This tool converts tablular images into text for people with visual impairments

TableVision, an AI software by Bengaluru’s Continual Engine helps convert images and tables to text for people with visual impairments

Updated - July 21, 2020 06:20 pm IST

Published - July 20, 2020 06:06 pm IST

Networking technology sharing

Networking technology sharing

When it comes to higher studies — from Accountancy and Mathematics to Chemistry and more — words alone are not enough. An array of tables, equations, variables, molecular structures and graphs — all imaginative tools of understanding concepts are necessary.

To help people with visual handicaps overcome this challenge and encourage them into taking up fields of STEM (Science, Technology, Engineering and Mathematics) and Accounts, a Bengaluru-based startup, Continual Engine (CE), has brought out a new tool called TableVision.

“What it basically does is convert images of tables, in JPEG or PNG formats, into HTML, Excel or Alt text formats,” explains K Sriram, advisor to Continual Engine, who also has visual impairment. “For blind students and employees like us, it is complicated to read an image as of today,” he adds.

The tools available, such as a screen reader, reads the text available on screen. Images on accessible websites, and ideally everywhere, should be accompanied by text describing the image, called Alt text. This text is generally put in manually. What TableVision does, is to remove the need to manually enter a description and instead use Artificial Intelligence to read the images.

“We have a repository of table images gathered from different fields. Based on these, the software is able to identify the header rows, the subheadings, and how columns are mapped to those subheadings, and so on,” explains CEO of Continual Engine, Mousumi Kapoor.

“If you look at bar graphs, pie charts, flow charts, maths and chemistry equations, graphs, they are all highly structured, so we can use AI or computer vision algorithms to extract features of these different images and string out a description for them,” she says.

The artificial intelligence and machine learning technology startup also has a branch in Dallas, Texas, US. For the past two years, a team of 30 has been working on providing accessible technology for people with visual disabilities.

In this regard, they have also been publishing e-books related to science and technology. In chemistry, there are many molecular formulae and chemical reactions that need to be studied. These are presented as images in books. For people with visual disabilities, it is difficult to visualise.

Take the methane molecule, for example. It would have to be read out loud as “a central carbon atom, bonded by a hydrogen atom at the top, a hydrogen atom at the bottom, a hydrogen atom on the left, and a hydrogen atom on the right”.

Sriram says that so far, many publishers and academic institutions and NGOs for the blind have approached CE to use the tool. “In fact, we are also getting conversion orders on per image or per book basis, not just for the whole tool as a product,” he adds.

Visit https://tablevision.ai/

0 / 0
Sign in to unlock member-only benefits!
  • Access 10 free stories every month
  • Save stories to read later
  • Access to comment on every story
  • Sign-up/manage your newsletter subscriptions with a single click
  • Get notified by email for early access to discounts & offers on our products
Sign in

Comments

Comments have to be in English, and in full sentences. They cannot be abusive or personal. Please abide by our community guidelines for posting your comments.

We have migrated to a new commenting platform. If you are already a registered user of The Hindu and logged in, you may continue to engage with our articles. If you do not have an account please register and login to post comments. Users can access their older comments by logging into their accounts on Vuukle.