Goto

Collaborating Authors

AllAnalytics - James M. Connolly - Handwriting Recognition Meets Machine Learning

#artificialintelligence

There are places in the tech space where we cease to stare in amazement about what the tech can do. Instead we whine that the tech can't do more. Take the case of handwriting recognition, whether it's what we scribble notes onto a tablet or when we scan handwritten text into a PC. We wish that it was smarter, that it recognized more characters and that the text was searchable and shareable. To be honest, I shouldn't say "we".



Handwriting Recognition - Open Electronics

#artificialintelligence

In this project, I build a pen device which can be used to recognize handwritten numerals. As its input, it takes multidimensional accelerometer and gyroscope sensor data. Its output will be a simple classification that notifies us if one of several classes of movements, in this case 0 to 9 digit, has recently occurred.


Recognition-based Segmentation of On-Line Cursive Handwriting

Neural Information Processing Systems

This paper introduces a new recognition-based segmentation approach torecognizing online cursive handwriting from a database of 10,000 English words. The original input stream of z, y pen coordinates isencoded as a sequence of uniform stroke descriptions that are processed by six feed-forward neural-networks, each designed to recognize letters of different sizes. Words are then recognized by performing best-first search over the space of all possible segmentations. Resultsdemonstrate that the method is effective at both writer dependent recognition (1.7% to 15.5% error rate) and writer independent recognition (5.2% to 31.1% error rate). 1 Introduction With the advent of pen-based computers, the problem of automatically recognizing handwriting from the motions of a pen has gained much significance. Progress has been made in reading disjoint block letters [Weissman et.


Recognition-based Segmentation of On-Line Cursive Handwriting

Neural Information Processing Systems

This paper introduces a new recognition-based segmentation approach to recognizing online cursive handwriting from a database of 10,000 English words. The original input stream of z, y pen coordinates is encoded as a sequence of uniform stroke descriptions that are processed by six feed-forward neural-networks, each designed to recognize letters of different sizes. Words are then recognized by performing best-first search over the space of all possible segmentations. Results demonstrate that the method is effective at both writer dependent recognition (1.7% to 15.5% error rate) and writer independent recognition (5.2% to 31.1% error rate). 1 Introduction With the advent of pen-based computers, the problem of automatically recognizing handwriting from the motions of a pen has gained much significance. Progress has been made in reading disjoint block letters [Weissman et.