Identification of Apple Varieties Using a Multichannel Hyperspectral Imaging System

Abstract

This paper reports the nondestructive detection of apple varieties using a multichannel hyperspectral imaging system consisting of an illumination fiber and 30 detection fibers arranged at source–detector distances of 1.5–36 mm over the spectral range of 550–1650 nm. Spatially resolved (SR) spectra were obtained for 1500 apples, 500 each of three varieties from the same orchard to avoid environmental and geographical influences. Partial least squares discriminant analysis (PLSDA) models were developed for single SR spectra and spectral combinations to compare their performance of variety detection. To evaluate the effect of spectral range on variety detection, three types of spectra (i.e., visible region: 550–780 nm, near-infrared region: 780–1650 nm, full region: 550–1650 nm) were analyzed and compared. The results showed that the single SR spectra presented a different accuracy for apple variety classification, and the optimal SR spectra varied with spectral types. Spectral combinations had better accuracies for variety detection with best overall classifications of 99.4% for both spectral ranges in the NIR and full regions; however, the spectral combination could not improve the results over the optimal single SR spectra in the visible region. Moreover, the recognition of golden delicious (GD) was better than those of the other two varieties, with the best classification accuracy of 100% for three types of spectra. Overall, the multichannel hyperspectral imaging system provides more spatial-spectral information for the apples, and the results demonstrate that the technique gave excellent classifications, which suggests that the multichannel hyperspectral imaging system has potential for apple variety detection.

Measurement of Early Disease Blueberries Based on Vis/NIR Hyperspectral Imaging System

“…Figure 5 illustrates the mean relative spectra for healthy and early disease blueberries of three spectral preprocessing methods over the spectral range of 400-1000 nm. There were two noticeable absorption peaks for the mean spectra of both healthy and early disease blueberries at around 680 nm, due to chlorophyll, and 970 nm, due to water or O-H functional groups [24,25]. There were no significant differences in the spectral range of 400-685 nm between healthy and early disease fruit, which could be due to the dark color of blueberries, resulting in difficult-to-observe pigment changes.…”

“…Hyperspectral imaging, which combines imaging and spectral information to detect external or internal quality attributes, is a promising detection method [20][21][22]. Furthermore, spectral signatures can be used to uniquely characterize, identify and quantify the chemical composition of agricultural products [23][24][25][26], which has advantages in the detection of some early defects that are invisible to the naked eye. In the last decade, numerous studies have been reported on the detection of diseases in fruit using hyperspectral imaging.…”

Assessment of Tomato Maturity in Different Layers by Spatially Resolved Spectroscopy

“…Whereas the dark reference spectra were acquired by closing the light source in a dark room. The relative spatially resolved spectra for the samples were calculated using the white, the dark and the original sample spectra [ 27 ]. The relative reflectance spectra were used in further data analysis.…”

Identification of Geographical Origin of Chinese Chestnuts Using Hyperspectral Imaging with 1D-CNN Algorithm

“…Therefore, HSI has a more comprehensive interpretation for the whole sample, which is conducive in discriminating different geographical origins of agricultural products. In this context, HSI has been widely adopted in the field of agricultural products, including fruits [23], cereals [24][25][26], meats [27], vegetables [28], and seafoods [29]. Additionally, the HSI technique was also often used to screen discolored [30,31], immature [32,33], moldy [34], and insect damage samples [35].…”