Now computers will understand and recognize your handwriting

Everybody will like to have their handwriting being recognized by their computers. In this project we are going to see that dream of yours coming true, In this project the engineers have designed and implemented a Handwriting Recognition System using a touch screen from a Palm Pilot which is a second generation PDA device that is m125, a black and white TV and a Mega32 microcontroller.

Unfortunately, due to the lack of specifications regarding the built-in LCD on the Palm Pilot, we were unable to reverse engineer the LCD protocol, however, now we are able to understand how the touch screen works after some careful investigations.

The previous project was highly adaptive, which used sophisticated algorithm, it should be able detect any patterns. But in current project, however, we choose to use a simple algorithm, Nearest Neighbourhood Algorithm which is the first algorithms used to determine a solution to the travelling salesman problem. In it, the salesman starts at a random city and repeatedly visits the nearest city until all have been visited. It quickly yields a short tour, but usually not the optimal one. So we use this algorithm as we have very limited amount of time. Thus far it can only recognize simple characters but it is easily extensible. There is no fundamental difference between recognizing a character and any other kind of patterns using our algorithm.

 As far as the source and the origination of the project is concerned, initially it began with automatic speech recognitions in the lab later it was considered as a very bad place for the same purpose since  Mega32 is too slow for full-fledged Fast Fourier Transform algorithm. Then they came across Palm PPP a last year project when they were searching for new ideas, it is a Simon game based on a Palm m125 touch screen. They thought it would be fantastic idea to do handwriting recognition like Graffiti. It requires a touch screen, a novel hardware input device and some smart programming, a perfect combination for a detecting handwriting patterns.