CIEGO Application is a very reliable android based application which has a vast scope because it is a basic utility application. The purpose behind the development of CIEGO application is to help the visually impaired ones recognizing their loved ones for which we are using an Android platform on wh
CIEGO application
CIEGO Application is a very reliable android based application which has a vast scope because it is a basic utility application. The purpose behind the development of CIEGO application is to help the visually impaired ones recognizing their loved ones for which we are using an Android platform on which the user has accessibility to give vocal inputs and receives back vocal output from the application which recognizes face, text, object, shape from a particular range of area. We use Open-CV and OCR libraries for this purpose.
The objective for developing this application is to help the disabled ones of the society specially the blind ones. The core purpose is to let the blind ones know what they are looking at or what object they are holding in their hand.
The objective of our work was to develop a gadget comprising of S.O.F.T (Shape, Object, Face, Text) Recognition that may help out the visually impaired ones of the society .The approach is to design an android application (CIEGO Application). Application will be able to work using a simple android smart-phone. The user interface of the application is very simple and easy to use comprising of single button on the main screen of the application that works as a medium for getting a vocal input from the user via a microphone of the smart phone. The system then checks and determines the vocal input and opens the respective module requested through the vocal input, the recognition starts as per the module.
In case the module is text recognition the OCR (Optical Character Recognizer) start its working by collecting the characters obtained from the real time image and process it to form the correct combination of the characters for the user, the text to speech feature now starts reading out the character(s) for the user.
The next case then could be the face recognition module. This module has quite a complex working initially. Firstly this module allows user to save the facial images with their respective names through the user interface. The names and images are saved at the back-end of the application using the Bitmap factory (the module is currently storing the images on the back end using the Bitmap factory but the future plans are to use SQL-Lite database when the application will be commercialized). After this initial procedure the face recognition module is ready to recognize the faces using the open-CV facial recognition library. The camera is already active and ready to send the real time images to the system for recognition. The facial images are then matched to those present at the back-end. The application after recognizing, calls out the name of the person whose face is being recognized. Same goes for Object and Shape recognition.
The motivating point for building/developing this application is to help the disabled ones of the society specially the blind ones. The core purpose is to let the blind ones know what they are looking at or what object they are holding in their hand. As per the World Health Organization (WHO) statistics of June 2012, there lives a sum of 285 million visually impaired individuals across the globe. Moreover, according to same statistics 90 percent out of this sum resides in developing countries where modern assistive gadgets are either unavailable or unaffordable. We will be trying to make such a gadget for the large sector of the community; this will have a positive impact on the society.
As the client opens the CIEGO App he enters in a world of recognition ease. Now he can recognize many objects, shapes, colors or even the text by just placing the camera at the thing he wants to be recognized.
The client first opens the app after which he tells the system what he wants to recognize using the app through voice input, the system then collects the input image through the camera, processes the image and gives the output vocally to the user so that he could hear what object he had been looking at. A normal image would be sent to the system where it will be processed according to clients desired output, whether he wants to recognize the object, shape, color, text .
The vocal input/output is a helpful feature as the primary user will be the visually impaired and therefore can’t read or write.
| Item Name | Type | No. of Units | Per Unit Cost (in Rs) | Total (in Rs) |
|---|---|---|---|---|
| Total in (Rs) | 0 |
The name of our Website is Feeling & Healing Hub. We give this name to our...
This project serves the need to automatically identify and track the location of people us...
Collectively this work aims to improve Biologists/Scientist understanding to use our compu...
The study on different development technique has been carried out. Two type of development...