Sign language recognition with deep neural networks | |
| Author | Maharjan, Lakash |
| Call Number | AIT RSPR no.CS-24-02 |
| Subject(s) | Sign language--Data processing Natural language processing (Computer science) |
| Note | A research study submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science |
| Publisher | Asian Institute of Technology |
| Abstract | This paper focuses on developing a sign language recognition system tailored to American Sign Language (ASL). Despite technological advancements, translating sign lan guage into spoken language or text remains challenging due to its complex grammar and subtle gestures. Our research utilizes the MediaPipe Holistic model and a Long Short Term Memory (LSTM) model, making use custom dataset containing key point data for 10 English gloss: hello, I love you, thanks, google, internet, jogging, house, book, drink, and drive. The proposed system is benchmarked with the classifier employing the k Nearest Neighbor (kNN) with Dynamic Time Warping (DTW). The proposed system yields 92% accuracy comparable to those obtained from the classifier using the kNN with DTWwhoseaccuracy is equal to 75%. In addition, we evaluated the robustness of the proposed system by corrupting the landmarks with zero-mean additive white Gaus sian noise whose standard deviation (SD) ranges from 0.01 to 1. The proposed system maintains accuracy beyond 90% when noise SD is less than or equal to 0.15 but exhibits a significant performance drop when the noise SD exceeds this value. |
| Year | 2024 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Chantri Polprasert |
| Examination Committee(s) | Attaphongse Taparugssanagorn;Chaklam Silpasuwanchai |
| Scholarship Donor(s) | Asian Institute of Technology |
| Degree | Research Studies Project Report (M. Sc.) - Asian Institute of Technology, 2024 |