Detection of Age and Defect of Grapevine Leaves Using Hyper Spectral Imaging

This paper demonstrates the potential of using hyperspectral imaging for detecting age and defects of grapevine leaves. For age detection studies a number of grapevine healthy leaves and for defect detection analysis 9 different defective leaves have been selected. Hyperspectral images of these leaves covered spectral wavelengths from 380 nm to 1000 nm. A number of features from the brightness in ultra violet (UV), visible (VIS) and near infrared (NIR) regions were derived to obtain the correlation of age and defect. From the experimental studies it has been observed that the mean brightness in terms of original reflection in visible range has correlation with different ages of grapevine leaves. Moreover, the position of mean 1st derivative brightness peak in VIS region, variation index of brightness and rate of change of brightness i.e., mean 1st derivative brightness at NIR provide a good indication about the age of the leaves. For defect detection whole area and selective areas containing the defects on the leaves have been experimentally analysed to determine which option provides better defect detection. Variation index of brightness was also employed as a guide to obtain information to distinguish healthy and unhealthy leaves using hyperspectral imaging. The experimental results demonstrated that hyperspectral imaging has excellent potential as a non-destructive as well as a non-contact method to detect age and defects of grapevine leaves.

[1]  K. Razi Naqvi,et al.  Does a leaf absorb radiation in the near infrared (780–900 nm) region? A new approach to quantifying optical reflection, absorption and transmission of leaves , 2004, Photosynthesis Research.

[2]  Laurie A. Chisholm,et al.  Effects of leaf age and psyllid damage on the spectral reflectance properties of Eucalyptus saligna foliage , 2005 .

[3]  Georgios LiakopoulosDimosthenis NikolopoulosGeorge Karabourniotis,et al.  The First Step from Light to Wine: Photosynthetic Performance and Photoprotection of Grapevine (Vitis vinifera L.) Leaves , 2007 .

[4]  Takeshi Inoue,et al.  Green light drives leaf photosynthesis more efficiently than red light in strong white light: revisiting the enigmatic question of why leaves are green. , 2009, Plant & cell physiology.

[5]  Renfu Lu,et al.  Original paper: Hyperspectral waveband selection for internal defect detection of pickling cucumbers and whole pickles , 2010 .

[6]  K. Hufkens,et al.  Seasonal patterns of foliar reflectance in relation to photosynthetic capacity and color index in two co-occurring tree species, Quercus rubra and Betula papyrifera , 2012 .

[7]  D. Greer,et al.  Modelling photosynthetic responses to temperature of grapevine (Vitis vinifera cv. Semillon) leaves on vines grown in a hot climate. , 2012, Plant, cell & environment.

[8]  Mathilde Knoll,et al.  Gas exchange of field-grown "Vitis vinifera" L. cv. Zweigelt leaves in relation to leaf age and position along the stem , 2012 .

[9]  V. K. Gupta,et al.  Spectral reflectance pattern in soybean for assessing yellow mosaic disease , 2013, Indian Journal of Virology.

[10]  Cristina E. Davis,et al.  Advanced methods of plant disease detection. A review , 2014, Agronomy for Sustainable Development.

[11]  Wang Jihua,et al.  Detection of Internal Leaf Structure Deterioration Using a New Spectral Ratio Index in the Near-Infrared Shoulder Region , 2014 .

[12]  Benoit Jaillais,et al.  Detection of Fusarium head blight contamination in wheat kernels by multivariate imaging , 2015 .

[13]  Jagadeesh Pujari,et al.  Image Processing Based Detection of Fungal Diseases in Plants , 2015 .

[14]  Jayme Garcia Arnal Barbedo,et al.  Detecting Fusarium head blight in wheat kernels using hyperspectral imaging , 2015 .

[15]  Yong He,et al.  Detection of early blight and late blight diseases on tomato leaves using hyperspectral imaging , 2015, Scientific Reports.

[16]  M. Lagorio,et al.  Reviewing the relevance of fluorescence in biological systems , 2015, Photochemical & photobiological sciences : Official journal of the European Photochemistry Association and the European Society for Photobiology.

[17]  M. Kishore,et al.  Hyperspectral imaging technique for plant leaf identification , 2015, 2015 International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT).

[18]  H. A. Hingoliwala,et al.  Smart Farming: Pomegranate Disease Detection Using Image Processing , 2015 .

[19]  Anne-Katrin Mahlein.  Plant Disease Detection by Imaging Sensors - Parallels and Specific Demands for Precision Agriculture and Plant Phenotyping. , 2016, Plant disease.

[20]  Manisha Sharma,et al.  Image Processing Based Leaf Rot Disease, Detection of Betel Vine (Piper BetleL.) , 2016 .

[21]  C. Clément,et al.  Leaf vs. inflorescence: differences in photosynthetic activity of grapevine , 2017, Photosynthetica.

[22]  Anna Gambin,et al.  Leaf and Plant Age Affects Photosynthetic Performance and Photoprotective Capacity1 , 2017, Plant Physiology.

[23]  M. A. Jiménez-Bello,et al.  Water Versus Source–Sink Relationships in a Semiarid Tempranillo Vineyard: Vine Performance and Fruit Composition , 2017, American Journal of Enology and Viticulture.

[24]  Andrew P French,et al.  Hyperspectral image analysis techniques for the detection and classification of the early onset of plant disease and stress , 2017, Plant Methods.

[25]  Zuzana Lhotáková,et al.  The Effect of Leaf Stacking on Leaf Reflectance and Vegetation Indices Measured by Contact Probe during the Season , 2017, Sensors.

[26]  A. K. Misra,et al.  Detection of plant leaf diseases using image segmentation and soft computing techniques , 2017 .

[27]  Atsushi Kume,et al.  Importance of the green color, absorption gradient, and spectral absorption of chloroplasts for the radiative energy balance of leaves , 2017, Journal of Plant Research.

[28]  Reza Ehsani,et al.  Detection of multi-tomato leaf diseases (late blight, target and bacterial spots) in different stages by using a spectral-based sensor , 2018, Scientific Reports.

[29]  Jorge Ricardo Ducati,et al.  Detection of grapevine leaf stripe disease symptoms by hyperspectral sensor , 2018 .

[30]  Yang Tao,et al.  Early Detection of Tomato Spotted Wilt Virus by Hyperspectral Imaging and Outlier Removal Auxiliary Classifier Generative Adversarial Nets (OR-AC-GAN) , 2019, Scientific Reports.