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, orientations and the presence of noise, has been developed. The HSP is an internal, noise-robust, noninformation-preserving operator which combines the properties of invariance of the high order pattern spectrum and the properties of noise robustness of the statistical pattern spectrum. A neural network trained by a back-propagation algorithm has been used to test the method on different classification problems. Experimental results are presented on both synthetic and real images corrupted by various levels of noise and containing an object in different positions. Comparisons with other existing shape descriptor operators have been also performed.
Noise robust and invariant object classification by the high-order statistical pattern spectrum
FORESTI, Gian Luca;
1999-01-01
Abstract
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, orientations and the presence of noise, has been developed. The HSP is an internal, noise-robust, noninformation-preserving operator which combines the properties of invariance of the high order pattern spectrum and the properties of noise robustness of the statistical pattern spectrum. A neural network trained by a back-propagation algorithm has been used to test the method on different classification problems. Experimental results are presented on both synthetic and real images corrupted by various levels of noise and containing an object in different positions. Comparisons with other existing shape descriptor operators have been also performed.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.