Shopping Assistant for Blind Community

Millions of people live in this world with incapacities of understanding the environment due to visual impairment. Although they can develop alternative approaches to deal with daily routines, they suffer from certain navigation diffculties as well as social awkwardness. For example, it is very diff

Project Title

Shopping Assistant for Blind Community

Project Area of Specialization

Computer Science

Project Summary

Millions of people live in this world with incapacities of understanding the environment due to visual impairment. Although they can develop alternative approaches to deal with daily routines, they suffer from certain navigation diffculties as well as social awkwardness. For example, it is very difficult for them to find a particular room in an unfamiliar environment. The aim of Shopping Assistant for Blind
Community is to help blind people in detecting and identifying objects when they are in a new place. This system captures the scene by the mobile camera and detects the objects and uses a conversational agent that guides the person suffering
from visual impairment to inform them about objects, their positioning, and guide them to the right path and allow them to pick required things by guiding them about the object by the voice when they go shopping. The system captures video/images with a mobile camera. In the next step, the system does image recognition to detect and identify objects and determine the distance or position on an object, by the machine learning algorithms. For object classification, the input images compared with the object category that was originally stored in the system. Finally, the objects are informed to the blind person by using voice.

Project Objectives

Industry Objectives:
Since 1970, object recognition technologies have matured to a point at which exciting applications are becoming possible for visual substitution. In fact, the industry has created a variety of computer vision products and services by developing new electronic aids for the blind in order to overcome the difficulties that the dog and cane do not respond to. But this aims also to introduce an app in society
that restores a central function of the visual system which is the identification of surrounding objects and guide the blinds by using a speech assistant. Thus, our contribution is to present a mobile application based on evaluating fast and robust algorithms to recognize and locate objects in surrounding that helps blind people to identify a set of objects used in everyday routine thereby enabling them to work independently.

Research Objectives:
One of the goals of this project is to describe a scene as precisely as a human being. One of the stepping stones towards this goal is object detection wherein the different objects of significance in the scene are detected and it is attempted to understand underlying semantics. This project tries to transform the visual world into the audio world with the potential to inform blind people of objects as well as
their spatial locations in a precise manner. It also focuses on providing Speed for real-time detection object detection algorithms need to not only accurately classify and localize important objects, but also need to be incredibly fast at
prediction time to meet the real-time demands of blinds people.

Academic Objectives:
Artificial intelligence is rapidly changing the world. AI enhances information throughput and efficiency, helping people create new opportunities. We're talking about new streams for revenue generation, savings, and jobs. It enhances users' lifestyle choices by using search algorithms that provide targeted information. So the objective of this project is to implement the learning of university education
this project using computer vision and natural language processing.

Project Implementation Method

The proposed system is given input in either of the forms i.e., a recorded video or a video stream through webcam.

The system is built by following the six major steps below:
Image/video capture: In this step, a camera used to capture the images/video of objects in an indoor environment. This is the first step in any artificial visual system.

Preliminary processing techniques: This step focuses on the removal/elimination of background noise, enhancing contrast, and binarization of images.

Object detection: In this step, various object detection algorithms used to detect the objects (around 15-20 which includes table, currency, medicine, glass,
humans etc.) in an image.

Object recognition: It is a computer vision technique to identify the objects in images.The proposed system used to identify different categories of objects.

Text generation: In this step, the objects in images recognized and calculate the distance from where the objects are captured and determine the objects name and converted into text.

Speech conversion: This is the final step in the guiding system development. The generated text converted into speech to assist blind people through a conversational agents.

Benefits of the Project

• The aim is to build a program that will direct visually impaired people to reach the desired destination and help them understand the natural world around them.
• To help visually disabled individuals who are confronting difficulty with everyday tasks in the public.
• Android application is easily accessible for every user.
• It has many versions with extending features and properties (e.g. lollipop. jellybean, kit Kat, etc).
• This application is most useful for a blind person. No need to carry a walking stick.

Technical Details of Final Deliverable

1. Proposal
2. Literature Review
3. Dataset Formation
4. Time for experimental Setup
5. Experimentation
6. Analysis of Result
7. Thesis Submission

The objects in images recognized and calculate the distance from where the objects are captured and determine the objects name and converted into text. The generated text converted into speech to assist blind people through a conversational agent.

Final Deliverable of the Project

Software System

Core Industry

IT

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People, Reduced Inequality

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com