Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images
Abstract Background Hyperspectral imaging is an emerging means of assessing plant vitality, stress parameters, nutrition status, and diseases. Extraction of target values from the high-dimensional datasets either relies on pixel-wise processing of the full spectral information, appropriate selection...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2017-06-01
|
| Series: | Plant Methods |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13007-017-0198-y |
| _version_ | 1818477038349058048 |
|---|---|
| author | Uwe Knauer Andrea Matros Tijana Petrovic Timothy Zanker Eileen S. Scott Udo Seiffert |
| author_facet | Uwe Knauer Andrea Matros Tijana Petrovic Timothy Zanker Eileen S. Scott Udo Seiffert |
| author_sort | Uwe Knauer |
| collection | DOAJ |
| description | Abstract Background Hyperspectral imaging is an emerging means of assessing plant vitality, stress parameters, nutrition status, and diseases. Extraction of target values from the high-dimensional datasets either relies on pixel-wise processing of the full spectral information, appropriate selection of individual bands, or calculation of spectral indices. Limitations of such approaches are reduced classification accuracy, reduced robustness due to spatial variation of the spectral information across the surface of the objects measured as well as a loss of information intrinsic to band selection and use of spectral indices. In this paper we present an improved spatial-spectral segmentation approach for the analysis of hyperspectral imaging data and its application for the prediction of powdery mildew infection levels (disease severity) of intact Chardonnay grape bunches shortly before veraison. Results Instead of calculating texture features (spatial features) for the huge number of spectral bands independently, dimensionality reduction by means of Linear Discriminant Analysis (LDA) was applied first to derive a few descriptive image bands. Subsequent classification was based on modified Random Forest classifiers and selective extraction of texture parameters from the integral image representation of the image bands generated. Dimensionality reduction, integral images, and the selective feature extraction led to improved classification accuracies of up to $$0.998\pm 0.003$$ 0.998 ± 0.003 for detached berries used as a reference sample (training dataset). Our approach was validated by predicting infection levels for a sample of 30 intact bunches. Classification accuracy improved with the number of decision trees of the Random Forest classifier. These results corresponded with qPCR results. An accuracy of 0.87 was achieved in classification of healthy, infected, and severely diseased bunches. However, discrimination between visually healthy and infected bunches proved to be challenging for a few samples, perhaps due to colonized berries or sparse mycelia hidden within the bunch or airborne conidia on the berries that were detected by qPCR. Conclusions An advanced approach to hyperspectral image classification based on combined spatial and spectral image features, potentially applicable to many available hyperspectral sensor technologies, has been developed and validated to improve the detection of powdery mildew infection levels of Chardonnay grape bunches. The spatial-spectral approach improved especially the detection of light infection levels compared with pixel-wise spectral data analysis. This approach is expected to improve the speed and accuracy of disease detection once the thresholds for fungal biomass detected by hyperspectral imaging are established; it can also facilitate monitoring in plant phenotyping of grapevine and additional crops. |
| first_indexed | 2024-12-10T09:32:56Z |
| format | Article |
| id | doaj.art-8ab72e8a09e048408942cd81d3968824 |
| institution | Directory Open Access Journal |
| issn | 1746-4811 |
| language | English |
| last_indexed | 2024-12-10T09:32:56Z |
| publishDate | 2017-06-01 |
| publisher | BMC |
| record_format | Article |
| series | Plant Methods |
| spelling | doaj.art-8ab72e8a09e048408942cd81d39688242022-12-22T01:54:17ZengBMCPlant Methods1746-48112017-06-0113111510.1186/s13007-017-0198-yImproved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral imagesUwe Knauer0Andrea Matros1Tijana Petrovic2Timothy Zanker3Eileen S. Scott4Udo Seiffert5Biosystems Engineering, Fraunhofer IFFLeibniz-Institute of Plant Genetics and Crop Plant Research (IPK)School of Agriculture, Food and Wine, The University of AdelaideSchool of Agriculture, Food and Wine, The University of AdelaideSchool of Agriculture, Food and Wine, The University of AdelaideBiosystems Engineering, Fraunhofer IFFAbstract Background Hyperspectral imaging is an emerging means of assessing plant vitality, stress parameters, nutrition status, and diseases. Extraction of target values from the high-dimensional datasets either relies on pixel-wise processing of the full spectral information, appropriate selection of individual bands, or calculation of spectral indices. Limitations of such approaches are reduced classification accuracy, reduced robustness due to spatial variation of the spectral information across the surface of the objects measured as well as a loss of information intrinsic to band selection and use of spectral indices. In this paper we present an improved spatial-spectral segmentation approach for the analysis of hyperspectral imaging data and its application for the prediction of powdery mildew infection levels (disease severity) of intact Chardonnay grape bunches shortly before veraison. Results Instead of calculating texture features (spatial features) for the huge number of spectral bands independently, dimensionality reduction by means of Linear Discriminant Analysis (LDA) was applied first to derive a few descriptive image bands. Subsequent classification was based on modified Random Forest classifiers and selective extraction of texture parameters from the integral image representation of the image bands generated. Dimensionality reduction, integral images, and the selective feature extraction led to improved classification accuracies of up to $$0.998\pm 0.003$$ 0.998 ± 0.003 for detached berries used as a reference sample (training dataset). Our approach was validated by predicting infection levels for a sample of 30 intact bunches. Classification accuracy improved with the number of decision trees of the Random Forest classifier. These results corresponded with qPCR results. An accuracy of 0.87 was achieved in classification of healthy, infected, and severely diseased bunches. However, discrimination between visually healthy and infected bunches proved to be challenging for a few samples, perhaps due to colonized berries or sparse mycelia hidden within the bunch or airborne conidia on the berries that were detected by qPCR. Conclusions An advanced approach to hyperspectral image classification based on combined spatial and spectral image features, potentially applicable to many available hyperspectral sensor technologies, has been developed and validated to improve the detection of powdery mildew infection levels of Chardonnay grape bunches. The spatial-spectral approach improved especially the detection of light infection levels compared with pixel-wise spectral data analysis. This approach is expected to improve the speed and accuracy of disease detection once the thresholds for fungal biomass detected by hyperspectral imaging are established; it can also facilitate monitoring in plant phenotyping of grapevine and additional crops.http://link.springer.com/article/10.1186/s13007-017-0198-yGrapevinePowdery mildewHyperspectralImage analysisInfection |
| spellingShingle | Uwe Knauer Andrea Matros Tijana Petrovic Timothy Zanker Eileen S. Scott Udo Seiffert Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images Plant Methods Grapevine Powdery mildew Hyperspectral Image analysis Infection |
| title | Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images |
| title_full | Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images |
| title_fullStr | Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images |
| title_full_unstemmed | Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images |
| title_short | Improved classification accuracy of powdery mildew infection levels of wine grapes by spatial-spectral analysis of hyperspectral images |
| title_sort | improved classification accuracy of powdery mildew infection levels of wine grapes by spatial spectral analysis of hyperspectral images |
| topic | Grapevine Powdery mildew Hyperspectral Image analysis Infection |
| url | http://link.springer.com/article/10.1186/s13007-017-0198-y |
| work_keys_str_mv | AT uweknauer improvedclassificationaccuracyofpowderymildewinfectionlevelsofwinegrapesbyspatialspectralanalysisofhyperspectralimages AT andreamatros improvedclassificationaccuracyofpowderymildewinfectionlevelsofwinegrapesbyspatialspectralanalysisofhyperspectralimages AT tijanapetrovic improvedclassificationaccuracyofpowderymildewinfectionlevelsofwinegrapesbyspatialspectralanalysisofhyperspectralimages AT timothyzanker improvedclassificationaccuracyofpowderymildewinfectionlevelsofwinegrapesbyspatialspectralanalysisofhyperspectralimages AT eileensscott improvedclassificationaccuracyofpowderymildewinfectionlevelsofwinegrapesbyspatialspectralanalysisofhyperspectralimages AT udoseiffert improvedclassificationaccuracyofpowderymildewinfectionlevelsofwinegrapesbyspatialspectralanalysisofhyperspectralimages |