TY  - CONF
AU  - Bodenstein, Christian
AU  - Götz, Markus
AU  - Jansen, Annika
AU  - Scholz, Henrike
AU  - Riedel, Morris
TI  - Automatic Object Detection using DBSCAN for Counting Intoxicated Flies in the FLORIDA Assay
PB  - IEEE
M1  - FZJ-2017-00433
SP  - 746 - 751
PY  - 2017
AB  - In this paper, we propose an instrumentation andcomputer vision pipeline that allows automatic object detectionon images taken from multiple experimental set ups. We demon-strate the approach by autonomously counting intoxicated fliesin the FLORIDA assay. The assay measures the effect of ethanolexposure onto the ability of a vinegar fly Drosophila melanogasterto right itself. The analysis consists of a three-step approach.First, obtaining an image of a large set of individual experiments,second, identify areas containing a single experiment, and third,discover the searched objects within the experiment. For theanalysis we facilitate well-known computer vision and machinelearning algorithms—namely color segmentation, threshold imag-ing and DBSCAN. The automation of the experiment enables anunprecedented reproducibility and consistency, while significantlydecreasing the manual labor.
T2  - 15th IEEE International Conference on Machine Learning and Applications
CY  - 18 Dec 2016 - 20 Dec 2016, Anaheim (USA)
Y2  - 18 Dec 2016 - 20 Dec 2016
M2  - Anaheim, USA
LB  - PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
DO  - DOI:10.1109/ICMLA.2016.0133
UR  - https://juser.fz-juelich.de/record/826187
ER  -