ETD Collection

Permanent URI for this collectionhttps://wiredspace.wits.ac.za/handle/10539/104


Please note: Digitised content is made available at the best possible quality range, taking into consideration file size and the condition of the original item. These restrictions may sometimes affect the quality of the final published item. For queries regarding content of ETD collection please contact IR specialists by email : IR specialists or Tel : 011 717 4652 / 1954

Follow the link below for important information about Electronic Theses and Dissertations (ETD)

Library Guide about ETD

Browse

Filters

20172

Settings

Has files: YesSubject: search.filters.subject.Noise control

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Using customised image processing for noise reduction to extract data from early 20th century African newspapers
    (2017) Usher, Sarah
    The images from the African articles dataset presented challenges to the Optical Character Recognition (OCR) tool. Despite successful binerisation in the Image Processing step of the pipeline, noise remained in the foreground of the images. This noise caused the OCR tool to misinterpret the text from the images and thus needed removal from the foreground. The technique involved the application of the Maximally Stable Extremal Region (MSER) algorithm, borrowed from Scene-Text Detection, and supervised machine learning classifiers. The algorithm creates regions from the foreground elements. Regions are classifiable into noise and characters based on the characteristics of their shapes. Classifiers were trained to recognise noise and characters. The technique is useful for a researcher wanting to process and analyse the large dataset. They could semi-automate the foreground noise-removal process using this technique. This would allow for better quality OCR output, for use in the Text Analysis step of the pipeline. Better OCR quality means less compromises would be required at the Text Analysis step. These concessions can lead to false results when searching noisy text. Fewer compromises means simpler, less error-prone analysis and more trustworthy results. The technique was tested against specifically selected images from the dataset which exhibited noise. It involved a number of steps. Training regions were selected and manually classified. After training and running many classifiers, the highest performing classifier was selected. The classifier categorised regions from all images. New images were created by removing noise regions from the original images. To discover whether an improvement in the OCR output was achieved, a text comparison was conducted. OCR text was generated from both the original and processed images. The two outputs of each image were compared for similarity against the test text. The test text was a manually created version of the expected OCR output per image. The similarity test for both original and processed images produced a score. A change in the similarity score indicated whether the technique had successfully removed noise or not. The test results showed that blotches in the foreground could be removed, and OCR output improved. Bleed-through and page fold noise was not removable. For images affected by noise blotches, this technique can be applied and hence less concessions will be needed when processing the text generated from those images.
  • No Thumbnail Available
    Item
    The application of non-linear partial differential equations for the removal of noise in audio signal processing
    (2017) Shipton, Jarrod Jay
    This work explores a new method of applying partial di erential equations to audio signal processing, particularly that of noise removal. Two methods are explored and compared to the method of noise removal used in the free software Audacity(R). The rst of these methods uses a non-linear variation of the di usion equation in two dimensions, coupled with a non-linear sink/source term, in order to lter the imaginary and real components of an array of overlapping windows of the signal's Fourier transform. The second model is that of a non-linear di usion function applied to the magnitude of the Fourier transform in order to estimate the noise power spectrum to be used in a spectral subtraction noise removal technique. The technique in this work features nite di erence methods to approximate the solutions of each of the models.