TY - JOUR
T1 - Glare based apple sorting and iterative algorithm for bruise region detection using shortwave infrared hyperspectral imaging
AU - Keresztes, Janos C.
AU - Diels, Elien
AU - Goodarzi, Mohammad
AU - Nguyen-Do-Trong, Nghia
AU - Goos, Peter
AU - Nicolai, Bart
AU - Saeys, Wouter
PY - 2017/8/1
Y1 - 2017/8/1
N2 - Bruises in apples is one of the most important quality factors during postharvest, which needs to be detected early and efficiently during sorting processes. In this study, a step-wise pixel based apple bruise detection system based on line scan hyperspectral imaging (HSI) in the shortwave infrared (SWIR) is demonstrated for three apple cultivars: ‘Jonagold’, ‘Kanzi’ and ‘Joly Red’. The SWIR HSI system performance was tested on apples from the different cultivars bruised at five different impact levels, and monitored from 1 to 36 h after bruising. While glare regions are commonly considered as anomalies and discarded from further analysis, their spectral signatures enabled in this work to distinguish between cultivars with a prediction accuracy up to 96%. Different partial least squares-discriminant analysis (PLS-DA) models were trained to discriminate cultivars and then to discriminate between sound, bruised, glossy and stem regions. Spectral area normalization pre-processing was found to be the most effective for pixel based bruise prediction, resulting in a prediction accuracy up to 90.1%. Post-processing of the binary images by exploiting spatial information further improved the bruise detection accuracy to 94.4%.
AB - Bruises in apples is one of the most important quality factors during postharvest, which needs to be detected early and efficiently during sorting processes. In this study, a step-wise pixel based apple bruise detection system based on line scan hyperspectral imaging (HSI) in the shortwave infrared (SWIR) is demonstrated for three apple cultivars: ‘Jonagold’, ‘Kanzi’ and ‘Joly Red’. The SWIR HSI system performance was tested on apples from the different cultivars bruised at five different impact levels, and monitored from 1 to 36 h after bruising. While glare regions are commonly considered as anomalies and discarded from further analysis, their spectral signatures enabled in this work to distinguish between cultivars with a prediction accuracy up to 96%. Different partial least squares-discriminant analysis (PLS-DA) models were trained to discriminate cultivars and then to discriminate between sound, bruised, glossy and stem regions. Spectral area normalization pre-processing was found to be the most effective for pixel based bruise prediction, resulting in a prediction accuracy up to 90.1%. Post-processing of the binary images by exploiting spatial information further improved the bruise detection accuracy to 94.4%.
KW - Apple bruise detection
KW - Fruit sorting
KW - Glare
KW - Joly Red
KW - Jonagold
KW - Kanzi
KW - Specular reflection
KW - SWIR hyperspectral imaging
UR - http://www.scopus.com/inward/record.url?scp=85018404754&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85018404754&partnerID=8YFLogxK
U2 - 10.1016/j.postharvbio.2017.04.005
DO - 10.1016/j.postharvbio.2017.04.005
M3 - Article
AN - SCOPUS:85018404754
SN - 0925-5214
VL - 130
SP - 103
EP - 115
JO - Postharvest Biology and Technology
JF - Postharvest Biology and Technology
ER -