Faculty Supervisor

Dr. Rachel Jiang


Dr. Abdul Mustafa

Date of Defense

Winter 11-8-2020

Program Name

Honours Bachelor of Computer Science (Mobile Computing)


Applied Computing


American sign language, MATLAB, deep learning, convolutional neural net-work, models, ASL data set, computer vision, transfer learning, WL-ASL


Faculty of Applied Science & Technology (FAST)


A solution to gesture recognition: Applying the current state of the art recognition algorithms to detect over 2000 phrases.


ASL speaking individuals always bring a companion as a translator [1]. This creates barriers for those who wish to take part in activities alone. Online translators exist however, they are limited to the individual characters instead of the gestures which group characters in a meaningful way, and connectivity is not always accessible. Thus, this research tackles the limitations of existing technologies and presents a model, implemented in MATLAB 2020b, to be used for predicting and classifying American sign language gestures/characters. The proposed method looks further into current neural networks and how they can be utilized against our transformed World Largest { American Sign Language data set. Resourcing state of the art detection and segmentation algorithms, this paper analyzes the efficiency of pre-trained net-works against these various algorithms. Testing current machine learning strategies like Transfer Learning and their impact on training a model for recognition. Our research goals are 1. Manufacturing and augmenting our data set. 2. Apply transfer learning on our data sets to create various models. 3. Compare the various accuracies of each model. And finally, present a novel pattern for gesture recognition.

Terms of Use

Terms of Use for Works posted in SOURCE.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.