Eye For Blind
The project is focusing on an app for blind people this app helps the blinds. In which our app is activated with the voice using Google Assistant and then after app activation the app open in camera mode to capture the image using voice of blind or physically impaired person, we can capture image by
2025-06-28 16:32:29 - Adil Khan
Eye For Blind
Project Area of Specialization Artificial IntelligenceProject SummaryThe project is focusing on an app for blind people this app helps the blinds. In which our app is activated with the voice using Google Assistant and then after app activation the app open in camera mode to capture the image using voice of blind or physically impaired person, we can capture image by voice intent. The Image Capture is process through Google Vision API and returns a word or string of words Then the speech guides the blind person about what camera sees.
The activation is based on the intent of the blind people the person voice then app activated, there are various API’s goes side by side Google CameraX, Google Voice Integration, Google Vision / Amazon Rekognition, Google Text-to-speech.
We are going to use the Android platform for this app the Android Studio, Java Language, XML for interfaces, Artificial Intelligence for the intent recognition and API to perform our speech work.
Project Objectives- Object Detection and Raw Recognition.
- App open with voice using Google Assistant.
- Image Clicked Through Voice.
- Image Processed Through Google Vision API / Amazon Rekognition
- The Detected Object Will Convert into Voice.
- Google Text-to-Speech convert word into Voice.
- This Project focuses on detecting different objects with live web camera or by mobile back camera using Android Java, XML and Python if needed.
- Utilize Google Vision API which detect object and returns name of Object. Also, we use CameraX API for Camera Mood and Google Text-to-Speech.
API’s Used:
Google CameraX
Google Vision / Amazon Rekognition
Google Voice Integration Library
Google Text-to-Speech
Benefits of the ProjectThis software can be used in medical as well as in securities fields. As describe above it will help Blind and Physically impaired people to use mobile camera as Human Eye Because They Listen what camera Seen.
In the future, plan is to expand this project to detect multiple object and faces.
Technical Details of Final Deliverable- Object detection system.
In first step, object detection system will be designed as prototype. The App open with voice using Google Assistant and open in Camera Mood.
In First Step,
The App take voice as input for capturing Image.
Voice Integration
In First Step,
The App take voice as input for capturing Image.
This will be an integrated system with all above mentioned features in it.
Image Process Through Google Vision API
In This Step the image is processed in Google Vision API or Amazon Rekognition API, detect and recognize the objects in the image
Text-to-Speech
As Google Vision API returns word and the text-to-speech API converts the word into Speech for the Person
Project documentation
User manual will also be provided to get information about software usage.
Final Deliverable of the Project Software SystemCore Industry HealthOther Industries Security Core Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Good Health and Well-Being for PeopleRequired Resources| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 42400 | |||
| Google Vision API / Amazon Recognition API | Equipment | 200000 | 0 | 32400 |
| Cloud Server | Equipment | 1 | 10000 | 10000 |