In our day to day life humans interact with computers or machines very frequently and these interactions result in completion of meaningful tasks or scheduled jobs. These interactions can involve a lot of applications like gaming, typing, scrolling, pointing, remote arm movement, etc. Out of all the ways of interacting such as mechanical movement like mouse, keyboard, joystick, etc., speech recognition, etc. The most effective one is thought to be through hand because the mechanical ones even include the movement of hand ultimately, so in order to make this interaction more convenient and efficient there was an idea of developing hand gesture recognition and it was later implemented but often it involved special instruments such as gloves with sensors or particular background. This proposed paper emphasizes the more effective way of human computer interaction which is hand gesture recognition. There are three main modules which are hand detection and hand tracking and hand gesture recognition. There are several applications of this way of interaction the user can customize to their own use. This model is fast and accurate and it can go up to 30fps and the main applications include the video game stimulation, virtual board and many other useful human computer interactions. The proposed model can detect hand even in strained backgrounds and without gloves in almost all of the cases and the model is robust and smooth. The hand gestures are one of the most natural ways of communication in humans rather than input through keyboards and mouse. This model can be used in VR and AR stimulations which would need a better way of human computer interaction than a keyboard and mouse. The main objective of this paper is to employ a new model to improve the human computer interaction. In the proposed model a menu will be displayed with the numbers representing the action desired by the user let us say 1. Represents the virtual mouse 2. Represents the virtual keyboard 3. Represents the other menu where a series of actions can be defined by the user. The proposed model uses the hand sign detection for the recognition of the numbers by the finger counting module and again using other hand sign detection module. The objective is to form a neural network to distinguish the hand signs in order recognize the hand sign to implement the desired action of the user. We have utilized Google`s Mediapipe Frame Work Arrangements has further developed hand recognition model and may understand 21 3D landmarks of Palm. Subsequently we`ll endeavor to know it and the method for utilizing this Library Python to understand our objective.

Mediapipe, Sign language recognition [SLR], Human computer interaction, Gesture recognition

[1] Cristina Manresa, Javier Varona, Ramon Mas and Francisco J. Perales, “Hand Tracking and Gesture Recognition for Human-Computer Interaction” Electronic Letters on Computer Vision and Image Analysis 5(3):96-104, 2005
[2] Er. Aditi Kalsh, Dr. N.S. Garewal “Sign Language Recognition System`` International Journal of Computational Engineering Research 2013
[3] Hui-Shyong Yeo & Byung-Gook Lee & Hyotaek Lim, “Hand tracking and gesture recognition system for human-computer interaction using low-cost hardware” Springer Science+Business Media New York 2013
[4] “survey on hand gesture techniques for sign language recognition.”IJTRS-V2-I7-005 Volume 2 Issue VII, August 2017
[5] Kai Li1,2,3, Jun Cheng2,3, Qieshi Zhang*,2,3, Jianming Liu1, “Hand Gesture Tracking and Recognition based Human-Computer Interaction System and Its Applications” Proceeding of the IEEE International Conference on Information and Automation Wuyi Mountain, China, August 2018
[6] Bhumika Gupta, Pushkar Shukla and Ankush Mittal “K-nearest correlated neighbour classification for Indian sign language gesture recognition using feature extraction”
[7] Mais Yasen and Shaidah Jusoh, “A systematic review on hand gesture recognition techniques, challenges and applications” PeerJ computer science
[8] M S Srividya, Anala M R, “Research trends in Hand Gesture Recognition techniques” International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878 (Online), Volume-8 Issue-6, March 2020
[9] Munir Oudah , Ali Al-Naji , and Javaan Chahl, “Hand Gesture Recognition Based on Computer Vision: A Review of Techniques” Journal of Imaging July 2020
[10] Nguyen Dang Binh, Enokida Shuichi, Toshiaki Ejima, ” Real-Time Hand Tracking and Gesture Recognition System” GVIP 05 Conference, 19-21 December 2005, CICC, Cairo, Egypt.
[11] Alisha Pradhan andB.B.V.L. Deepak ,”Obtaining hand gesture parameters using Image Processing”,2015 International Conference on Smart Technology and Management(ICSTM).
[12] Prakash B Gaikwad, Dr. V.K.Bairagi,” Hand Gesture Recognition for Dumb People using Indian Sign Language”, International Journal of Advanced Research in computer Science and Software Engineering, pp:193-194, 2014.
[13] Tin Hninn Hninn Maung, ”Real-Time Hand Tracking and Gesture Recognition System Using Neural Networks” World Academy of Science, Engineering and Technology 26 2009.
[14] Umang Patel & Aarti G. Ambekar “Moment based sign language recognition for IndianLanguages “2017 Third International Conference on Computing, Communication, Control and Automation (ICCUBEA).
[15] Vikram Sharma M, “Virtual Talk for deaf, mute, blind and normal humans,” Texas instruments India Educator’s conference, 2013.
[16] Viraj Shinde, Tushar Bacchav, Jitendra Pawar, Mangesh Sanap, “Hand Gesture Recognition System Using Camera” International Journal of Engineering Research & Technology (IJERT) Vol. 3 Issue 1, January - 2014 IJERT ISSN: 2278-0181
[17] Yellapu Madhuri and Anburajan Mariamichael)”Vision based sign language translation device” conference paper: February 2013