There are more than 7billion people in the world where there are around 500 million people in the world who are denied from normal lifestyle due to physical and mental issue. It is completely fair to say that every person deserves to enjoy a normal lifestyle. While physically and mentally challenged people find suitable way to surpass their limits, thus become able in other ways, researchers always try to find solutions better than the existing one. A complete remedial of such issue is included in advanced medical science, and the amelioration of such issue to a better extent is the challenge for the engineers. In this work we have focused on hand gestures. Hand gestures are created using the movement of hand and arm, using fingers to create different shapes, using fingers and palm to create different angles. Single or both hands can be used to create different expressions. The main objective of this work is to generate an algorithm that can recognize different patterns of hand gestures with notable accuracy. American Sign Language is one possible reference model that can be used. Images of different hand signs are taken as inputs using a webcam, followed by segmentation of the images using polygon approximation and approximate convex decomposition. Feature extraction is done by recording the unique feature among the various convex segments of the hand. The resultant singularities are then used as extracted feature vectors. This involves training with the obtained features which are approximately unique for different hand gestures. Hence, we will be able to identify sign languages and successively make disabled individuals socially acceptable. This work is an extension of the work entitled “A Machine Learning Framework Using Distinctive Feature Extraction for Hand Gesture Recognition” in 2018 IEEE 8th Annual Computing and Communication Workshop and Conference (IEEE-CCWC).
展开▼
