Nondestructive Detection and Quantification of Blueberry Bruising using Near-infrared (NIR) Hyperspectral Reflectance Imaging

Abstract

Currently, blueberry bruising is evaluated by either human visual/tactile inspection or firmness measurement instruments. These methods are destructive, time-consuming, and subjective. The goal of this paper was to develop a non-destructive approach for blueberry bruising detection and quantification. Experiments were conducted on 300 samples of southern highbush blueberry (Camellia, Rebel, and Star) and on 1500 samples of northern highbush blueberry (Bluecrop, Jersey, and Liberty) for hyperspectral imaging analysis, firmness measurement, and human evaluation. An algorithm was developed to automatically calculate a bruise ratio index (ratio of bruised to whole fruit area) for bruise quantification. The spectra of bruised and healthy tissues were statistically separated and the separation was independent of cultivars. Support vector machine (SVM) classification of the spectra from the regions of interest (ROIs) achieved over 94%, 92%, and 96% accuracy on the training set, independent testing set, and combined set, respectively. The statistical results showed that the bruise ratio index was equivalent to the measured firmness but better than the predicted firmness in regard to effectiveness of bruise quantification, and the bruise ratio index had a strong correlation with human assessment (R2 = 0.78 − 0.83). Therefore, the proposed approach and the bruise ratio index are effective to non-destructively detect and quantify blueberry bruising.

Breeding Trait Priorities of the Blueberry Industry in the United States and Canada

“…Breeders typically use this trait to select cultivars adapted to mechanical harvesting (Mehra et al, 2013;Moggia et al, 2017, Olmstead andFinn, 2014). Firmness has largely been evaluated subjectively by simply squeezing the fruit and objectively by using the compression force method (Jiang et al, 2016) and, as mentioned previously, has also been associated with consumer preference and extended shelf life. Despite the relevance of this trait in the blueberry production and distribution chain, it is still unclear which specific fruit texture characteristics-such as crispness, hardness, juiciness, and mealinessare most critical for overall firmness and extended shelf life, consumer preference, and resistance to bruising.…”

“…Despite the relevance of this trait in the blueberry production and distribution chain, it is still unclear which specific fruit texture characteristics-such as crispness, hardness, juiciness, and mealinessare most critical for overall firmness and extended shelf life, consumer preference, and resistance to bruising. Alternative highthroughput methods based on bioyield force (Blaker et al, 2014) and near-infrared hyperspectral reflectance imaging (Jiang et al, 2016) have been developed to evaluate fruit damage. Mechanical force methods such as the texture analyzer have been used to study fruit texture characteristics associated with extended shelf life, but this method has not been correlated with resistance to mechanical fruit damage (Giongo et al, 2013).…”

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

“…Software modifications focus on automatic image registration to fuse the top and bottom RBG images 34 . For hyperspectral imaging advanced unsupervised feature extraction approaches 28 as well as more sensitive supervised target detection methods such as SVMs 35 are tested. Thereby the hyperspectral data potentially allow for the assessment of multiple soil, rhizosphere and root properties 36 .…”

Seasonal dynamics of lingonberry and blueberry spectra

“…Moreover, distinct reflectance spectra of berries and flowers of lingonberry and blueberry species are not currently available. Possibly the closest resembling blue-colored shrub berries previously measured for spectral reflectance are different blueberry cultivars grown commercially in the United States (Leiva-Valenzuela et al 2012, 2013Jiang et al 2016).…”