Monocular Vision-based Signer-Independent Pakistani Sign Language Recognition System using Supervised Learning

Background/Objectives: To construct a Pakistani sign language learning-based gesture recognition system with a reasonable rate of accuracy. Methods/Statistical Analysis: It should be <70 words. Include the method adapted to study the objectives/sampling details or simulation or statistical analysis of data; technique employed; mention unique/ important points of modification of methodology in the current study. Mention about test samples the control employed or approach used for comparing the test sample. Findings: The proposed system uses static images to extract local and global, region and boundary-based descriptors for acquiring gesture information, which is provided as input for supervised learning method known as Support Vector Machine (SVM). The purpose of this research is to formally introduce a practical learning-based PSL recognition system, which can lay the groundwork for future research pertaining to PSL. The proposed system was developed and the ten class supervised learning based system was able to achieve an accuracy of 83%. Application/Improvements: It is a preliminary work, which will be further improved to construct a real-time static and dynamic gesture based PSL system that is able to recognize words and sentences information.