Outdoor Assistance for Visually Impaired People Using Machine Learning

Visually impaired and blindness caused by various diseases has been hugely increased because of various problems in the eyes and by born also many people are affected by eye problems to giving solutions for that we choose the project. These people face numerous challenges in playing out their everyday tasks, particularly in self-exploring in a situation that is unusual for them. They can't distinguish the item around them and them unable to recognize the object around them precisely much of the time. With the help of Object detection and classification technique, assist the blind people because during their mobility what are the objects present in front of those people it will be easily identified and giving instructions into the speaker itself. In this paper, our main idea is to detect the object in front of blind persons that detected objects are converted into voice feedback. For object detection, we use Single-Shot Detector Model for Train-Test configuration. then we use Play sound and GTTS python cross-platform libraries for classified labels into voice feedback. This system provides an efficient way of guiding the visually challenged people.

Vehicle Motion Planning for the Visually Challenged People Using Ant Colony Optimization

This paper presents a novel proposal to solve the problem of obstacle detection and path planning for visually challenged people based on simple Ant Colony Optimization Meta-heuristic (SACO-MH). The mission of the path planning problem is to enable the vehicle to move from the starting point to the target point while satisfying certain constraints. Constraint conditions are: not a collision with known or unknown obstacles, away from the obstacle as far as possible, determines the shortest path, shortest time and so on. Obstacle detection is made with the help of sensor technology and it is intimated to the user with the help of a smart watch. A voice based navigation system guides the user

VirtualEye: Android Application for the Visually Impaired

In India, almost 18 million visually impaired people have difficulties in managing their day-to-day activities. Hence, there is a need to develop an application that can assist them every time and give vocal instructions in both English and Hindi. In this paper, we introduced a robust lightweight Android application that facilitates visually impaired individuals by providing a variety of essential features such as object and distance detection, Indian currency note detection, and optical character recognition that can enhance their quality of life. This application aims to have a user-friendly GUI well suited to the needs of the blind user and modules like Object Recognition with Image Captioning so that the visually challenged user can gain a better understanding of their surroundings.

Person Identification Using Face and Speech Recognition for Visually Challenged with Mask Detection

A system and method for facilitating a visually impaired person for identifying a person. The method includes the step of storing a plurality of instructions for facilitating the visually impaired person identify the person in front of them by their face and/or voice characteristics by updating our project with Mask Detection using OpenCv and keras. It includes the step of receiving voice signals from the person present in surrounding of the visually impaired person and includes the step of capturing the pictures of a particular person and their surroundings of the visually impaired person and storing the processed data into the database or any storage devices. The data will be processed to AWS server or any local storage for processing and determining the person with the help of the database we already have. After processing and identifying the person with the help of face and voice recognition modules the name is sent to the visually impaired user’s phone in the form of a text message which will be read aloud by his phone’s virtual assistant.