Abstract:
In spite of advances being made in modern technology and computer vision models. However, they usually lack the effective intelligent solutions for understanding and inte...Show MoreMetadata
Abstract:
In spite of advances being made in modern technology and computer vision models. However, they usually lack the effective intelligent solutions for understanding and interpreting objects. This object recognition and conversion to speech as a broadcasting can be used for visually impaired people to address their unique challenges traversing through life. There is a pressing need for a nuanced approach that alliance with the transformers functionality to accept, understand, and tread through the vast expense of features that are extracted from the images that are received as an input to the model and then processed for their efficient identification accurately so that this identification used in real life. This tech is hereby used for a variety of tasks such as QR codes, recognizing currency codes, fruits, vegetables, street signs, etc. This is used to build an environment more inclusive and catering to the needs of the visually challenged.
Published in: 2024 IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS)
Date of Conference: 24-25 February 2024
Date Added to IEEE Xplore: 02 April 2024
ISBN Information: