Hand-Written Character Recognition Using Kohonen Network
Pankaj Agarwal · 2011
This paper presents a simple learning rule for recognition of mouse dragged character on our computer screen using artificial neural network. We use Kohonen self organization map for pattern classification which employs unsupervised learning algorithm. The results are quite encouraging in terms of percentage of characters being successfully recognized. One advantage of proposed scheme is that the system is quite tolerant to changing conditions and inputs. The system consistently learns. Moreover the recognition ratio is excellent in the proposed system.