Hey Balraj here, Balraj Arpit, CEO of Balraj Software Pvt. Ltd. and today I want to share something very interesting to you which I believe will make you think twice about it. Did you know that computer do not understand our handwriting. Yes, you get it right. When I was in college and came to know about it then I was stunned and questioned,”Then how Google handwriting input works?” Actually, it easy to develop such application which records pattern of your writing, match with the pattern of the respective letter and convert it into computer text. I’m not talking about it, I’m talking about scanned documents which are handwritten.
Let me tell you about OCR first, OCR stands for Optical Character Recognition which is an electronic scanner that convert typed, handwritten or printed text into machine-encoded text. Now, you must be thinking that OCR does recognize handwriting and there are several apps like Pen to Print in stores that convert handwriting to text. Yes, they do but they’re not accurate technically that you will come to know in this post.
Dr. Sonal Jain, HOD of Computer Science introduced me to ImageCLEF (Image Cross Language Evalation Forum) in 2015, I was curious so I participated in ImageCLEF 2015 with alias name EdXCode. ImageCLEF aims to provide an evaluation forum for the cross–language annotation and retrieval of images. Motivated by the need to support multilingual users from a global community accessing the ever growing body of visual information, the main goal of ImageCLEF is to support the advancement of the field of visual media analysis, indexing, classification, and retrieval, by developing the necessary infrastructure for the evaluation of visual information retrieval systems operating in both monolingual, cross–language and language-independent contexts. ImageCLEF aims at providing reusable resources for such benchmarking purposes.
During my participation at ImageCLEF, I started writing blog in my original handwriting using stylus which made me World’s first blogger who publish his blog in original handwriting. Name of my blog was Dreamed Enough which became popular in more than 50 countries within 2 months of writing, so I made a permanent tattoo on my nape. Eventually, I was selected for Oxford Summer Course at University of Oxford. Later I unpublished the blog because I met an accident and got engaged with my company Balraj Software. Best part of my blog was Google or any search engine could not read what I was writing except title, tags or anything that were typed. OCR apps that can read our handwriting are developed in past couple of years and it’s not yet infallible, you can try some apps or devices. Research and Development is still going and ImageCLEF is a premiere forum for it. I was working on recognizing ancient hand-written manuscripts which was a tough deal. I would love work again on this kind of technologies if needed. To participate or know more about ImageCLEF then visit: https://www.imageclef.org
OCR has been improved that are able to recognize our handwriting but result is not accurate. At the other hand, we don’t have OCR supporting other languages. ImageCLEF is more much more than just handwriting, it’s a forum where researchers from around the globe trying to develop technology that helps computer to understand visual data, i.e. textual, visual, 3D, 3D, etc.
So, we can say that still computer do not understand our handwriting but at the same time the day is not so far when computer will start understanding visual inputs whether it’s manuscript, 3D design, etc.
Hope, you enjoyed this post. Please, rate this post below and share with friends and family.