In this paper, a new set of aspect invariant moments for handwritten numeral recognition are presented. These new moments exhibit two useful properties. Firstly, they are aspect invariant. This eliminates the need for size normalization of the unconstrained numerals. Secondly, their dynamic range remains constant with moment order. This overcomes the problem of diminishing high order moments, which occurs when other moment invariants are used. Thus, aspect invariant moments are particularly suitable for use with neural networks. Experimental results (using a multilayer perceptron and the backpropagation learning rule) show that a very high recognition rate (98.73%) and low substitution rate (1.06%) can be achieved on a totally unconstrained handwritten numeral database.<>
A new set of moment invariants for handwritten numeral recognition
Proceedings of 1st International Conference on Image Processing ; 1 ; 154-158 vol.1
01.01.1994
400770 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
A New Set of Moment Invariants for Handwritten Numeral Recognition
British Library Conference Proceedings | 1994
|Script Independent Handwritten Numeral Recognition
British Library Conference Proceedings | 2006
|A hybrid multiple classifier system of unconstrained handwritten numeral recognition
British Library Online Contents | 2007
|A Hybrid Multiple Classifier System of Unconstrained Handwritten Numeral Recognition
British Library Online Contents | 2005
|