The proposed method consists of three processing levels: (a) Acquisition of images via MARC. (b) Feature extraction: all the sub-images were characterized by 12 features made by color moments in each channel of HSV space. (c) Classification: a Parellel Multiple Classifier System (PMCS) was used to classify sub-images as rust or non-rust. PMCS exhibited the great advantage to perform in parallel computation, drastically reducing the computational time.
Notes on Parallel Multiple Classifier System for Rust Detection in Marine Vessel Inspection
Rosalia Maglietta;Annalisa Milella;Massimo Caccia;Gabriele Bruzzone
2016
Abstract
The proposed method consists of three processing levels: (a) Acquisition of images via MARC. (b) Feature extraction: all the sub-images were characterized by 12 features made by color moments in each channel of HSV space. (c) Classification: a Parellel Multiple Classifier System (PMCS) was used to classify sub-images as rust or non-rust. PMCS exhibited the great advantage to perform in parallel computation, drastically reducing the computational time.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.