Advertisement

American Journal of Potato Research

, Volume 94, Issue 1, pp 88–93 | Cite as

Potato Tuber Length-Width Ratio Assessment Using Image Analysis

  • Yongsheng Si
  • Sindhuja SankaranEmail author
  • N. Richard Knowles
  • Mark J. Pavek
Short Communication

Abstract

Potato tuber length to width (L/W) ratio is a critical crop trait evaluated during the development and selection of new cultivars to assess the effects of environment and management on tuber size and shape. The major challenges in manual measurement of L/W ratio are that it is labor-intensive, time consuming, and sometimes inconsistent. A high-throughput, digital image-based method for estimation of L/W ratio was developed in this study. Tests were conducted using tubers from a local retail market (red, white and russet) and from a field experiment with Payette Russet cultivar specifically designed to alter tuber size and shape. An image processing algorithm was developed to process the potato tuber images and the L/W ratio data from the images were compared to manual caliper measurements. A high accuracy in tuber L/W ratio estimation was consistently observed using image-based analysis. Among the different potato cultivars, red cultivars had a lower average accuracy in L/W ratio estimation of 94%, while other cultivars exhibited 96% and higher average accuracies.

Keywords

Machine vision Image processing Size analysis Phenotyping 

Resumen

La relación largo-ancho del tubérculo de la papa (L/W, por sus siglas en inglés), es un carácter crítico del cultivo que se evalúa durante el desarrollo y selección de nuevas variedades para analizar los efectos del ambiente y de manejo en el tamaño y forma del tubérculo. Los mayores retos en las mediciones manuales de la relación L/W son la mano de obra intensiva que se requiere, el tiempo que les lleva, y algunas veces las inconsistencias. En este estudio, se desarrolló un método integral, basado en imagen digital para la estimación de la relación L/W. Se condujeron pruebas usando tubérculos de un mercado de menudeo local (roja, blanca y tipo russet) y de un experimento de campo con la variedad Payette Russet diseñado específicamente para alterar el tamaño y la forma del tubérculo. Se desarrolló un algoritmo de procesamiento de imagen del tubérculo de papa, y los datos de la relación L/W de las imágenes se compararon con mediciones manuales de un calibrador (tipo vernier, nota del traductor). Mediante el uso de análisis basado en imágenes, se observó consistentemente una alta precisión en la estimación de la relación L/W del tubérculo. Entre las diferentes variedades de papa, las rojas tuvieron un promedio más bajo de precisión en la estimación de la relación L/W de 94%, mientras que otras variedades exhibieron promedio de precisiones de 96% y mayores.

Notes

Acknowledgments

The research was performed at Washington State University. This research was funded, in part, by the USDA National Institute of Food and Agriculture, Hatch Project, 1002864 (WNP00821) and by the program of study abroad for young teachers sponsored by the Agricultural University of Hebei.

References

  1. Barnes, M., T. Duckett, and G. Cielniak. 2009. Boosting minimalist classifiers for blemish detection in potatoes. In 24th International IEEE Conference on Image and Vision Computing, New Zealand, 397402.Google Scholar
  2. Bradeen, J.M., and C. Kole. 2011. Genetics, genomics and breeding of potato. CRC Press.Google Scholar
  3. Fajardo, D., K.G. Haynes, and S. Jansky. 2013. Starch characteristics of modern and heirloom potato cultivars. American Journal of Potato Research 90: 460–469.CrossRefGoogle Scholar
  4. Hassankhani, R., and H. Navid. 2012. Potato sorting based on size and color in machine vision system. Journal of Agricultural Science 4: 235–244.Google Scholar
  5. Hirsch, C. N., C. D. Hirsch, K. Felcher, J. Coombs, D. Zarka, A. Van Deynze, W. De Jong, R.E. Veilleux, S. Jansky, P. Bethke, D.S. Douches, and C.R. Buell. 2013. Retrospective view of North American potato (Solanum tuberosum L.) breeding in the 20th and 21st centuries. G3 3: 1003–1013. doi:10.1534/g3.113.005595.Google Scholar
  6. Kumar, T., and K. Verma. 2010. A theory based on conversion of RGB image to gray image. International Journal of Computer Applications 7: 7–10.CrossRefGoogle Scholar
  7. Lindqvist-Kreuze, H., A. Khan, E. Salas, S. Meiyalaghan, S. Thomson, R. Gomez, and M. Bonierbale. 2015. Tuber shape and eye depth variation in a diploid family of Andean potatoes. BMC Genetics 16: 1.CrossRefGoogle Scholar
  8. Meyer, F., and S. Beucher. 1990. Morphological segmentation. Journal of Visual Communication and Image Representation 1: 21–46.CrossRefGoogle Scholar
  9. National Potato Council. 2013. Potato Utilization, United States. 2011–2013. http://nationalpotatocouncil.org/files/9214/4223/8719/Pg._77_Potato_Utilization_US_2011-2013.pdf . Accessed 3 Jan 2016.
  10. Noordam, J. C., G.W. Otten, T.J. Timmermans, and B.H. van Zwol. 2000. High-speed potato grading and quality inspection based on a color vision system. In Machine vision applications in industrial inspection, 206–217. International Society for Optics and Photonics.Google Scholar
  11. Otsu, N. 1975. A threshold selection method from gray-level histograms. Automatica 11: 285–296.CrossRefGoogle Scholar
  12. Pavek, M.J., and N.R. Knowles. 2015. Potato cultivar yield and postharvest quality evaluations for 2015. Washington State University Special Report .http://potatoes.wsu.edu/wp-content/uploads/2016/01/Potato-Cultivar-Yield-and-Postharvest-Quality-Evaluations-Research-Edition-2015.pdf. Accessed 3 Jan 2016
  13. Pedreschi, F., D. Mery, and T. Marique. 2008. Grading of potatoes. In Computer vision technology for food quality evaluation, ed. Da-Wen Sun, 305–318, Elsevier.Google Scholar
  14. Tao, Y., C.T. Morrow, P.H. Heinemann, and H.J. Sommer. 1995. Fourier-based separation technique for shape grading of potatoes using machine vision. Transactions of the ASAE 38: 949–957.CrossRefGoogle Scholar
  15. Van Eck, H.J., J.M. Jacobs, P. Stam, J. Ton, W.J. Stiekema, and E. Jacobsen. 1994. Multiple alleles for tuber shape in diploid potato detected by qualitative and quantitative genetic analysis using RFLPs. Genetics 137: 303–309.PubMedPubMedCentralGoogle Scholar
  16. Zhou, L., V. Chalana, and Y. Kim. 1998. PC-based machine vision system for real-time computer-aided potato inspection. International Journal of Imaging Systems and Technology 9: 423–433.CrossRefGoogle Scholar

Copyright information

© The Potato Association of America 2016

Authors and Affiliations

  • Yongsheng Si
    • 1
    • 2
  • Sindhuja Sankaran
    • 2
    Email author
  • N. Richard Knowles
    • 3
  • Mark J. Pavek
    • 3
  1. 1.College of Information Science and TechnologyAgriculture University of HeBeiBaodingChina
  2. 2.Department of Biological Systems EngineeringWashington State UniversityPullmanUSA
  3. 3.Department of HorticultureWashington State UniversityPullmanUSA

Personalised recommendations