Theses and dissertations (Accounting and Informatics)
Permanent URI for this collectionhttp://ir-dev.dut.ac.za/handle/10321/4
Browse
2 results
Search Results
Item Development of a clustering algorithm for universal color image segmentation(2023-01-01) Joseph, Seena; Olugbara, Oludayo O.Image segmentation is an important stage of many real-world image applications in the domain of computer vision as a core method for understanding and analyzing digital images. It is aimed to segregate the most salient objects in an image by clustering homogenous regions based on the characteristics of image pixels. Segmentation of salient objects is a complex process because of the existence of numerous inherent characteristics of images that can impede the performance of the process. Due to these diverse image characteristics, a model that is suitable for one category of images is essentially inappropriate for other image categories, which makes image segmentation an open problem. Myriads of classical segmentation algorithms have been developed over the years, yet generalization and universal optimum performance are far from ideal levels. Clustering algorithms have been developed in recent times for the effective segmentation of images. However, the performance of the majority of the existing clustering-based segmentation algorithms substantially relies on the selection of an optimal number of initial clusters. Incorrect cluster count selection may result in uneven highlighting of the target object and be susceptible to under- or oversegmentation of images. This opens an avenue to fully discover a universal clustering algorithm for image segmentation that would be appropriate for manifold classes of images. In this study, the color histogram clustering algorithm has been proposed to automatically determine a suitable number of clusters that indicates homogenous regions in an image. The aim was to segment the most salient object from its surrounding regions using color histogram clustering that characterizes homogenous regions based on primitive features. The segmentation algorithm starts with histogram clustering-based on the quantized RGB color image to automatically identify the clusters that correspond to the homogenous regions in the image. The perceptual homogeneity of the input RGB color image is achieved by the transformation to L*a*b* color model based on four primitive features. The primitive features are color contrast, contrast ratio, spatial feature, and center prior that are extracted to compute the descriptor of each cluster. The cluster level saliency score is then computed as a function of the four primitive features extracted from the color image. The cluster level saliency is used to compute the final saliency score of each pixel to highlight the target object. The color histogram clustering method of this study combines the Otsu thresholding algorithm with the saliency map to represent the segmented image in a silhouette format. Morphological operations are finally performed to remove the undesired artifacts that may be present at the segmentation stage. Hence, this present study has introduced a novel, simple, robust, and computationally efficient color histogram clustering algorithm that agglutinates color contrast, contrast ratio, spatial feature, and central prior for efficiently segmenting the target objects in diverse image categories. The performance of the proposed algorithm was evaluated using the widely used metrics of precision, recall, F-measure, mean absolute error, and overlap ratio on six different categories of images selected from five benchmarked corpora of MSRA10K, ASD, SED2, ImgSal, and DUT OMRON. Moreover, 1000 images from ECSSD, 4447 images from HKU-IS, and 1500 images from COCO datasets were selected to validate the performance of the algorithm on more complex natural datasets. Experimental results have indicated that the proposed algorithm outperformed 30 bottom-up non-deep learning and seven top-down deep learning salient object detection algorithms. The performance of the proposed algorithm was further evaluated on four medical image datasets and the effects of image preprocessing were comprehensively investigated. The performance of the proposed image segmentation algorithm was analyzed in terms of accuracy, sensitivity, specificity, and dice similarity on 10015 images from HAM10000, 2594 images from ISIC2018 dataset, and 200 images from the PH2 dataset against six supervised and six unsupervised benchmark segmentation algorithms. The performance of the proposed algorithm was further validated on the segmentation of 1145 leukocyte nuclei images from the Raabin-WBC dataset in terms of accuracy, sensitivity, specificity, Dice similarity, and Jaccard index. In total, 22307 images with a variety of properties were used to test the performance of the proposed algorithm. In addition, the effects of image preprocessing on the performance of the proposed algorithm were further investigated in this study. The statistical results obtained have shown that the proposed algorithm is free from image preprocessing, and demonstrated its application on a wide class of images without any bounding to the heterogeneous characteristics of the input images. The novelty of the work reported in this thesis has demonstrated that the proposed algorithm is superior to the investigated supervised deep learning and prominent unsupervised segmentation algorithms in terms of quantitative results and visual effects.Item Image content-based user preference elicitation for personalised mobile recommendation of shopping items(2021-10-26) Oyewole, Stanley Ade; Olugbara, Oludayo O.Personalised recommendation of product items has been recognised as an exciting snug suggestion for an individual customer. This is required to meet the preferences of an individual customer and improve the sales of merchants. Most current research works in content-based recommendation heavily relied on an orthodox 2-dimensional “user by item” data structure has been used extensively in different application areas for product items recommendation. However, this structure is limited in delivering personalised recommendations to mobile customers because of the inherent “problem of concept drift” that can result in degrading the performance of a recommendation system. This research work introduces an image content-based preference elicitation model based on the approach of supervised machine learning to deliver personalised product items recommendation to mobile customers. This model of product items recommendation leverages the extraction of multiple aspects of item dynamic features to characterise the preferences of mobile customers. This will help mobile customers and nomadic to pervasively discover product items that are most relevant to their interests and reduce barriers to purchase. To start with, a new image-based item classification framework that leverages a novel 4-dimensional colour image representation and Eigen-colour features is built to realise efficient item-class features. The framework is devised to realise a timedependent item relevance score for selecting a set of product items of interest. These features were integrated with other features such as price, location, and incentive associated with a product item to improve the performance of a shopping recommendation system. This is to build the proposed design towards addressing the concept drift problem and large recommendation space problems often associated with the orthodox items recommendation systems. Experimental results of testing an implementation of the proposed item classification framework have shown a recommendation system to produce low-dimensional item features and an implicit shortterm preference profile for a new system user with recommendation accuracy of 92.2% on popular PI100 e-commerce shopping items corpus. Moreover, another experiment on item-based multiple criteria decision-making techniques has revealed that multiple factors can adequately address the concept drift problem. The proposed technique spawns better top-5, top-10, and top-15 rank personalised recommendation accuracy results when compared to the orthodox content-based approach. Finally, as a proof of concept, an imaging interface that anchors the proposed framework in a client-server system was simulated on a mobile phone