M. Garbez^1,2, É. Belin³, Y. Chéné³, N. Donès⁴, G. Hunault⁵, D. Relion¹, M. Sigogne¹, R. Symoneaux⁶, D. Rousseau⁷ and G. Galopin^1
1 IRHS, INRAE, Institut Agro, Université d’Angers, SFR 4207 QuaSaV, 49071, Beaucouzé, France
² Pépinières Desmartis, Bergerac, France
³ Université d’Angers, Laboratoire Angevin de Recherche en Ingénierie des Systèmes (LARIS), Angers, France
⁴ PIAF, INRAE, UCA, Clermont-Ferrand, France
⁵ Université d’Angers, Laboratoire Hémodynamique, Interaction, Fibrose, et Invasivité Tumorale Hépatique (HIFIH), Angers, France
⁶ Unité de Recherche GRAPPE, Université Bretagne Loire, Ecole Supérieure d’Agricultures (ESA), INRA, Angers, France
⁷ Université de Lyon, Centre de Recherche en Acquisition et Traitement de l’Image pour la Santé (CREATIS), Villeurbanne, France

SUMMARY Sensory methods applied to ornamental plants enable studying more objectively plant visual quality key drivers of consumer preferences. However, management upkeep of a trained panel for sensory profile is time-consuming, not flexible and represents non-negligible costs. The present paper achieves the proof of the concept about using morphometrical descriptors integrating 2D image features from rotating virtual rose bush videos to predict their visual appearance according to different sensory attributes. Using real plants cultivated under a shading gradient and imaged in rotation during three development stages, acceptable prediction error of the sensory attributes ranging from 6.2 to 19.8% (normalized RMSEP) were obtained with simple ordinary least squares (OLS) regression models and linearization. The most accurate model obtained was for the flower quantity perception. Finally, a secondary analysis highlighted in most of the studied traits a significant influence of defoliation, stressing therefore the impact of the leaves on plant architecture, and thus on the visual appearance. Keywords image analysis, linear regression, Rosa hybrida,sensory profile, video, woody ornamental plant

Significance of this study What is already known on this subject? Visual quality of ornamental plants is a key parameter playing a major role in the purchase triggering for consumers. Visual quality can be assessed by a panel of consumers from 2D views by considering homogeneous plants in their rotation. What are the new findings? Use of morphometric descriptors evaluated in 3D by rotation on video by image analysis to predict sensory attribute scores for ornamental plants. This method, developed from virtual roses (Garbez et al., 2016), is validated for real plants with high phenotypic variability. What is the expected impact on horticulture? Within ornamental horticulture context, visual quality of plants is an important criterion for customers. The realization of a sensory evaluation of the aesthetic value is important. Its prediction by morphometric attributes allows it to be automatized and generalized easily and quickly. It’s future tool to help innovation in ornamental horticulture.

E-mail: gilles.galopin@agrocampus-ouest.fr  

References

• Barthélémy, D., and Caraglio, Y. (2007). Plant architecture: A dynamic, multilevel and comprehensive approach to plant form, structure and ontogeny. Ann. Bot. 99(3), 375–407. https://doi.org/10.1093/aob/mcl260.

• Boumaza, R., Demotes-Mainard, S., Huché-Thélier, L., and Guérin, V. (2009). Visual characterization of the esthetic quality of the rosebush. J. Sensory Studies 24(5), 774–796. https://doi.org/10.1111/j.1745-459X.2009.00238.x.

• Boumaza, R., Huché-Thélier, L., Demotes-Mainard, S., Le Coz, E.L., Leduc, N., Pelleschi-Travier, S., Qannari, E.M., and Guérin, V. (2010). Sensory profiles and preference analysis in ornamental horticulture: The case of the rosebush. Food Qual. and Pref. 21(8), 987–997. https://doi.org/10.1016/j.foodqual.2010.05.003.

• Chéné, Y., Rousseau, D., Belin, É., Garbez, M., Galopin, G., and Chapeau-Blondeau, F. (2016). Shape descriptors to characterize the shoot of entire plant from multiple side views of a motorized depth sensor. Machine Vision and Applic. 27(4), 447–461. https://doi.org/10.1007/s00138-016-0762-x.

• Demotes-Mainard, S., Bertheloot, J., Boumaza, R., Huché-Thélier, L., Guéritaine, G., Guérin, V., and Andrieu, B. (2013). Rose bush leaf and internode expansion dynamics: Analysis and development of a model capturing interplant variability. Front. Plant Sci. 4(418). https://doi.org/10.3389/fpls.2013.00418.

• Gao, M., Van der Heijden, G., Vos, J., Eveleens, B.A., and Marcelis, L.F.M. (2012). Estimation of leaf area for large scale phenotyping and modeling of rose genotypes. Sci. Hortic. 138, 227–234. https://doi.org/10.1016/j.scienta.2012.02.014.

• Garbez, M., Galopin, G., Sigogne, M., Favre, P., Demotes-Mainard, S., and Symoneaux, R. (2015). Assessing the visual aspect of rotating virtual rose bushes by a labeled sorting task. Food Qual. and Pref. 40, 287–295. https://doi.org/10.1016/j.foodqual.2014.06.008.

• Garbez, M., Chéné, Y., Belin, É., Sigogne, M., Labatte, J.M., Hunault, G., and Galopin, G. (2016). Predicting sensorial attribute scores of ornamental plants assessed in 3D through rotation on video by image analysis: A study on the morphology of virtual rose bushes. Comp. and Electr. in Agricult. 121, 331–346. https://doi.org/10.1016/j.compag.2016.01.001.

• Garbez, M., Symoneaux, R., Belin, É., Caraglio, Y., Chéné, Y., Donès, N., Durant, J.B., Hunault, G., Relion, D., Sigogne, M., Rousseau, D., and Galopin, G. (2018). Ornamental plants architectural characteristics in relation to visual sensory attributes: A new approach on the rose bush for objective evaluation of the visual quality. Eur. J. Hortic. Sci. 83(3), 187–201. https://doi.org/10.17660/eJHS.2018/83.3.8.

• Godin, C. (2000). Representing and encoding plant architecture: A review. Ann. of Forest Sci. 57(5), 413–438. https://doi.org/10.1051/forest:2000132.

• Gongal, A., Amatya, S., Karkee, M., Zhang, Q., and Lewis, K. (2015). Sensors and systems for fruit detection and localization: A review. Comp. and Electr. in Agricult. 116, 8–19. https://doi.org/10.1016/j.compag.2015.05.021.

• Harmsen, S.R., and Koenderink, N.J.J.P. (2009). Multi-target tracking for flower counting using adaptive motion models. Comp. and Electr. in Agricult. 65(1), 7–18. https://doi.org/10.1016/j.compag.2008.07.004.

• Horgan, G.W. (2001). The statistical analysis of plant part appearance – A review. Comp. and Electr. in Agricult. 31(2), 169–190. https://doi.org/10.1016/S0168-1699(00)00190-3.

• Huché-Thélier, L., Boumaza, R., Demotes-Mainard, S., Canet, A., Symoneaux, R., Douillet, O., and Guérin, V. (2011). Nitrogen deficiency increases basal branching and modifies visual quality of the rose bushes. Sci. Hortic. 130(1), 325–334. https://doi.org/10.1016/j.scienta.2011.07.007.

• Kawabata, S., Yokoo, M., and Nii, K. (2009). Quantitative analysis of corolla shapes and petal contours in single-flower cultivars of lisianthus. Sci. Hortic. 121(2), 206–212. https://doi.org/10.1016/j.scienta.2009.01.024.

• Kohsel, L. (2001). New unsupervised approach for solving classification problems with computer vision. Acta Hortic. 562, 361–375. https://doi.org/10.17660/ActaHortic.2001.562.43.

• Kohsel, L., and Bennedsen, B.S. (2001). Performance of human experts grading pot roses in a commercial environment. Acta Hortic. 562, 273–283. https://doi.org/10.17660/ActaHortic.2001.562.32.

• Kuhn, M. (2008). Building predictive models in R using the caret package. J. Statistical Softw. 28(5). https://doi.org/10.18637/jss.v028.i05.

• Kuhn, M. (2016). caret: Classification and Regression Training (Version 6.0-68). http://cran.r-project.org/package=caret.

• Kuhn, M., and Johnson, K. (2013). Applied Predictive Modeling (New York, USA: Springer). https://doi.org/10.1007/978-1-4614-6849-3.

• Li-Marchetti, C., Le Bras, C., Relion, D., Citerne, S., Huché-Thélier, L., Sakr, S., and Crespel, L. (2015). Genotypic differences in architectural and physiological responses to water restriction in Rose bush. Front. Plant Sci. 6(355). https://doi.org/10.3389/fpls.2015.00355.

• Meilgaard, M.C., Carr, B.T., and Civille, G.V. (2006). Sensory Evaluation Techniques, 4^th edn. (Boca Raton: CRC Press). https://doi.org/10.1201/b16452.

• Moreda, G.P., Muñoz, M.A., Ruiz-Altisent, M., and Perdigones, A. (2012). Shape determination of horticultural produce using two-dimensional computer vision – A review. J. Food Engin. 108(2), 245–261. https://doi.org/10.1016/j.jfoodeng.2011.08.011.

• Næs, T., Brockhoff, P., and Tomic, O. (2011). Statistics for Sensory and Consumer Science (Chichester: John Wiley & Sons). https://doi.org/10.1002/9780470669181.

• Nœs, T., and Kowalski, B. (1989). Predicting sensory profiles from external instrumental measurements. Food Qual. and Pref. 1(4–5), 135–147. https://doi.org/10.1016/0950-3293(89)90001-3.

• Otsu, N. (1979). A threshold selection method from gray level histogram. IEEE Transactions on Systems, Man and Cybernetics 9, 62–66. https://doi.org/10.1109/TSMC.1979.4310076.

• R Development Core Team. (2015). R: A language and environment for statistical computing (V. 3.2.3). (Vienna, Austria: R Foundation for Statistical Computing). http://www.R-project.org/.

• Rousseau, D., Chéné, Y., Belin, E., Semaan, G., Trigui, G., Boudehri, K., and Chapeau-Blondeau, F. (2015). Multiscale imaging of plants: current approaches and challenges. Plant Methods 11(1), 6. https://doi.org/10.1186/s13007-015-0050-1.

• Ruiz-Altisent, M., Ruiz-Garcia, L., Moreda, G.P., Lu, R., Hernandez-Sanchez, N., Correa, E.C., and García-Ramos, J. (2010). Sensors for product characterization and quality of specialty crops. Comp. and Electr. in Agricult. 74(2), 176–194. https://doi.org/10.1016/j.compag.2010.07.002.

• Santagostini, P., Demotes-Mainard, S., Huché-Thélier, L., Leduc, N., Bertheloot, J., Guérin, V., and Boumaza, R. (2014). Assessment of the visual quality of ornamental plants: Comparison of three methodologies in the case of the rosebush. Sci. Hortic. 168, 17–26. https://doi.org/10.1016/j.scienta.2014.01.011.

• Silva, L., Koga, M.L., Cugnasca, C.E., and Costa, A.H.R. (2013). Comparative assessment of feature selection and classification techniques for visual inspection of pot plant seedlings. Comp. and Electr. in Agricult. 97, 47–55. https://doi.org/10.1016/j.compag.2013.07.001.

• Yeo, I.K., and Johnson, R.A. (2000). A new family of power transformations to improve normality or symmetry. Biometrika 87(4), 954–959. https://doi.org/10.1093/biomet/87.4.954.

Received: 25 January 2019 | Accepted: 22 July 2019 | Published: 22 June 2020 | Available online: 22 June 2020