Noise robust and invariant object classification by the high-order statistical pattern spectrum

A new shape descriptor, the high order statistical pattern spectrum (HSP), able to extract from real images a set of descriptive features which can be used to classify objects regardless of their positions, sizes, orientation s and the presence of noise, has been developed. The HSP is an internal, no ise-robust, noninformation-preserving operator which combines the propertie s of invariance of the high order pattern spectrum and the properties of no ise robustness of the statistical pattern spectrum. A neural network traine d by a back-propagation algorithm has been used to test the method on diffe rent classification problems. Experimental results are presented on both sy nthetic and real images corrupted by various levels of noise and containing an object in different positions. Comparisons with other existing shape de scriptor operators have been also performed.