Hyperspectral Imaging and Their Applications in the Nondestructive Quality Assessment of Fruits and Vegetables

Li, Xiaona; Li, Ruolan; Wang, Mengyu; Liu, Yaru; Zhang, Baohua; Zhou, Jun

doi:10.5772/intechopen.72250

Cited by 29 publications

(13 citation statements)

References 126 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Quantitative image analysis software also eases multispectral imaging use. For instance, principal component analysis (PCA) reduces dimensionality of multiple images to make fewer images in which high variability spots are highlighted [12] . A pioneer paper on this topic unlocked the potential use of PCA for multispectral imaging to reveal hidden underdrawings and quantify pigment mixtures in antique art works [4] .…”

Section: Hardware In Contextmentioning

confidence: 99%

MEDUSA: An open-source and webcam based multispectral imaging system

Pineda

Pérez

Gaviria³

et al. 2022

HardwareX

View full text Add to dashboard Cite

Section: Hardware In Contextmentioning

confidence: 99%

MEDUSA: An open-source and webcam based multispectral imaging system

Pineda

Pérez

Gaviria³

et al. 2022

HardwareX

View full text Add to dashboard Cite

“…The use of computer vision with deep learning methods allows the early and correct identification of the evaluated stress-causing agent [14]. Hyperspectral [14][15][16][17][18][19][20][21] and multispectral images [22][23][24][25][26][27][28] are increasingly important in rapid and non-destructive testing for diagnosing plant diseases.…”

Section: Introductionmentioning

confidence: 99%

Non-Invasive Monitoring of the Thermal and Morphometric Characteristics of Lettuce Grown in an Aeroponic System through Multispectral Image System

et al. 2022

View full text Add to dashboard Cite

Aeroponics is a soilless cultivation technology integrating plant nutrition, physiology, ecological environment, agricultural automation and horticulture. One of the soilless advantages is that a non-invasive observation of the root system growth development is possible. This paper presents a vegetative growth evaluation of lettuce plants in an aeroponic chamber, where root and leaf development parameters were measured in three lettuce crops through plant images captured in the visible (VIS), near infrared (NIR) and far infrared (IR) spectra. A total of ninety lettuce plants was transplanted for this research, thirty for each experimental crop. The three lettuce crops were grown for thirty days in an aeroponic growth plant chamber inside a greenhouse under favorable conditions. The morphometric and thermal parameters of the lettuce roots (perimeter, area, length and average temperature) and leaves (perimeter, area and average temperature) were evaluated for each crop along ten image-capturing sessions through an implemented multispectral vision system. The average values of the root and leaf morphometric parameters obtained with the implemented imaging system along the lettuce growing period were statistically analyzed with Tukey testing. The obtained analysis results show no significant difference for a value of p ≤ 0.05 in 86.67%. Hence, the morphometric parameters can be used to characterize the vegetative lettuce growth in aeroponic crops. On the other hand, a correlation analysis was conducted between the thermal parameters computed with the root and leaf thermal image processing and the measured ambient temperature. The results were: R = 0.945 for correlation between ambient and leaf temperature, R = 0.963 for correlation between ambient and root temperature and R = 0.977 for leaf and root temperature. According to these results, the plant temperature is highly correlated with the ambient temperature in an aeroponic crop. The obtained study results suggest that multispectral image processing is a useful non-invasive tool to estimate the vegetative root and leaf growth parameters of aeroponic lettuce plants in a greenhouse.

show abstract

“…Hyperspectral imaging (see Figure 3) is an emerging technology that integrates conventional imaging and spectroscopy to simultaneously collect spatial and spectral information from the surface of an object. [37][38][39] The images obtained from hyperspectral imaging sensor are referred to as data cubes since they are composed of spatially arranged pixels in a two-dimensional space and a set of spectral reflectance intensities (for each pixel) in the third dimension. In comparison with conventional photos, which have a few spectral broadbands, for example, RGB and multispectral image (MSI), the hyperspectral images have several hundreds of narrow spectral bands of the same scene.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral imaging for the elimination of visual ambiguity in corrosion detection and identification of corrosion sources

Lavadiya

Sajid

Yellavajjala

et al. 2021

Structural Health Monitoring

View full text Add to dashboard Cite

The similarity in the hue of corroded surfaces and coated surfaces, dust, vegetation, etc. leads to visual ambiguity which is challenging to eliminate using existing image classification/segmentation techniques. Furthermore, existing methods lack the ability to identify the source of corrosion, which plays a vital role in framing the corrosion mitigation strategies. The goal of this study to employ hyperspectral imaging (1) to detect corroded surfaces under visually ambiguous scenarios and (2) identify the source of corrosion in such scenarios. To this end, three different corrosive media, namely, (1) 1M hydrochloric acid (HCl), 2) 3.5 wt.% sodium chloride solution (NaCl), and (3) 3 wt.% sodium sulfate solution (Na2SO4), are employed to generate chemically distinctive corroded surfaces. The hyperspectral imaging sensor is employed to obtain the visible and near infrared (VNIR) spectra (397 nm–1004 nm) reflected by the corroded/coated surfaces. The intensity of the reflectance in various spectral bands are considered as the descriptive features in this study, and the training and test datasets were generated consisting of 35,000 and 15,000 data points, respectively. SVM classifier is trained and then its efficacy on the test data is assessed. Furthermore, validation datasets are employed and the generalization ability of the trained SVM classifier is verified. The results from this study revealed that the SVM classifier achieved an overall accuracy of 94% with the misclassifications of 18% and 13% in the case of NaCl and Na2SO4 corrosion, respectively. Reflectance spectra obtained in the VNIR region was found to eliminate the visual ambiguity between the corroded and coated surfaces and, identify the source of corrosion accurately. Further, the range of key wavelengths of the spectra that play an important role in the distinguishability of coating and chemically distinctive corroded surface were identified to be 500–520 nm, 660–680 nm, 760–770 nm, and 830–850 nm.

show abstract

Hyperspectral Imaging and Their Applications in the Nondestructive Quality Assessment of Fruits and Vegetables

Cited by 29 publications

References 126 publications

MEDUSA: An open-source and webcam based multispectral imaging system

MEDUSA: An open-source and webcam based multispectral imaging system

Non-Invasive Monitoring of the Thermal and Morphometric Characteristics of Lettuce Grown in an Aeroponic System through Multispectral Image System

Hyperspectral imaging for the elimination of visual ambiguity in corrosion detection and identification of corrosion sources

Contact Info

Product

Resources

About