An AI-Based Visual Aid With Integrated Reading Assistant for the Completely Blind

Khan, Muiz Ahmed; Paul, Pias; Rashid, Mahmudur; Hossain, Mainul; Ahad, Md. Atiqur Rahman

doi:10.1109/thms.2020.3027534

Cited by 80 publications

(31 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The aforementioned system is divided into two parts each, with a separate microcontroller, which increases its cost and complexity. Another AI-based visual aid system for the completely blind was proposed [ 31 ]. The system consists of a camera and sensors for obstacle avoidance, image processing algorithms for object detection, and an integrated reading assistant to read images and produce output in the form of audio.…”

Section: Related Workmentioning

confidence: 99%

An IoT Machine Learning-Based Mobile Sensors Unit for Visually Impaired People

Dhou

Nabulsi

Al-Ali

et al. 2022

Sensors

View full text Add to dashboard Cite

Visually impaired people face many challenges that limit their ability to perform daily tasks and interact with the surrounding world. Navigating around places is one of the biggest challenges that face visually impaired people, especially those with complete loss of vision. As the Internet of Things (IoT) concept starts to play a major role in smart cities applications, visually impaired people can be one of the benefitted clients. In this paper, we propose a smart IoT-based mobile sensors unit that can be attached to an off-the-shelf cane, hereafter a smart cane, to facilitate independent movement for visually impaired people. The proposed mobile sensors unit consists of a six-axis accelerometer/gyro, ultrasonic sensors, GPS sensor, cameras, a digital motion processor and a single credit-card-sized single-board microcomputer. The unit is used to collect information about the cane user and the surrounding obstacles while on the move. An embedded machine learning algorithm is developed and stored in the microcomputer memory to identify the detected obstacles and alarm the user about their nature. In addition, in case of emergencies such as a cane fall, the unit alerts the cane user and their guardian. Moreover, a mobile application is developed to be used by the guardian to track the cane user via Google Maps using a mobile handset to ensure safety. To validate the system, a prototype was developed and tested.

show abstract

Section: Related Workmentioning

confidence: 99%

An IoT Machine Learning-Based Mobile Sensors Unit for Visually Impaired People

Dhou

Nabulsi

Al-Ali

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Transient errors, while not permanently damaging hardware components, can cause transient bit flips (from 0 to 1 or 1 to 0) that can cause run failures or incorrect run results. Researchers in academia and industry typically take advantage of the redundancy inherent in modern systems and the availability of redundant resources (such as extra cores, time, or threads) to provide effective solutions to tolerate soft errors [21]. Error detection, error containment, and error recovery are often the basic in providing reliability against soft errors.…”

Section: Ind-var11mentioning

confidence: 99%

Embedded Microprocessor Wireless Communication Data Collection Aids in Early Warning of Default Risk for Internet Finance Bank Customers

2021

Journal of Sensors

View full text Add to dashboard Cite

Thanks to the maturity and innovation of embedded technology, products based on embedded platforms continue to penetrate people’s lives and play a pivotal role in various fields of society, while the development of data acquisition systems based on wireless communication of embedded microprocessors is one of the frontier directions of embedded development. Modern commercial bank risk management system includes risk control organization, risk measurement techniques (including risk warning), risk avoidance techniques, and total risk management model. In this paper, a multichannel data acquisition system combined with a wireless sensor platform is designed for early warning of default risk of Internet financial bank customers, which can realize real-time monitoring, acquisition, display, and data storage of DC signals and indoor environment information output from sensor platforms or electronic devices, and for frequent transactions, fund splitting, and mortgage pledging related to complex customers in today’s e-commerce platform, which triggers when the associated enterprise credit risk presents complexity, continuity, wholeness, multiplicity, volatility, severity, etc., it is used to improve risk judgment and risk warning ability, enhance investment risk response ability, and reduce the related losses caused by marketing risk.

show abstract

“…The third class of devices include Voice Synthesizers, Braille Output terminals and magnifiers that help the user to read and know the information. A smart wearable glass has been developed using Raspberry Pi (RPi) and Ultrasonic sensor by Khan et al [1]. In their work, they have developed modules for obstacle detection and reading assistant.…”

Section: Related Workmentioning

confidence: 99%

“…The Encoder is a Convolutional Neural Network (CNN) that generates a fixed size feature vector for the input image. Instead of the VGG16 model [10] used by [9] or the ResNet-101 model used by [1] , this paper uses the Inception-V3 model trained on the Imagenet dataset as the encoder. Inception-V3 [11] has been chosen because it acts as a multiple feature extractor by computing 1x1, 3x3 and 5x5 convolutions within the same module of the inception network.…”

Section: Encodermentioning

confidence: 99%

VisBuddy -- A Smart Wearable Assistant for the Visually Challenged

Sivakumar¹,

Meenakshisundaram²,

Ramesh³

et al. 2021

Preprint

View full text Add to dashboard Cite

Vision plays a crucial role to comprehend the world around us as more than 85% of the external information is obtained through the vision system. It largely influences our mobility, cognition, information access, and interaction with the environment as well as with other people. Blindness prevents a person from gaining knowledge of the surrounding environment and makes unassisted navigation, object recognition, obstacle avoidance, and reading tasks major challenges. Many existing systems are often limited by cost and complexity. To help the visually challenged overcome these difficulties faced in everyday life, we propose the idea of VisBuddy, a smart assistant which will help the visually challenged with their day-to-day activities. VisBuddy is a voice based assistant, where the user can give voice commands to perform specific tasks. VisBuddy uses the techniques of image captioning for describing the user's surroundings, optical character recognition (OCR) for reading the text in the user's view, object detection to search and find the objects in a room and web scraping to give the user the latest news. VisBuddy has been built by combining the concepts from Deep Learning and the Internet of Things. Thus, VisBuddy serves as a cost efficient, powerful and an all-in-one assistant for the visually challenged by helping them with their day-to-day activities.Keywords visual assistant • image captioning • optical character recognition • object detection • raspberry pi • wearable system

show abstract

An AI-Based Visual Aid With Integrated Reading Assistant for the Completely Blind

Cited by 80 publications

References 39 publications

An IoT Machine Learning-Based Mobile Sensors Unit for Visually Impaired People

An IoT Machine Learning-Based Mobile Sensors Unit for Visually Impaired People

Embedded Microprocessor Wireless Communication Data Collection Aids in Early Warning of Default Risk for Internet Finance Bank Customers

VisBuddy -- A Smart Wearable Assistant for the Visually Challenged

Contact Info

Product

Resources

About