A deep learning approach to classifying tyres using sidewall images
- Authors: Gifford, Dean
- Date: 2019
- Subjects: Image processing -- Digital techniques , Image processing Computer science
- Language: English
- Type: Thesis , Masters , MSc
- Identifier: http://hdl.handle.net/10948/39720 , vital:35351
- Description: End of Life Tyres (ELT's) pose a potential health and environmental risk when dumped in illegal stockpiles. For recycling to be considered feasible, a profitable business opportunity needs to be created. One method of making the recycling process of tyres more profitable is by understanding the compounds found within each tyre. This study aims at classifying these tyres in order to achieve this knowledge. A literature review was done to investigate neural networks, convolutional neural networks as well as existing deep learning architectures for image classification. A deep learning approach was applied in order to classify the logos of tyres as these approaches have proved their success in both image classification and more specifically logo classification. Although tyre classification has been implemented in the past, a deep learning approach has not been applied and the logo has not been the classifying element in any other studies. The main difference of this study compared to previous research surrounding deep learning and logo classification is the properties of the tyre logo. Logos on tyres are very similar in colour as they are purely formed in rubber and very seldom have any colour to them. Additionally, the embossed logos can contain variation among same branded tyres due to small inconsistencies in the moulds. The implementation of this deep learning solution saw multiple convolutional neural networks implemented. Some of these architectures were also implemented using transferred learning. The metrics obtained as outputs from training and testing the architectures were the accuracy, precision, recall, and F1-score. These metrics were compared in conjunction with the confusion matrix produced from testing. To ensure that variance was accounted for in the experiments, the k-fold cross-validation technique was adopted. The results of this study identified that one convolutional neural network model, MobileNet, was particularly well suited for the context of classifying logos on tyre sidewalls. The MobileNet architecture had the highest performance metrics for both training from scratch (96.7% accuracy) and transferred learning (98.8% accuracy). Three other models performed particularly well when trained from scratch, these were a modification of the LeNet architecture, ResNet50 and InceptionV3. The transferred learning results were also impressive with four out of the 5 models achieving an accuracy above 94%. Interestingly, the ResNet50 architecture failed to train when transferred learning was applied. Contrasting to this, the two models VGG16 and VGG19 failed to train when trained from scratch but performed equally as well as the other models when transferred learning was implemented. This indicates that although transferred learning can improve the performance of models, it is highly dependent on the task as well as the model. Overall the results obtained proved that a deep learning approach could be applied in order to classify tyres accurately.
- Full Text:
- Date Issued: 2019
A model for context awareness for mobile applications using multiple-input sources
- Authors: Pather, Direshin
- Date: 2015
- Subjects: Context-aware computing , Mobile apps , MIMO systems
- Language: English
- Type: Thesis , Masters , MCom
- Identifier: http://hdl.handle.net/10948/2969 , vital:20378
- Description: Context-aware computing enables mobile applications to discover and benefit from valuable context information, such as user location, time of day and current activity. However, determining the users’ context throughout their daily activities is one of the main challenges of context-aware computing. With the increasing number of built-in mobile sensors and other input sources, existing context models do not effectively handle context information related to personal user context. The objective of this research was to develop an improved context-aware model to support the context awareness needs of mobile applications. An existing context-aware model was selected as the most complete model to use as a basis for the proposed model to support context awareness in mobile applications. The existing context-aware model was modified to address the shortcomings of existing models in dealing with context information related to personal user context. The proposed model supports four different context dimensions, namely Physical, User Activity, Health and User Preferences. A prototype, called CoPro was developed, based on the proposed model, to demonstrate the effectiveness of the model. Several experiments were designed and conducted to determine if CoPro was effective, reliable and capable. CoPro was considered effective as it produced low-level context as well as inferred context. The reliability of the model was confirmed by evaluating CoPro using Quality of Context (QoC) metrics such as Accuracy, Freshness, Certainty and Completeness. CoPro was also found to be capable of dealing with the limitations of the mobile computing platform such as limited processing power. The research determined that the proposed context-aware model can be used to successfully support context awareness in mobile applications. Design recommendations were proposed and future work will involve converting the CoPro prototype into middleware in the form of an API to provide easier access to context awareness support in mobile applications.
- Full Text:
- Date Issued: 2015