MCCCS by OpenImageAnalysisGroup

Related publications and applications to MCCCS

In this section, related publications and applications are summarized which are using the MCCCS system for different kinds of analysis.

Leaf Segmentation & Leaf Counting Challenges

Both challenges (LSC, LCC) are organized in connection with the Computer Vision Problems in Plant Phenotyping (CVPPP) workshop (official website). Here, the MCCCS is used for the prediction of leaf counts and leaf borders. Details can be found in the following conference paper:

Jean-Michel Pape and Christian Klukas. Utilizing machine learning approaches to improve the prediction of leaf counts and individual leaf segmentation of rosette plant images. In S. A. Tsaftaris, H. Scharr, and T. Pridmore, editors, Proceedings of the Computer Vision Problems in Plant Phenotyping (CVPPP), pages 3.1-3.12. BMVA Press, September 2015. pdf

Results for the testing sets

For the testing data sets the ground truth data was not known, the test results (shown below) were supplied by the CVPPP organizers.

The approach by using the MCCCS showed the best results in the 2015 Challenge. The results are presented in the CVPPP at the BMVC 2015 in Swansea.

Results for the LCC:

	CountDiff	AbsCountDiff	PercentAgreement [%]	MSE
A1	-0.21(1.24)	0.82(0.95)	45.5	1.55
A2	-0.56(2.24)	1.67(1.50)	22.2	4.78
A3	-0.34(1.75)	1.27(1.24)	23.2	3.12
All	-0.32(1.63)	1.15(1.20)	30.6	2.74

Results for the LSC:

	BestDice [%]	AbsDiffFGLabels	DiffFGLabels
A1	80.9 (6.3)	0.8 (1.0)	-0.2 (1.2)
A2	78.6 (7.7)	1.7 (1.5)	-0.6 (2.2)
A3	64.5 (16.1)	1.2 (1.2)	-0.3 (1.7)
all	71.3 (15.1)	1.1 (1.2)	-0.3 (1.6)

Leaf disease quantification

Jean-Michel Pape. Ein Klassifikationssystem zur quantitativen Analyse von Krankheitssymptomen im Kontext der Hochdurchstatz-Phänotypisierung von Pflanzen. Master thesis, Dept. of Computer Science, Otto-von-Guericke-Universität Magdeburg, 2016.

Example classification on detached barley leaves infected with powdery mildew.