Comparison of efficient AI algorithms for assisting and conquering infirmity of blind people: improved approach for visually impaired
Comparison of efficient AI algorithms for assisting and conquering infirmity of blind people: improved approach for visually impaired
- Author(s): K. R. S. Al-Kiyumi 1 ; N. A. S. Al-Tourshi 1 ; F. M. S. Al-Muqbali 1 ; F. Hajamohideen 1
- DOI: 10.1049/icp.2021.0875
For access to this article, please select a purchase option:
Buy conference paper PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Thank you
Your recommendation has been sent to your librarian.
- Author(s): K. R. S. Al-Kiyumi 1 ; N. A. S. Al-Tourshi 1 ; F. M. S. Al-Muqbali 1 ; F. Hajamohideen 1
-
-
View affiliations
-
Affiliations:
1:
Department of Information Technology , Sohar College of Applied Sciences , Sultanate of Oman
Source:
3rd Smart Cities Symposium (SCS 2020),
2021
p.
365 – 370
-
Affiliations:
1:
Department of Information Technology , Sohar College of Applied Sciences , Sultanate of Oman
- Conference: 3rd Smart Cities Symposium (SCS 2020)
- DOI: 10.1049/icp.2021.0875
- ISBN: 978-1-83953-522-2
- Location: Online Conference
- Conference date: 21-23 September 2020
- Format: PDF
Disability of human beings is greatly affecting the potential normal life of the affected people especially the blind. Modern technologies help visually impaired to practice their day to day activities indisputably. They practically need an aide to move across the nook and corner and in overpass the street, in sensing or mingling. There are ongoing scientific researches in the area of rectifying blindness, but it has to go long way to achieve the solution. Also, there are research unleashes the ideas of assisting the blind people deficiency but lacks in technological aspects of implementation. One of our previous research provides the AI technologies to recognise and lead the daily life of the visually impaired in a much better way using face recognition LBPH and Haar algorithms. In the evolution view of face recognition and AI technologies, this research looks to enhance the way the other researches done and helps visually impaired to walk and carry out their daily activities easiest way possible and safety by using Internet of Things (IOT) and Artificial Intelligence (AI). This study articulates the different sets of algorithms and compare the features that help in amending the existing research with solidarity to help the visually impaired community. The aim of this comparison of algorithms is to provide the smart blind device to detect color, object, faces. Also, this research discusses the human perception of color images with different models and several color models such as RGB, YUV, CMY, CMYK and HIS are discussed and compared. However, for face detection, this research compares the pros and the cons of Eigenfaces, Local Binary Patterns Histograms (LBPH), Fisherfaces, Scale Invariant Feature Transform (SIFT), Speed Up Robust Features (SURF) algorithms. The programming tools used in this research are OpenCV and Python. The IoT devices used in this experiment are Raspberry Pi Wide Angle Camera Module 2, Arduino Uno and GSM, GPS modules. In conclusion, this research enhances the visually impaired people life with better AI and IoT technologies.
Inspec keywords: handicapped aids; image classification; cameras; assisted living; feature extraction; face recognition; artificial intelligence; Internet of Things; image colour analysis
Subjects: Computer vision and image processing techniques; Computer assistance for persons with handicaps; Image recognition