Hand Gesture Recognition

GRD Journals- Global Research and Development Journal for Engineering | Volume 5 | Issue 4 | March 2020 ISSN: 2455-5703

Hand Gesture Recognition T. Ranjith Kumar Student Department of Information Technology Coimbatore Institute of Technology, Coimbatore, India

G. Vijaya Kumar Student Department of Information Technology Coimbatore Institute of Technology, Coimbatore, India

K. S. Praveenraaj Student Department of Information Technology Coimbatore Institute of Technology, Coimbatore, India

Mr. C. Murale Assistant Professor Department of Information Technology Coimbatore Institute of Technology, Coimbatore, India

Abstract Pattern matching and Gesture Recognition are the most rapidly growing fields of research industry. Being a part in non-verbal communication hand gestures are playing a vital role in real life environment. Main objective of this project is to provide the physically challenged users a better way to interact with normal peoples. Hand gesture recognition is such a research field area which includes pre-processing and segmentation, orientation detection, feature extraction and classification. In the field there are many algorithms that exist to analyzing the image. It presents the hand gesture to detect and classify the various kinds of finger symbols and displays the corresponding information. The system employs the hand gestures that are captured using webcam and using thresholding and 2D filtering techniques the captured images are segmented as binary images. Then these images are processed further and the features are extracted and get the corresponding information.

Keywords- Image Processing, Human Computer Interaction, Video Processing, Blob Detection

I. INTRODUCTION Gesture and Gesture recognition terms are heavily encountered in human computer interaction. Gestures are the motion of the body or physical action form by the user in order to convey some meaningful information. Gesture recognition is the process by which gesture made by the user is made known to the system. Through the use of computer vision or machine eye, there is great emphasis on using hand gesture as a substitute of new input modality in broad range application with the development and realization of virtual environment, current user-machine interaction tools and methods including mouse, joystick, keyboard and electronic pen are not sufficient. Hand gesture has the natural ability to represents ideas and actions very easily, thus using these different hand shapes, being identified by gesture recognition system and interpreted to generate corresponding event, has the potential to provide a more natural interface to the computer system. This type of natural interaction is the core of immersive virtual environments. If we ignore the world of computers for a while and consider interaction among human beings, we can simply realize that we are utilizing a wide range of gestures in our daily personal communication. By the fact it is also shown that people gesticulate more when they are talking on telephone and are not able to see each other as in face to face communication. The gestures vary greatly among cultures and context still are intimately used in communication. The significant use of gestures in our daily life as a mode of interaction motivates the use of gestural interface and employs them in wide range of application through computer vision.

All rights reserved by www.grdjournals.com

11

Hand Gesture Recognition (GRDJE/ Volume 5 / Issue 4 / 003)

II. SYSTEM ARCHITECTURE

III. METHODOLOGY To implement this approach we have utilized a simple web cam which is working on 20 fps with 7 mega pixel intensity. On having the input sequence of images through webcam it uses some preprocessing steps for removal of background noise and employs for segmenting the hand object from rest of the background, so that only segmented significant cluster or hand object is to be processed in order to calculate shape based features. This simple shape based approach to hand gesture recognition can identify around 45 different gestures on the bases of 5 bit binary string resulted as the output of this algorithm. This proposed implemented algorithm has been tested over 450 images and it gives approximate recognition rate of 94%.

IV. LITERATURE SURVEY Meenakshi Panwar[1] Image Pre-processing is necessary for image enhancement and for good results. In this algorithm, the input sequence of RGB images gets converted in to YCbCr images as RGB color space is more sensitive to different light conditions so we need to encode the RGB information into YCbCr. Image segmentation is typically performed to locate the hand object in image.

Kapuscinski [2] After finding out the skin colored region from image, used Hit-Miss Transform in the feature extraction step and Hidden Markov Model (HMM) as a proper classifier and the accuracy was 98% Ruchi Manish Gurav [3] Rectangles are creating some problem due to that we have also implemented the alternate representation method for same gestures I i.e. fingertip detection using convex hull algorithm.

Ashish S. Nikam[4] By considering in mind the similarities of human hand shape with four fingers and one thumb, the software aims to present a real time system for recognition of hand gesture on basis of detection of some shape based features like orientation, Centre of mass centroid, fingers status, and thumb in positions of raised or folded fingers of hand.

Ferentinos,Konstantinos.P[5] implanted the system by training the neural networks and uses five basic CNN technologies AlexNet, AlexNetOWTBn, GoogLeNet, Overfeat, Visual Geometry Group (VGG16 net).

Rokade [6] proposed RGB segmentation which is more sensitive to light conditions and the threshold value for conversion of output image to binary image that value is different for different lighting conditions.

All rights reserved by www.grdjournals.com

12

Hand Gesture Recognition (GRDJE/ Volume 5 / Issue 4 / 003)

V. EXPERIMENTAL RESULTS AND DISCUSSION

Fig. 4.1: Original image

Fig. 4.3: Binary image

Fig. 4.2: Gray scale image

Fig. 4.4: Contour detection

Fig. 4.5: Video processing

All rights reserved by www.grdjournals.com

13

Hand Gesture Recognition (GRDJE/ Volume 5 / Issue 4 / 003)

VI. CONCLUSION AND FUTURE WORK We proposed a shape based approach for hand gesture recognition with several steps including smudges elimination orientation detection, thumb detection, finger counts etc. Visually Impaired people can make use of hand gestures for writing text on electronic document like MS Office, notepad etc. The strength of this approach includes its simplicity, ease of implementation, and it does not required any significant amount of training or post processing, it provide us with the higher recognition rate with minimum computation time. The weakness of this method is that we define certain parameters and threshold values experimentally since it does not follow any systematic approach for gesture recognition, and maximum parameters taken in this approach are based on assumption made after testing number of images. If we compare our approach with our previous approach described in paper .The success rate has been improved from 92.3% to 94% , the computation time decreased up to fraction of seconds. Also to make the system more robust, we have eliminated some of the constraints needed to be followed in our previous approach which makes it simpler. The proposed algorithm is simple and independent of user characteristics.

REFERENCES [1]

[2] [3]

[4] [5] [6]

[7] [8] [9]

“An analysis of Convolutional Long Short-Term Memory Recurrent Neural Networks For Gesture recognition” Eleni Tsironi,Pablo Barros ∗,Cornelius Weber,Stefan Wermter 1, in proceeding of IEEE international Conference Department Of Computer Science, Knowledge Technology (WTM),University Of Hamburg,Vogt-Koelln-Strasse 30,Hamburg D-22527,Germany, 2017 The Authors. Published by Elsevier B.V. “An Deep Fisher Discriminant Learning For Mobile Hand Gesture recognition” in Proceedings of IEEE International Conference on Deep Fisher ,University Of Central Florida,Orlando,FL,USA 2018 Elsevier Ltd. “Exploiting deep residual networks for human action recognition from skeletal data“Department of Computer Science, Applied Artificial Intelligence Research Group, University Carlos III de Madrid, Madrid 28270, Spain, Received 29 September 2017; Received in revised form 15 January 2018; Accepted 6 March 2018.

“RGB-D-based human motion recognition with deep learning: A survey” University of Barcelona and Computer Vision Center, Campus UAB, 08193 Bellaterra, Barcelona, Spain,2018 The Authors. Published by Pichao Wang.

Meenakshi Panwar and Pawan Singh Mehra , "Hand Gesture Recognition for Human Computer Interaction", in Proceedings of IEEE International Conference on Image Information Processing (ICIIP 2011), Waknaghat, India, November 2018.

Amornched Jinda-apiraksa, Warong Pongstiensak, and Toshiaki Kondo, "A Simple Shape-Based Approach to Hand Gesture Recognition", in Proceedings of IEEE International Conference on Electrical Engineering/ Electronics Computer Telecommunications and Information Technology (ECTI-CON), Pathumthani, Thailand , pages 851-855, May 2015.

A. Jinda-Apiraksa, W. Pongstiensak, and T. Kondo, "Shape-Based Finger Pattern Recognition using Compactness and Radial Distance," The 3rd International Conference on Embedded Systems and Intelligent Technology (ICESIT 2010), Chiang Mai, Thailand, February 2017.

Rajeshree Rokade , Dharmpal Doye, Manesh Kokare, "Hand Gesture Recognition by Thinning Method", in Proceedings of IEEE International Conference on Digital Image Processing (ICDIP), Nanded India, pages 284-287, March 2018 Qing chen, N. D. Georgans, “Hand Gesture Recognition Using Haar-Like Features and a Stochastic Context-Free Grammar”, IEEE transactions on instrumentation and measurement Ottawa Univ., Vol. 57, no. 8.pp.113-117,August 2017

All rights reserved by www.grdjournals.com

14