Pubblicazione scientifica

In VIVO Fish Diet Discrimination using Selected Hyperspectral Image Classification Methods

FILONE TECNOLOGICO	TEMA
trasformazione e commercializzazione

RIASSUNTO

The main aim of this study was to evaluate the performance of different supervised classification methods to discriminate live fish based on their diet received during cultivation using hyperspectral imagery system. 160 rainbow trout were fed either a commercial based diet or completely plant-based diet. Hyperspectral images of the live fish acquired in the spectral region of 394-1090 nm. Spectra were extracted from the region of interest and pre-processed using Savitzky-Golay smoothing algorithm to remove noise. Afterward, three classifiers including support vector machine, random forest and k-nearest neighbors were used. According to the criteria of correct classification rate and kappa coefficient, the support vector machine with linear kernel was achieved the best performance for classirying live fish due to their diet.

DATA

Data di pubblicazione: 01/09/2018

AUTORI

MOHAMMADMEHDI SABERIOON
PETR CISAR
LAURENT LABBE

ENTE DI AFFERENZA

UNIVERSITY OF SOUTH BOHEMIA IN CESKE BUDEJOVICE FACULTY OF FISHERIES AND PROTECTION OF WATERS SOUTH BOHEMIAN RESEARCH CENTRE OF AQUACULTURE AND BIODIVERSITY OF HYDROCENOSES INSTITUTE OF COMPLEX SYSTEMS ZAMEK 136 NOVE HRADY 37 333 CZECH REPUBLIC
INRA UE 0937 PEIMA PISCICULTURE EXPERIMENTALE INRA DES MONTS D’ARREE SIZUN FRANCE
UNIV SOUTH BOHEMIA IN CESKE BUDEJOVICE FACULTY OF FISHERIES & PROTECTION OF WATERS SOUTH BOHEMIAN RSCH CTR AQUACULTURE & BIODIVERSITY OF HYDROCENOSES INST COMPLEX SYS ZAMEK 136 NOVE HRADY 37 333 CZECH REPUBLIC

RIVISTA

2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS) (Page(s): 1-5)

indietro