The use of polar representation of covariance descriptors, suitable for the classification of circular feature sets, is proposed. It overcomes the implicit limits of state-of-the-art methods based on axis-oriented rectangular patches. The suitability of the proposed solution is verified on two case studies, namely head detection and polymer classification in photomicrograph contexts.
Polar Representation of Covariance Descriptors for Circular Features / Gualdi, Giovanni; Prati, Andrea; Cucchiara, Rita. - In: ELECTRONICS LETTERS. - ISSN 0013-5194. - STAMPA. - 46:15(2010), pp. 1063-1064. [10.1049/el.2010.0021]
Polar Representation of Covariance Descriptors for Circular Features
GUALDI, Giovanni;PRATI, Andrea;CUCCHIARA, Rita
2010
Abstract
The use of polar representation of covariance descriptors, suitable for the classification of circular feature sets, is proposed. It overcomes the implicit limits of state-of-the-art methods based on axis-oriented rectangular patches. The suitability of the proposed solution is verified on two case studies, namely head detection and polymer classification in photomicrograph contexts.
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris
