In this paper a Hyper Basis Function based multinetwork classifier for visual crowding evaluation in indoor environment is proposed. Some common topics concerning the classification problem, like the generalisation ability; the robustness, the adaptivity and performance evaluation are explored. The role of doubt classification is also introduced and discussed. Experimental results obtained in a real-world situation are finally reported
Visual Crowding Evaluation: A Neural Network Based Approach
Boninsegna, Massimo;
1995-01-01
Abstract
In this paper a Hyper Basis Function based multinetwork classifier for visual crowding evaluation in indoor environment is proposed. Some common topics concerning the classification problem, like the generalisation ability; the robustness, the adaptivity and performance evaluation are explored. The role of doubt classification is also introduced and discussed. Experimental results obtained in a real-world situation are finally reportedFile 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.