Filtering by
- All Subjects: artificial intelligence
- All Subjects: accessibility
- Creators: McDaniel, Troy
Games have traditionally had a high barrier to entry because they necessitate unique input devices, fast reaction times, high motor skills, and more. There has recently been a push to change the design process of these games to include people with disabilities so they can interact with the medium of games as well. This thesis examines the current guiding principles of accessible design, who they are being developed by, and how they might help guide future accessible design and development. Additionally, it will look at modern games with accessibility features and classify them in terms of the Game Accessibility Guidelines. Then, using an interview with a lead developer at a game studio as aid, there will be an examination into modern game industry practices and what might be holding developers or studios back when it comes to accessible design. Finally, further suggestions for these developers and studios will be made in order to help them and others improve in making their games more accessible to people with disabilities.
Generative models have recently gained popularity as they synthesize unseen visual features and convert zero-shot learning into a classical supervised learning problem. These generative models are trained using seen classes and are expected to implicitly transfer the knowledge from seen to unseen classes. However, their performance is stymied by overfitting towards seen classes, which leads to substandard performance in generalized zero-shot learning. To address this concern, this dissertation proposes a novel generative model that leverages the semantic relationship between seen and unseen categories and explicitly performs knowledge transfer from seen categories to unseen categories. Experiments were conducted on several benchmark datasets to demonstrate the efficacy of the proposed model for both zero-shot learning and generalized zero-shot learning. The dissertation also provides a unique Student-Teacher based generative model for zero-shot learning and concludes with future research directions in this area.
This dissertation outlines various applications to improve accessibility and independence for visually impaired people during shopping by helping them identify products in retail stores. The dissertation includes the following contributions; (i) A dataset containing images of breakfast-cereal products and a classifier using a deep neural (ResNet) network; (ii) A dataset for training a text detection and scene-text recognition model; (iii) A model for text detection and scene-text recognition to identify product images using a user-controlled camera; (iv) A dataset of twenty thousand products with product information and related images that can be used to train and test a system designed to identify products.
This thesis presents three models for incremental learning; (i) Design of an algorithm for generative incremental learning using a pre-trained deep neural network classifier; (ii) Development of a hashing based clustering algorithm for efficient incremental learning; (iii) Design of a student-teacher coupled neural network to distill knowledge for incremental learning. The proposed algorithms were evaluated using popular vision datasets for classification tasks. The thesis concludes with a discussion about the feasibility of using these techniques to transfer information between networks and also for incremental learning applications.