Bangla sign digits recognition using depth information
Sign Language Recognition (SLR) targets interpreting sign language into text or speech, so as to facilitate communication between deaf-mute people and ordinary people. The task has a broad social impact but is still very challenging due to the complexity and large variations in hand actions. The existing dataset for Sign Language Recognition (SLR) in Bangla Sign Language (BdSL) is based on RGB images. Recent research on sign language recognition has shown better recognition accuracy using depth-based features. In this paper, we present a complete dataset for Bangla sign digits from Zero (Shunno in Bangla) to Nine (Noy in Bangla) using MediaPipe, a cross-platform depth-map estimation framework. The proposed method can utilize hand skeleton joint points containing depth information in addition to x, and y coordinates from RGB images only. To validate the effectiveness of our proposed approach, we have run MediaPipe on a benchmark American Sign Language (ASL) dataset. Running different classifiers in our proposed dataset we got 98.65% using Support Vector Machine (SVM). Moreover, we compared our dataset with the existing Bangla digit dataset Ishara Bochon using a deep learning-based approach and achieved significantly higher accuracy.
PDF
