Character Recognition in Web Page Images

Project Title

Character Recognition in Web Page Images

Project Area of Specialization Artificial IntelligenceProject Summary

We always wanted to do something that will help the masses on a daily basis and it didn’t take us a lot of time to notice things in mainstream systems which really hampered the productivity of people. One of these things is the inability to search for text on a webpage written in the form of an image. It happens to us all. Sometimes we can only wish that there was an extension or built in functionality in browsers to help us search through text we are looking for in the images. It is too much of a hassle to look for them manually.

So that's what we are going to do. Develop a browser extension that allows people to search through text in images of a webpage.

Project Objectives

 We are currently looking to develop a browser extension that will help us search text in all the images on a webpage through OCR (Optical Character Recognition) models. The final product of that search in theory will be similar to what we can do by pressing Ctrl + F and typing a keyword in chrome browser.

A search box appears we write the text we are looking for inn search box and we have all the results matching that keyword on the webpage in the form of highlighted text. We are looking to achieve something similar with our extension.

Project Implementation Method

We will use the inbuilt capabilties of javascript DOM to get the images in a webpage after that we will use our trained OCR model to parse the text in images and let the end user search the required text through our extension UI.

Benefits of the Project

This service will allow the users to elevate their browsing experience by giving the ability to search image based text in a webpage. It might be really helpful for the students who are looking for some keywords in a webpage and those keywords are in images. Even normal user will benefit from this since thy might be lookig for something that is not on a webpage.

We might also extend it's applications by text to speech conversion for it to be used by differently abled people

Technical Details of Final Deliverable

The final deliverable of this project is going to be a browser based extension. We will develop this extension by using react as our javascript framework. 

We are also going to use Adobe Illustrator and Adobe XD to develop UI for the extension. We will train our OCR model by using Artificial Neural Networks and we will use Javascript for that purpose.we will also use binary trees to make the ability to search through text faster.

Final Deliverable of the Project Software SystemCore Industry ITOther IndustriesCore Technology Artificial Intelligence(AI)Other Technologies OthersSustainable Development Goals Quality Education, Industry, Innovation and InfrastructureRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	67000
Amazon Web Services Estimated Cost	Equipment	1	30000	30000
Adobe Illustrator Subscription 8 months	Equipment	1	27000	27000
Stationary And Office Supplies	Miscellaneous	1	10000	10000