A new set of moment invariants for handwritten numeral recognition

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