The 'Neural' Phonetic Typewriter
Computer
Synthesis of print-quality cursive script based on a model of the human handwriting mechanism
Proceedings of the International Conference on Electronic Publishing on Document manipulation and typography
Line thinning by line following
Pattern Recognition Letters
Off-Line Cursive Script Word Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
The State of the Art in Online Handwriting Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Synergy of clustering multiple back propagation networks
Advances in neural information processing systems 2
Experiments in the Contextual Recognition of Cursive Script
IEEE Transactions on Computers
| Hi-index | 0.00 |
A neural net structure was developed to recognize isolated cursive script characters. Characters were composed of features suggested by an established model of handwriting. The model assumes that handwritten characters are formed from a limited number of primitive hand motions characterized by the X-Y oscillations in the vertical (Y) and horizontal (X) directions. Consistent with this model, representation for handwritten characters contain features that are invariant under rotation, translation, changes in size and/or style. Besides their applicability to categorization of handwritten characters, these features are also assumed to control neural ''motor'' activities during writing. The initial application of a single backward error propagation network to handwritten script recognition resulted in slow learning and was limited to approximately 50% correct classification. Changing the architecture to a cluster of smaller networks and adding some simple heuristics improved performance dramatically. In its current form, the approach yields recognition up to 80% for our test data.