Kernel descriptors consist in finite-dimensional vectors ex- tracted from image patches and designed in such a way that the dot product approximates a nonlinear kernel, whose pro- jection feature space would be high-dimensional. Recently, they have been successfully used for fine-gradined object recogntion, and in this work we study the application of two such descriptors, called EMK and KDES (respectively de- signed as a kernelized generalization of the common bag-of- words and histogram-of-gradient approaches) to the MAED 2014 Fish Classification task, consisting of about 50,000 un- derwater images from 10 fish species.
Fish species identification in real-life underwater images
Palazzo S.;Murabito F.
2014-01-01
Abstract
Kernel descriptors consist in finite-dimensional vectors ex- tracted from image patches and designed in such a way that the dot product approximates a nonlinear kernel, whose pro- jection feature space would be high-dimensional. Recently, they have been successfully used for fine-gradined object recogntion, and in this work we study the application of two such descriptors, called EMK and KDES (respectively de- signed as a kernelized generalization of the common bag-of- words and histogram-of-gradient approaches) to the MAED 2014 Fish Classification task, consisting of about 50,000 un- derwater images from 10 fish species.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.
