PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

Sign Language is the only method used in communication between the hearing-impaired community and common community. Sign Language Recognition (SLR) system, which is required to recognize sign languages, has been widely studied for years. The studies are based on various input sensors, gesture segmentation, extraction of features and classification methods. This paper aims to analyze and compare the methods employed in the SLR systems, classifications methods that have been used, and suggests the most promising method for future research. Due to recent advancement in classification methods, many of the recent proposed works mainly contribute on the classification methods, such as hybrid method and Deep Learning. This paper focuses on the classification methods used in prior Sign Language Recognition system. Based on our review, HMM-based approaches have been explored extensively in prior research, including its modifications. Deep Learning such as Convolutional Neural Network is popular in the past five years. Hybrid CNN-HMM and fully Deep Learning approaches have shown promising results and offer opportunities for further exploration. However, overfitting and high computational requirements still hinder their adoption. We believe the future direction of the research is toward developing a simpler network that can achieve high performance and requires low computational load, which embeds the feature learner into the classifier in multi-layered neural network fashion.