Abstract:
Thai sign language recognition is one of the challenges for machine learning, especially visual-based recognition. The most common problem is data preparation before processing because sign language is a form of communication that uses both verbal and non-verbal communication, and cannot separate them from each other such as facial expressions, hand gestures, and body language. In this research proposed an innovative technique for video processing called Sequenced Edge Grid Images (SEGI) for sign language recognition to interpret hand gesture, body movement, and facial expression. The proposed technique was implemented with a convolutional neural network (CNN). The experiments showed SEGI with CNN has increases test accuracy rate with approximately 11% compared to static hand gesture images. Finally, researchers discovered a CNN structure suitable for dataset and examination data by transferring a pre-trained CNN. The fine-tuning with SEGI technique improved 99.8%, thus highest among all the methods.