16/06/2022
Long before computers or the internet, doctors were still treating patients, students were still taking notes in class, letters were still being written and books were being published. You get the drift. The art of writing has been around for centuries. Digitization came with the extra burden of having to either store the handwritten scans as images or having manually type every word on the manuscripts to convert them to softcopies. Then OCR came along but it was still not perfect. Access to data containing handwritten text and the cheap processing power has enabled humans to train models that ‘learn’ like a human being to ‘read’ text. The concept of learning comes from how the human brain works.Think of a child, they come into the world not knowing how to speak or read but give the child enough examples on how an ‘a’ looks and it becomes second nature to identify the letter. In fact, its hard not to read text when you see it. Your brain will read any text it can identify on autopilot.
Text extraction using AI models that work on handwritten text or print scans can be used to save time needed to convert manuscripts to softcopies. However, the process faces a few challenges:
Full analysis on our blog mlforbusiness.com
