. "Bari" . "551360" . "Weed detection using chlorophyll fluorescence imaging and artificial neural network" . . "90-809789-1-4" . . "2"^^ . . "We developed the concept of Tyystjarvi et al. (1999) who proposed a new approach to automate the weed identification using specific characteristic features in fluorescence kinetics of individual plant species. We used chlorophyll fluorescence imaging technique by an open imaging fluorometer FluorCam. The measurement on Apera spica-venti, Galium aparine, Stellaria media, Tripleurospermum inodorum as a representatives of weed species and Triticum aestivum, Brassica napus, Beta vulgaris, Helianthus annus as crop representatives were made at two different growth stages. The measurement shows high discrimination ability of the method at cotyledons (first leaf) stage with decreasing sensitivity. To improve the recognition accuracy, we used the artificial neural network classifier, trained on at least 100 plants. The classification rate for discrimination between crops and G. aparine ranged between 90 and 100%. Discrimination between individual weed species the discrimination rate ranged between 85 and 100%." . "Babu\u0161n\u00EDk, Ji\u0159\u00ED" . "We developed the concept of Tyystjarvi et al. (1999) who proposed a new approach to automate the weed identification using specific characteristic features in fluorescence kinetics of individual plant species. We used chlorophyll fluorescence imaging technique by an open imaging fluorometer FluorCam. The measurement on Apera spica-venti, Galium aparine, Stellaria media, Tripleurospermum inodorum as a representatives of weed species and Triticum aestivum, Brassica napus, Beta vulgaris, Helianthus annus as crop representatives were made at two different growth stages. The measurement shows high discrimination ability of the method at cotyledons (first leaf) stage with decreasing sensitivity. To improve the recognition accuracy, we used the artificial neural network classifier, trained on at least 100 plants. The classification rate for discrimination between crops and G. aparine ranged between 90 and 100%. Discrimination between individual weed species the discrimination rate ranged between 85 and 100%."@en . "2005-06-19+02:00"^^ . "[AA69FC00E3BA]" . . "EWRS" . "Weed detection using chlorophyll fluorescence imaging and artificial neural network" . . . "13th EWRS Symposium" . . "RIV/25328859:_____/05:#0000060" . "weed; neural network; chlorophyll fluorescence imaging"@en . . "D\u00E1le jsme rozv\u00EDjeli koncepci Tyystjarvi et al. (1999), kte\u0159\u00ED navrhli nov\u00FD postup automatizovan\u00E9 identifikace plevel\u016F pomoc\u00ED specifick\u00FDch znak\u016F v kinetice fluorescence jednotliv\u00FDch druh\u016F rostlin. Pou\u017Eili jsme metodu zobrazov\u00E1n\u00ED chlorofylov\u00E9 fluorescence svyu\u017Eit\u00EDm fluorometru FlurCam s otev\u0159enou verz\u00ED. M\u011B\u0159en\u00ED na Apera spica-venti, Galium aparine, Stellaria media, Tripleurospermum inodorum jako z\u00E1stupc\u00EDch druh\u016F plevel\u016F a Triticum aestivum, Brassica napus, Beta vulgaris, Helianthus annus jako z\u00E1stupc\u00EDch plodin bylo provedeno ve dvou r\u016Fstov\u00FDch f\u00E1z\u00EDch. M\u011B\u0159en\u00ED ukazuje vysokou rozli\u0161ovac\u00ED schopnost metody ve f\u00E1zi d\u011Blo\u017En\u00EDch l\u00EDstk\u016F (prvn\u00ED list) se sni\u017Euj\u00EDc\u00ED se citlivost\u00ED p\u0159i pozd\u011Bj\u0161\u00EDm m\u011B\u0159en\u00ED. Ke zlep\u0161en\u00ED p\u0159esnosti rozpozn\u00E1n\u00ED jsme vyu\u017Eili klasifik\u00E1toru um\u011Bl\u00E9 neuronov\u00E9 s\u00EDt\u011B tr\u00E9novan\u00E9 alespo\u0148 na 100 rostlin\u00E1ch. Stupe\u0148 rozli\u0161en\u00ED plodin a G. aparine se pohyboval v rozmez\u00ED 90-100%. V pokusu s rozli\u0161en\u00EDm jednotliv\u00FDch druh\u016F plevel\u016F byl stupe\u0148 rozli\u0161en\u00ED 85-100%."@cs . "Detekce plevel\u016F pomoc\u00ED zobrazov\u00E1n\u00ED chlorofylov\u00E9 fluorescence a um\u011Bl\u00E9 neuronov\u00E9 s\u00EDt\u011B"@cs . . "Weed detection using chlorophyll fluorescence imaging and artificial neural network"@en . "3"^^ . "Jago\u0161ov\u00E1, Lenka" . . "Weed detection using chlorophyll fluorescence imaging and artificial neural network"@en . "Detekce plevel\u016F pomoc\u00ED zobrazov\u00E1n\u00ED chlorofylov\u00E9 fluorescence a um\u011Bl\u00E9 neuronov\u00E9 s\u00EDt\u011B"@cs . . . "S6-1; S6-2" . . "3"^^ . "RIV/25328859:_____/05:#0000060!RIV06-MZE-25328859" . . . . "Klem, Karel" . "P(QD1350)" . . "Bari" .