Automated Real-time Gesture Recognition using Hand Motion Trajectory
Sweta Swami, Yusuf Parvez, Nathi Ram Chauhan · International Journal of Engineering and Technology · 2017
In this quite busy and technologically evolved world, gesture plays a very vital role in person's everyday life to convey the data or send command to the machines using only the motions or wave of the hand and thus, automating the processes.Gesture recognition is basically a part of HCI (Human Computer Interaction).In the past recent years, many algorithms and methodology have been implemented on the gesture recognition and achieve a touch less environment between the computer and the human.In many of the developed algorithms and the methodologies, the use of high end cameras is mandatory.For example, the Kinect camera for motion capture used in PS3 gaming.In this paper, focus has been given on the utilization of the normal web camera to recognize the gesture as robust and correct as possible.The proposed methodology in the present work is the use of deep learning algorithm in order to learn the features of the gestures and then further classify them correctly in the real time.The main target is to recognize the alphabets of the English language like (A, B, C, D) by just waving hand in front of the web camera of the laptop with 5 mega pixel resolution.Firstly, the object of any specific color is detected for tracking the movement.Then, the skin color detection is done to effectively track the movement of human hand.The Deep Belief Neural Network is used to learn the gestures in the training phase of the project.The training of the system is done using the database manually created which consists of 11 characters, 4 samples each.Finally, the gestures are recognized in real-time using Deep Learning Algorithm.The proposed methodology with incorporation of the Deep Belief Neural Network learning method achieves the 95.5 % of the success rate.The recognition rate obtained from the present work mentioned in this paper is 95.5% which is significantly higher as compared to already published recognition rate which is 92.3% on the real-time gesture recognition.Keyword -Hand Gesture Recognition, Real time implementation, DNN, deep learning I. INTRODUCTION The impediment of virtual environments carries in the entire new set of complications for user interfaces.The introduction of 3D objects and world in which the occupied user permit the people like doctors, engineers, architects and scientists, to visualize complex structures and systems with prominent degrees of superiority and naturalism.A stereo or 3D view of the scene is furnished by Shutter glasses, which is no longer kept in a desktop monitor but may be a big room or projection screen.The regulating elements in such systems presently is the important communications.Virtual environments look for creating the world where the communication skills are real.Presently mechanical, magnetic and acoustic input devices track the user and deliver govern the program, selection, and running of objects in virtual scenes.The main limitation of this technology is its cost.However, size, physical location requirements, and 2D version are other limitations.Other more advanced devices are offered for virtual reality including gloves or wearable tools like mechanical sensors, micro cameras and actuators which can handle 3D worlds, and some applications tactile sensations are also provided.Unfortunately, the user acceptance is confined due to high costs.So, making them more desirable for applications like remote surgery equipment or flight simulators.To communicate with the factual world the new and advanced alternative, natural interface should be invented.Thus, the user must be capable to grab, point and move 3D objects just like real objects.So, a new way has been provided by these challenges for human-computer communication via computer vision techniques and it is likely to form innovative input devices which can be employed and the new devices upgraded further.Input command is given by it rather than photo or record video.Computer vision devices are transformed into input command devices as keyboard or mouse.A hand is used to create the gesture and provide an input command to the computer vision devices.The computer recognizes the signals as an input and that will be beneficial to all the users to do so without a direct device and can do what they want.