Auflistung nach Autor:in "Schikora, Marek"
1 - 4 von 4
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragA framework for multiple radar and multiple 2D/3D camera fusion(Informatik 2009 – Im Focus das Leben, 2009) Schikora, Marek; Romba, Benedikt
- KonferenzbeitragPixel-based classification method for detecting unhealthy regions in leaf images(INFORMATIK 2011 – Informatik schafft Communities, 2011) Madhogaria, Satish; Schikora, Marek; Koch, Wolfgang; Cremers, DanielIn this paper, we present a pixel-based, discriminative classification algorithm for automatic detection of unhealthy regions in leaf images. The algorithm is designed to distinguish image pixels as belonging to one of the two classes: healthy and unhealthy. The task is solved in three steps. First, we perform segmentation to divide the image into foreground and background. In the second step, support vector machine (SVM) is applied to predict the class of each pixel belonging to the foreground. And finally, we do further refinement by neighborhood-check to omit all falsely-classified pixels from second step. The results presented in this work are based on a model plant (Arabidobsis thaliana), which forms the ideal basis for the usage of the proposed algorithm in biological researches concerning plant disease control mechanisms.
- KonferenzbeitragProbabilistic classification of disease symptoms caused by salmonella on arabidopsis plants(INFORMATIK 2010. Service Science – Neue Perspektiven für die Informatik. Band 2, 2010) Schikora, Marek; Schikora, Adam; Kogel, Karl-Heinz; Koch, Wolfgang; Cremers, DanielSeveral reports have linked food poisoning with the consumption of raw vegetables and fruits contaminated by Salmonella. Most studies suggested an extracellular lifestyle of Salmonella on plants. However, more recent studies show that Salmonella are also able to colonize the intracellular compartment of various plant tissues causing chlorosis and eventually death of infected organs. The aim of this work is to present a probabilistic classification algorithm for disease symptoms on Arabidopsis thaliana plant in order to improve the current biological research. The algorithm itself uses images of Arabidopsis thaliana leaves as input and consists of two steps. The first step is the detection of pixels belonging to a leaf. This is done with a globally optimal color segmentation method. The second step is realized with a probabilistic framework to classify each pixel. Finally a morbidity rate is computed based on the classification result.
- KonferenzbeitragZur landwirtschaftlichen Nutzung der Datenfusion – Probleme und Lösungsansätze(IT-Standards in der Agrar- und Ernährungswirtschaft – Fokus: Risiko- und Krisenmanagement, 2014) Heinskill, Josef; Koch, Wolfgang; Krozer, Viktor; Schikora, Marek; Schikora, Adam