The course lecturer was interviewed and the transcript of the interviews served as the data used in this project. The data generated from the interviews were analysed using the theoretical concept of semantics (semantic gravity and semantic density) which is one of the dimensions of Legitimation Code Theory (LCT) developed by Karl Maton. The analysis of the data uncovered two main issues. Firstly, there is a wide semantic range in the required knowledge and skills in order for the students to be successful in the course. Secondly, the analysis reveals that there is a link between semantic gravity and semantic density in terms of the knowledge that students need to have, understand and master in order to be successful in the course. This study raises the possibility of the epistemic properties of engineering science knowledge being a contributing factor to the underperformance of the ex-ASPECT students in the department of electrical engineering of the University of Cape Town. Suggestions are then given for further studies on finding solutions to the identified problems.