Showing items 1 - 12 of 12

Your selections:

A study on Hough transform-based fingerprint alignment algorithms

An investigation into the parameters influencing neural network based facial recognition

  • Authors: Oerder, Stacy-Ann
  • Date: 2012-09-05
  • Subjects: Face perception - Data processing , Neural networks (Computer science) , Image processing - Digital techniques , Pattern recognition systems
  • Type: Thesis
  • Identifier: uj:9584 , http://hdl.handle.net/10210/7007
  • Description: D.Ing. , This thesis deals with an investigation into facial recognition and some variables that influence the performance of such a system. Firstly there is an investigation into the influence of image variability on the overall recognition performance of a system and secondly the performance and subsequent suitability of a neural network based system is tested. Both tests are carried out on two distinctly different databases, one more variable than the other. The results indicate that the greater the amount of variability the more negatively affected is the performance rating of a specific facial recognition system. The results further indicate the success with the implementation of a neural network system over a more conventional statistical system.
  • Full Text:

Computer-aided detection of tuberculosis in chest radiographs

Image analysis using digitized video input

  • Authors: Spijkerman, Lambertus Gerrit
  • Date: 2014-11-20
  • Subjects: Computer vision , Image processing - Digital techniques
  • Type: Thesis
  • Identifier: uj:13098 , http://hdl.handle.net/10210/12976
  • Description: M.Sc. (Computer Science) , This dissertation examines the field of computer vision, with special attention being given to vision systems that support digitized video image analysis. The study may be broadly divided into three main sections. The first part offers an introduction to standard vision systems, focusing on the hardware architectures and the image analysis techniques used on them. Hardware configurations depend mainly on the selected frame-grabber and processor type. Parallel architectures are highlighted, as they represent the most suitable platform for a real-time digitized video image analysis system. The image analysis techniques discussed include: image preprocessing, segmentation, edge detection, optical flow analysis and optical character recognition. The second part of the study covers a number of real-world computer vision applications, and commercially available development environments. Several traffic surveillance systems are discussed in detail, as they relate to the practical vehicle identification system developed in the third part of the study. As mentioned above, the development of a Vehicle Identification Prototype, called VIP, forms the basis for the third and final part of this study. The VIP hardware requirements are given, and the software development and use is explained. The VIP's source code is provided so that it may be evaluated, or modified, by any interested parties.
  • Full Text:

Image classification using machine learning techniques

  • Authors: Nkonyana, Thembinkosi Nelson
  • Date: 2016
  • Subjects: Image processing - Digital techniques , Image analysis , Remote-sensing images , Pattern recognition systems , Machine learning
  • Language: English
  • Type: Masters (Thesis)
  • Identifier: http://hdl.handle.net/10210/212965 , uj:21061
  • Description: Abstract: Image classification entails the important part of digital image and has been very essential in the application of remote sensing systems, thus the demand for research to find advanced algorithms and tools to solve problems experienced in classification has shown great increase in interest over the years. In this day and age, remote sensing has globally being applied with the use of current advanced satellite systems and sensors, but the need to provide analysis and decision making has been a challenge. The contribution of this dissertation is an empirical comparison (evaluation) of five machine learning (ML) techniques, in terms of classifying satellite images. The ML techniques consist of Random Forest (RF), K Nearest Neighbour (k-NN), Naïve Bayes (NB), Multi-layer Perceptron (MLP) and Support Vector Machines (SVM). The evaluation of these five techniques is based on a selection of six performance measures, such as [Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Relative Absolute Error (RAE), Root Relative Squared Error (RRSE), Precision, and Receiver Operating Characteristics (ROC)] Three publicly available remote sensing datasets are utilised for this task. The experimental results show that RF achieved higher accuracy rates, with robust performance, followed by MLP, k-NN, NB and SVM classifier exhibiting the worst performance. Hence, the use of ML for image analysis and pattern recognition is a promising approach. , M.Phil. (Electrical Engineering)
  • Full Text:

Improved steganography through the strategic placement of information and the optimization thereof through the use of evolutionary algorithms

  • Authors: Cilliers, Michael
  • Date: 2015
  • Subjects: Cryptography , Computer algorithms , Genetic algorithms , Image processing - Digital techniques , Evolutionary computation
  • Language: English
  • Type: Masters (Thesis)
  • Identifier: http://hdl.handle.net/10210/84521 , uj:19232
  • Description: Abstract: The development of steganography techniques does not occur in isolation. There is an arms race between steganography and steganalysis techniques. The development of a steganography technique that could adapt when needed could be beneficial. This research begins with a literature study exploring existing methods. Both steganog- raphy and steganalysis approaches are covered in order to get an overview of the environ- ment. Optimization methods are also examined to find a suitable method of optimizing the developed algorithm. The information that is gathered in the literature study was then used to develop a steganography algorithm that aims to decrease detectability through the strategic placement of information. The algorithm is developed in such a way as to allow for optimization. A genetic algorithm is implemented to help optimize the embedding of the information in a specific environment. This should allow the algorithm to be re- optimized when new steganalysis techniques are developed. The algorithm should thus remain relevant as steganalysis advances. The developed algorithms show that the placement of information in the image has an effect on its detectability. The developed algorithm even outperforms the random distribution LSB technique. The optimization that was implemented also produced positive results. The dissertation also includes the development of a novel evolutionary algorithm that drew its inspiration from the aphid life cycle. By switching between reproduction strate- gies the algorithm is able to adjust the balance between exploration and exploitation. , M.Sc. (Computer Science)
  • Full Text:

Landscape aware miniature aerial vehicles (MAVs)

Removal of rain from images by means of digital filters and camera obscuration techniques

  • Authors: Coetzee, Willie
  • Date: 2014-07-23
  • Subjects: Image processing - Digital techniques
  • Type: Thesis
  • Identifier: uj:11801 , http://hdl.handle.net/10210/11524
  • Description: M. Ing. (Mechanical Engineering) , This research aims at identifying techniques which can be used to remove rain from a digitized rain distorted image. The research commenced with computer implemented rain removal techniques but also lead to camera obscuration techniques. Camera rain obscuration technique: Before a rainy scene is digitized, rain can be removed from the projected image by the correct selection of camera aperture and shutter speed settings. These settings will determine the way the real image is transformed through the lens and onto the recording plane. Computer image restoration technique: Rain removal after digitization is performed in both the frequency and the spatial domain by means of two dimensional image processing and filtering techniques. Time consuming frequency domain techniques were replaced by equivalent convolutional techniques. Experiments on simulated and real scenes corrupted with rain indicated that it is possible to improve the image appearance with only a marginal decrease in signal to noise ratio.
  • Full Text:

Super features: a probabilistic approach to feature matching and correction

The enhancement of long range imagery captured through a turbulent atmosphere

The use of fractal theory, wavelet coding and learning automata in image compression

VFFD : voting features for face detection

  • 1
  • Disclaimer
  • Privacy
  • Copyright
  • Contact