Early detection of decay on apples using hyperspectral reflectance imaging combining both principal component analysis and improved watershed segmentation method

Li, Jiangbo; Luo, Wei; Wang, Zheli; Fan, Shuxiang

doi:10.1016/j.postharvbio.2018.12.007

Cited by 96 publications

(44 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notwithstanding the complexity of the data produced by visible and near-infrared (NIR) HSI technology, this technology has been recently combined with chemometrics in successful applications for disease detection in different fruits. Examples include apples [14,15], peaches [16], oranges [17,18], mandarins [19] and strawberries [20]. Likewise, the identification of grapevine diseases by spectral imaging techniques has been an object of study [21].…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Imaging to Assess the Presence of Powdery Mildew (Erysiphe necator) in cv. Carignan Noir Grapevine Bunches

et al. 2020

View full text Add to dashboard Cite

Powdery mildew is a worldwide major fungal disease for grapevine, which adversely affects both crop yield and produce quality. Disease identification is based on visible signs of a pathogen once the plant has already been infected; therefore, techniques that allow objective diagnosis of the disease are currently needed. In this study, the potential of hyperspectral imaging (HSI) technology to assess the presence of powdery mildew in grapevine bunches was evaluated. Thirty Carignan Noir grape bunches, 15 healthy and 15 infected, were analyzed using a lab-scale HSI system (900–1700 nm spectral range). Image processing was performed to extract spectral and spatial image features and then, classification models by means of Partial Least Squares Discriminant Analysis (PLS-DA) were carried out for healthy and infected pixels distinction within grape bunches. The best discrimination was achieved for the PLS-DA model with smoothing (SM), Standard Normal Variate (SNV) and mean centering (MC) pre-processing combination, reaching an accuracy of 85.33% in the cross-validation model and a satisfactory classification and spatial location of either healthy or infected pixels in the external validation. The obtained results suggested that HSI technology combined with chemometrics could be used for the detection of powdery mildew in black grapevine bunches.

show abstract

Section: Introductionmentioning

confidence: 99%

Hyperspectral Imaging to Assess the Presence of Powdery Mildew (Erysiphe necator) in cv. Carignan Noir Grapevine Bunches

et al. 2020

View full text Add to dashboard Cite

show abstract

“…From the calculation, the first four principal components (PCs), accounting for 82.35%, 13.83%, 2.5% and 0.6% of the total variance, respectively, were selected for further analysis, because more than 99.28% of variation was retained in first four PCs. Since each PC score is a linear combination by each spectral point multiplied by the corresponding loading, the wavelengths located at local maximal values (peaks) or minimal values (valleys) of the loadings curve have a more important contribution to the PC score [ 52 ]. Therefore, the loadings curves of the first four PCs, as shown in Figure 5 , were subjected to selecting the effective wavebands.…”

Section: Resultsmentioning

confidence: 99%

“…Traditionally, measurement of chlorophyll content based on chemical analysis, such as ultraviolet spectrophotometry and high performance liquid chromatography, involve labor-intensive, time-consuming and tedious extraction procedures. Recent studies have demonstrated the feasibility of retrieval of chlorophyll content from hyperspectral vegetation indices composed by the reflectance of specific bands [ 52 ]. But this technique provides spectrum information with low spatial resolution, which fails to provide the spectral details at each pixel on targets images.…”

Section: Discussionmentioning

confidence: 99%

Early Visual Detection of Wheat Stripe Rust Using Visible/Near-Infrared Hyperspectral Imaging

Yao

2019

Sensors

View full text Add to dashboard Cite

Wheat stripe rust is one of the most important and devastating diseases in wheat production. In order to detect wheat stripe rust at an early stage, a visual detection method based on hyperspectral imaging is proposed in this paper. Hyperspectral images of wheat leaves infected by stripe rust for 15 consecutive days were collected, and their corresponding chlorophyll content (SPAD value) were measured using a handheld SPAD-502 chlorophyll meter. The spectral reflectance of the samples were then extracted from the hyperspectral images, using image segmentation based on a leaf mask. The effective wavebands were selected by the loadings of principal component analysis (PCA-loadings) and the successive projections algorithm (SPA). Next, the regression model of the SPAD values in wheat leaves was established, based on the back propagation neural network (BPNN), using the full spectra and the selected effective wavelengths as inputs, respectively. The results showed that the PCA-loadings–BPNN model had the best performance, which modeling accuracy (RC2) and validation accuracy (RP2) were 0.921 and 0.918, respectively, and the RPD was 3.363. The number of effective wavelengths extracted by this model accounted for only 3.12% of the total number of wavelengths, thus simplifying the models and improving the rate of operation greatly. Finally, the optimal models were used to estimate the SPAD of each pixel within the wheat leaf images, to generate spatial distribution maps of chlorophyll content. The visualized distribution map showed that wheat leaves infected by stripe rust could be identified six days after inoculation, and at least three days before the appearance of visible symptoms, which provides a new method for the early detection of wheat stripe rust.

show abstract

“…The NIR technique associated with chemometrics (PLS algorithm) allowed us to elaborate predictive models for the conventional ripening parameters [45]. Particular mention has to be made in this paragraph to the use of hyperspectral imaging systems (HSI) and scanner cameras [5,8,60,67,81,109,112,126,129,143,144,148]. Hyperspectral imaging is a complex, highly multidisciplinary field that can be defined as the simultaneous acquisition of spatial images in many spectrally contiguous bands.…”

Section: Process Control Authenticity and Classification Studiesmentioning

confidence: 99%

Review: NIR Spectroscopy as a Suitable Tool for the Investigation of the Horticultural Field

Cattaneo

Stellari

2019

Agronomy

View full text Add to dashboard Cite

The last 10 years of knowledge on near infrared (NIR) applications in the horticultural field are summarized. NIR spectroscopy is considered one of the most suitable technologies of investigation worldwide used as a nondestructive approach to monitoring raw materials and products in several fields. There are different types of approaches that can be employed for the study of key issues for horticultural products. In this paper, an update of the information collected from the main specific International Journals and Symposia was reported. Many papers showed the use of NIR spectroscopy in the horticultural field, and the literature data were grouped per year, per product, and per application, such as studies of direct (chemical composition) and indirect (physical and sensorial) properties (P), process control (PC), and authenticity and classification studies (AC). A mention was made of a recent innovative approach that considers the contribution of water absorption in the study of biological systems.

show abstract

Early detection of decay on apples using hyperspectral reflectance imaging combining both principal component analysis and improved watershed segmentation method

Cited by 96 publications

References 38 publications

Hyperspectral Imaging to Assess the Presence of Powdery Mildew (Erysiphe necator) in cv. Carignan Noir Grapevine Bunches

Hyperspectral Imaging to Assess the Presence of Powdery Mildew (Erysiphe necator) in cv. Carignan Noir Grapevine Bunches

Early Visual Detection of Wheat Stripe Rust Using Visible/Near-Infrared Hyperspectral Imaging

Review: NIR Spectroscopy as a Suitable Tool for the Investigation of the Horticultural Field

Contact Info

Product

Resources

About