Modelling postharvest quality of blueberry affected by biological variability using image and spectral data

Abstract

The above results indicated the potential for using spatial and spectral techniques to develop robust models for predicting blueberry postharvest quality containing biological variability. © 2015 Society of Chemical Industry.

Uses of selection strategies in both spectral and sample spaces for classifying hard and soft blueberry using near infrared data

“…One is that the developed models do not take biological variations such as seasonal and cultivar variations into account. In our previous publications, we had found that the obtained prediction models would be more robust with biological variations introduced 17 . Zhang et al ., also elaborated influences of physical and biological variability on inspection accuracy of the final model 18 .…”

Recent Developments in Methods and Techniques for Rapid Monitoring of Sugar Metabolism in Fruits

“…In the last decade, hyperspectral imaging has found a wide range of applications in the food industry (Barbin and others ; Elmasry and others ; Elmasry and others ; Feng and Sun ; Kamruzzaman and others ; Barbin and others 2013; Feng and Sun ; Feng and others ; Kamruzzaman and others ; Wu and Sun ; Wu and Sun ; Liu and others ). The hyperspectral images acquired under different wavelength dispersion devices, such as at visible/NIR bands (400 to 1100 nm) and NIR bands (1000 to 2500 nm) were also both proved available for sugar analysis and assessment in fruits (Lorente and others ; Wei and others ; Hu and others ; Pu and others ). HSI, one of the noninvasive and reagent‐free spectral imaging techniques, provides a more continuous spectral measurement across the region of interest and visualizes the spatial distribution of different components in samples with very high spectral resolution (Wu and Sun ).…”

“…Nogales‐Bueno and others () exploited the correlation between sugar concentration and hyperspectral reflectance images (900 to 1700 nm) of grapes during ripening, based on the modified PLSR, and they obtained a global model of red and white intact grape samples with an R value of 0.99. Also, Hu and others () built the least squares support vector machine regression models of blueberry postharvest quality based on hyperspectral images obtained at wavelengths ranging from 410 to 1113 nm in reflectance mode (890 spectra) and from 690 to 1050 nm in transmittance mode (449 spectra), and they investigated effects of cultivar and seasonal variability on its spectral variations. The results indicated that the performance of a 3‐cultivar NIR model for SSC prediction was better than the 2‐cultivar model.…”

Effects of power ultrasound treatment on the shelf life of button mushrooms: Digital image processing and microbial counting can reveal the effects

“…To address this limitation, digital image processing can be a promising approach to accurately quantify the effects of postharvest improvement methods and treatments on its appearance and marketability. Currently, in some researches, digital image processing has been used to assess the storage quality of several agricultural products (Hu et al., 2016; Maniwara et al., 2014; Saeys et al., 2019). Therefore, this study aims to measure both color properties and microbial content of button mushrooms during 12 day storage at 4°C under power ultrasonics treatment and its interaction with other treatments to provide an efficient treatment for increasing the storage quality of this product.…”