Multiple Sign Language Identification Using Deep Learning Techniques
Ahmed Mahmoud Sultan,
Waleed Makram Mohamed Zaki,
Mohammed Kayed,
Abdel Mgeid Amin Ali
Issue:
Volume 11, Issue 1, June 2023
Pages:
1-11
Received:
21 January 2023
Accepted:
14 February 2023
Published:
29 May 2023
Abstract: The research presents a general overview of sign languages, and a previous survey was conducted on all aspects of sign languages including the tools used to collect sign languages and the best algorithms to achieve the best results. A specialized database is prepared to combine the alphabet signs of the Arabic, American, and British languages, as they are the most important sign languages and the most widespread in the world. Based on different sign languages and deep learning techniques such as LeNet, VGG-16, and CapsNet, which are considered among the best methods for solving sign language problems based on our previous studies. The purpose of the research is to remove the communication gap between the deaf, and normal speaking people who speak one sign language or those who try to communicate from different countries and to identify these languages easily. We applied some of the traditional deep learning techniques such as LeNet, and then we applied VGG-16 using pre-training models and adjusted some layers to suit our problem. Also we applied CapsNet as it is perfectly suitable for solving the problem of sign language deformation, rotation, and scaling. The best results were achieved using VGG-16, as it was trained on a previous database like ImageNet, which contains millions of images. We got an accuracy of 99.69% when training the model of VGG-16, and an accuracy of 99.65% when testing the model. On the other hand, we got lower accuracies in CapsNet and LeNet compared to VGG-16. We got 96.54%, 97.45%, and 94.95% on BSL, ASL, and ArSL respectively while applying LeNet model, while we got 98.4848%, 98.4286%, and 99.5652% on ArSL, ASL, and BSL respectively while applying CapsNet model. Using VGG-16 we got 99.05%, 98.50%, and 99.69% on ArSL, ASL, and BSL respectively.
Abstract: The research presents a general overview of sign languages, and a previous survey was conducted on all aspects of sign languages including the tools used to collect sign languages and the best algorithms to achieve the best results. A specialized database is prepared to combine the alphabet signs of the Arabic, American, and British languages, as t...
Show More
A Web-based Least Significant Bit (LSB) Image Steganographic Technique
Issue:
Volume 11, Issue 1, June 2023
Pages:
12-18
Received:
5 July 2022
Accepted:
11 October 2022
Published:
6 July 2023
Abstract: Steganography is the art of hiding secret messages into cover during communication. Steganography is a technique for sending secret messages across ordinary cover carriers in such a way that the presence of the messages is unnoticed. There are various steganographic techniques based on the cover being used in the steganographic process. The covers can be an image, audio, video, and text. The most widely used steganographic technique nowadays is Image Steganography. Image steganography is hiding the existence of the data using the image as the cover object. Most of the image steganographic technique hides the secret messages as plaintext and intruders may try to extract the secret message if he/she knows that the image being communicated is a stego image. In this paper, a web-based Least Significant Bit (LSB) image steganographic technique with two layers of AES encryption that does not require a key exchange mechanism between sender and receiver is explained. The proposed method follows six step mechanism on the sender’s side which includes user authentication to initiate communication, two 128-bit key generation and storing it to the central server database, message encryption using one of the generated keys in previous step and image encryption using another key followed by the image steganography. The image generated after sixth step is ready to send via any medium to the receiver. The receiver of the image also follows six steps process to convert the stego image to the decrypted message. After completing the authentication, receiver inputs the received image from the sebder and the system checks for the integrity of the inputted image. Once the integrity is verified, the system pulls the decryption keys from the database. Using this decryption keys, the image decryption and message takes place. The goal of the proposed method is to avoid key exchange mechanism using client/server architecture. The proposed method encrypts the secret message and stego image to add another layer of security.
Abstract: Steganography is the art of hiding secret messages into cover during communication. Steganography is a technique for sending secret messages across ordinary cover carriers in such a way that the presence of the messages is unnoticed. There are various steganographic techniques based on the cover being used in the steganographic process. The covers ...
Show More
