Visually impaired individuals often face social limitations and struggle in unfamiliar environments without assistance, as visual information is crucial for most daily tasks. As such, the project proposed to utilize AI, Machine Learning, IoT, and Text Recognition to aid those who are blind or visually impaired. Its main objective is to implement various features such as a Vision and Voice assistant, Image Recognition, Face Recognition, Object Identification, e-book text extraction, chat bot, and obstacle notification to help individuals with visual impairments.
By doing so, the project improves the quality of life for visually impaired individuals by providing them with greater independence and support by using voice commands to identify objects in their surroundings, perform text analysis to recognize text on physical documents, and utilize face recognition technology to identify individuals.
By doing so, the project improves the quality of life for visually impaired individuals by providing them with greater independence and support by using voice commands to identify objects in their surroundings, perform text analysis to recognize text on physical documents, and utilize face recognition technology to identify individuals.

https://utasoman-my.sharepoint.com/:f:/g/personal/venkadeshan_ramalingam_utas_edu_om/Eg9oDlvkQM5OqEQF0EJPNqYBrliShoDXcit6WiSlTNvnWw?e=pqb5XQ

• Oman

• Older persons
• People with disabilities
• Adult
• Elderly

YES. This research work is replicable when the entire research process is conducted again, using the same methodologies and techniques or even with the high user-end hardware devices support with massive sample data set pass as input for the techniques such as Person Identification, Object Identification, Voice Commands, and Text Extraction. Since all the Machine Learning algorithms codes are Open Source, this research work could be replicable with incorporating the concepts of OpenCV with YOLO, Voice commands recognition, and the training set for identifying the person. This creative approach may be widely adopted and modified with the help of collaborative endeavors, community engagement, and collaborations with assistive technology organizations, opening it out to a wider spectrum of people worldwide.

YES. The sustainability of this open-source project initiatives like OpenCV, YOLO, OCR, TensorFlow, E-Speak, and Speech Recognition using Google Speech API and Python depends on the collective support and collaboration of individuals, companies, and organizations. Moreover, this project can be easily integrated and incorporated with the recent advancement in AI and Machine Learning technologies / Algorithms. With the support of emerging trends, we can keep the project up-to-date and future adaptable.

AI-IoT Research and Innovation Project Centre: The domain of education has also adopted the AI and IoT technological services to move from traditional methods to sophisticated and advanced teaching and learning approaches to cope with learning needs and raise quality. It is evident from our project work developed in the AI-IoT Research and Innovation project centre, UTAS-Shinas tend to improve the student’s academic performance by providing a smart learning environment and hands-on practical methods of interacting with smart devices. By carried out such a project development in the research laboratories impact significantly in advancing sustainable development and building a more inclusive and equitable information and knowledge digital societies, making it a valuable platform for promoting the benefits of ICTs and addressing digital transformation challenges. Its interactive, inclusive, and comprehensive agenda and programme, which are shaped by multiple stakeholders in an open consultation process, have enabled meaningful discussion, training and digital cooperation towards common goals.