Comparison of Two Techniques of Pattern Recognition in the Image Analysis-Based Wheat Stalk Length Characterization

Jan Thore Benthien 1 , Sabrina Heldner 2 , Benjamin Seppke 3 , and Jan Hörbelt 4
  • 1 Thünen Institute of Wood Research, , Leuschnerstraße 91, 21031, Hamburg, Germany
  • 2 Thünen Institute of Wood Research, , Leuschnerstraße 91, 21031, Hamburg, Germany
  • 3 Cognitive Systems Laboratory, Department of Informatics, MIN Faculty, University of Hamburg, Vogt-Kölln-Straße 30, 22527, Hamburg, Germany
  • 4 Faculty of Life Sciences, Rhine-Waal University of Applied Sciences, Marie-Curie-Straße 1, 47533, Kleve, Germany


The chaff quality or, more specifically, the distribution of stalk length after straw shredding during wheat harvest with a combined harvester is of significant interest for ploughless tillage practices. The currently applied characterization methods (manual length measurement or the cascade sieve analysis) are time-consuming and labour-intensive. Image analysis-based size characterization has the potential to solve these problems. In this study, two techniques of digital image processing, the well-known method of image moments (rectangular model) and a sub-pixel skeletonization approach (flow lines-tracing), were applied comparatively for stalk length measurement. Upon applying the rectangular model, the analyzed stalks were found to be longer than when the flow lines-tracing algorithm was applied. This was attributed to the unbiased decision criteria of the measuring method. A greater length of the stalk is to be expected in the main stalk than when the length of a twisted or branched stalk is measured from the edge length of a rectangular box that encloses it.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • Albrecht, C. (2003). Konstruktion einer Vorrichtung zur Beschickung von Siebmaschinen (Construction of a device for feeding screening machines). Institute of Agricultural Engineering, University of Hohenheim. Stuttgart. Germany.

  • Benthien, J.T., Bähnisch, C., Heldner, S., Ohlmeyer, M. (2014). Effect of fiber size distribution on medium-density fiberboard properties caused by varied steaming time and temperature of defibration process. Wood and Fiber Science 46(2), 175-185.

  • DIN ISO 9276-1:2004-09, Darstellung der Ergebnisse von Partikelgrößenanalysen - Teil 1: Grafische Darstellung (ISO 9276-1:1998) (Representation of results of particle size analysis - Part 1: Graphical representation (ISO 9276-1:1998))

  • Rechberger, C., Prankl, J., Obernberger, G., Handler, F., Prankl, H. (2012). “Automatisierte Bestimmung der Partikellängenverteilung von Grassilagen anhand bildanalytischer Methoden” (Automated particle length distribution analysis of processed forage by means of image analysis), in Proceedings of the 70. Internationale Tagung Landtechnik (70th International Conference Agricultural Engineering), 6.-7. November 2012, Karlsruhe, Germany.

  • Seppke, B., Bähnisch, C., Benthien, J.T., Heldner, S., Ohlmeyer, M. (2015). “A Concurrent Skeleton-based Approach for the Characterization of Wood Fibers with Sub-pixel Precision for Fiber Board Production”, in Proceedings of the 10th International Conference on Mass Data Analysis of Images and Signals (MDA), 11.-14. July 2015, Hamburg, Germany.

  • Voßhenrich, H.H. (2000). Beim Häckseln liegt noch vieles im Argen (Still much trouble when cop-ping). Top Agrar 7/2000, 68-70.


Journal + Issues