Search

In this technology driven era, effective communication is the backbone for success of any business. In Post- Covid times, effective and engaging digital communications have become integral part of our day to day lives ranging from basic online learning and education delivery to complex remote health care management. This increasing demand has given rise to introduction of many tools to support video conferencing solutions. Many of these tools have limitation that they require dedicated hardware resources and installation of software at client and host end. Increasing use of communication tools inspire us to explore the concept of video conferencing in more depth. The motivation for undertaking this research work is to develop a light-weight chat tool that facilitates peer-peer communication with minimal resources. In simple terms, just a simple web browser at both ends shall be enough to enhance user engagement with customized video calling experiences. Furthermore, many additional attributes like user login authentication, screen recording, screen sharing, text chat, multiuser chat, room management, audio/video controls have been integrated in developed tool. We also performed the performance evaluation of communication quality using various image/video quality measuring metrics like PSNR (Peak signal-to-noise ratio), SSIM (structural similarity index measure) and VMAF (Video Multi-method Assessment Fusion). Our results depict that with the joining of 2nd and 3rd video stream other than the room creator, the PSNR, SSIM and VMAF values are 28.55, 94.84, 61.24 and 26.24, 93.74, 51.62 respectively. The reduction in PSNR and other video quality metrics is observed due the fact that with addition of each user a noise element is inducted in the communicating system. A holistic performance analysis was also performed using different types of browsers and also varying room-sizes. [ABSTRACT FROM AUTHOR]

Technologies focusing on the visually impaired play an important role in assisting the visually challenged and easing their living standards. Previously there have been several other technologies and papers proposed under this category to help the visually challenged. Applications have been built, and are being developed, to help these people work independently without anybody else's need and complete daily tasks easily, without any difficulty using Artificial Intelligence. The proposed application, Noon Gil, supports voice commands and performs operations accordingly using architectures and algorithms like The technologies used are Optical Character Recognition (OCR), Convolutional Neural Networks (CNNs), Natural Language Processing (NLP), Mobile Vision API, TensorFlow Lite, Google ML Kit, MobileNet SSD, etc. Our project which is an android application with an overall accuracy of 94.74% comprises three main functions: Text Detection with an accuracy of 90.83%, Object Detection with 94.40% accuracy and barcode scanning with 99%. [ABSTRACT FROM AUTHOR]