Artificial Eye for the Blind

Benagi, Abhinav, Narayan, Dhanyatha, Rage, Charith, Sushmitha, A

arXiv.org Artificial Intelligence 

Visual Impaired humans cannot perceive their environment and navigate like normal Humans do, which results in reduced mobility.They also fear the society and are often treated as incable submissive section of society. In the light of making a blind person overcome his fear and step out to the society independently and confidently, we have added a few features to the blind stick enabling the blind to be able to detect gender,age and basic actions done by a person through which he can react to his opposite party in an appropriate manner. This project is useful when it comes to blind people being able to detect facial expressions in order to respond to environmental situations precisely.It also helps them detect the age and gender of the person to respond accordingly. It also helps them interpret text from images without relying on the third party for help.For security purposes, it helps in detecting the actions carried out by the person in the surroundings and taking appropriate actions against the situation. If this project is implemented appropriately, it can help blind people in carrying out a wide range of everyday activities effortlessly which adds on a lot of scope for the juvenile generation. For facial expression detection, AI uses a lot of non-verbal functionalities such as facial expressions, body language and gestures. Whereas, to determine the age and gender it uses a broad dataset which includes a significant amount of pictures of men and women contributing to the dataset which in turn helps in accurately determining the age and gender of the person.Text to speech conversion is done by storing many different font and text images in patterns. It uses matching algorithms to distinguish between text images, character by character.In conclusion, the blind stick accommodates multiple features each of which can be accessed with separate functionalities such as, one functionality for action and object detection, one for image to speech conversion, one for facial recognition.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found