Submit your paper : editorIJETjournal@gmail.com

Paper Title : American Sign Language to Audio Conversion using CNN in Python and Website Creation.

ISSN : 2395-1303
Year of Publication : 2020
10.29126/23951303/IJET-V6I5P2

Alphonsa Merlin Roy, Alisa Magdeline Rodrigues, Amrita Elsa Vettiyil, Caroline B.Joseph, Ms. S.Santhi Jabarani

         


Abstract
- American sign language to audio conversion system converts the input image of a particular alphabet to an audio output signal. This is implemented with the help of a Convo- lutional Neural Network(CNN). The network initially processes the reshaping of an image into its required dimensions and scale parameters. These processed images are all collected and then further sent as input to the training stage. Then the trained network is tested using external image inputs. It accurately recognizes and identifies the newly fed images by comparing with the previously trained ones stored in the database. After testing proves to be efficient, final text to speech conversion takes place and thereby receive the speech output. This system is further implemented into a website where it lays a platform for communication for external users.

Reference
[1] Ariya Thongtawee, Onamon Pinsanoh and Yuttana Kitjaidure, ”A Novel Feature Extraction for American Sign Language Recognition Using Webcam,” The 2018 Biomedical Engineering International Conference (BMEiCON-2018) [2] Saad Albawi , Tareq Abed Mohammed anSaad AL-ZAWI ”Understand- ing of a Convolutional Neural Network,” 2017 International Conference on Engineering and Technology(ICET) [3] Rahul Chauhan, Kamal Kumar Ghanshala and R.C Joshi,”Convolutional Neural Network (CNN) for Image Detection and Recognition,” 2018 First International Conference on Secure Cyber Computing and Com- munication (ICSCCC) Fig. 6. Homepage of the Website Fig. 7. Captured sign and corresponding audio and text as seen in the website [4] Adithya V., Vinod P.R. and Usha Gopalakrishna, ” Artificial Neural Network Based Method for Indian Sign Language Recognition,” Pro- ceedings of 2013 IEEE Conference on Information and Communication Technologies (ICT 2013) [5]P. Subha Rajam and Dr. G. Balakrishnan, ”Real Time Indian Sign Language Recognition System to aid Deaf-dumb People,” 2011 IEEE 13th International Conference on Communication Technology [6] Patel, R., Dhakad, J., Desai, K., Gupta, T., Correia, S. (2018). Hand Gesture Recognition System using Convolutional Neural Networks. 2018 4th International Conference on Computing Communication. [7] Saad Albawi,Saad Al Zawi,(2017).Understanding of a Convolutional Neural Network.2017/IEEE [8] Raniah Zaheer,Humera Shaziya (2019).A study of the Optimisation Algorithms in Deep Learning. 2019 IEEE/International conference on inventive systems and control. [9].JSON file https://fileinfo.com/extension/json [10]HDF5 file https://www.geeksforgeeks.org/hdf5-files-in-python/ [11]Tkinter https://www.tutorialspoint.com/ [12]PYTTXS3 https://pypi.org/project/pyttsx3/ [13] Hanin M. Abdullah, and Ahmed M. Zeki , “Frontend and Backend Web Technologies in Social Networking Sites: Facebook as an Example ,” 2014 3rd International Conference on Advanced Computer Science Applications and Technologies. [14] HTML AND CSS BASICS https://frontendmasters.com/books/front-end- handbook/2018/learning/html-css.html films and exchange anisotropy,” in Magnetism, vol. III, G. T. Rado and H. Suhl, Eds. New York: Academic, 1963, pp. 271–350. [15] Bangzhong Cao,Minyong Shi,Chunfang Li, “The Solution of Web Font- end Performance Optimization ,”2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI 2017). [16] JAVASCRIPT https://en.wikipedia.org/wiki/JavaScript [17]DJANGO FRAMEWORK https://www.djangoproject.com/start/overview/

Keywords
Database, CNN, Adam, Learning rate, .JSON, pyttsx3, Website