Near-infrared hyperspectral reflectance imaging for detection of bruises on pickling cucumbers

By D. P. Ariana, Renfu Lu, Daniel E. Guyer. Computers and Electronics in Agriculture, 2006

238 citations recorded by the source corpus.

Mechanical injury often causes hidden internal damage to pickling cucumbers, which lowers the quality of pickled products and can incur economic losses to the processor. A near-infrared hyperspectral imaging system was developed to capture hyperspectral images from pickling cucumbers in the spectral region of 900–1700 nm. The system consisted of an imaging spectrograph attached to an InGaAs camera with line-light fiber bundles as an illumination source. Hyperspectral images were taken from the pickling cucumbers at 0–3, and 6 days after they were subjected to dropping or rolling under load which simulated damage caused by mechanical harvesting and handling systems. Principal component analysis (PCA), band ratio, and band difference were applied in the image processing to segregate bruised cucumbers from normal cucumbers. Bruised tissue had consistently lower reflectance than normal tissue and the former increased over time. Best detection accuracies from the PCA were achieved when a bandwidth of 8.8 nm and the spectral region of 950–1350 nm were selected. The detection accuracies from the PCA decreased from 95 to 75% over the period of 6 days after bruising, which was attributed to the self-healing of the bruised tissue after mechanical injury. The best band ratio of 988 and 1085 nm had detection accuracies between 93 and 82%, whereas the best band difference of 1346 and 1425 nm had accuracies between 89 and 84%. The general classification performance analysis suggested that the band ratio and difference methods had similar performance, but they were better than the PCA.

Subfields: Analytical Chemistry, Animal Science and Zoology, Plant Science

View Paper: https://www.semanticscholar.org/paper/179b330c5b3a5c7dda6179ec7e30eb67b4b98da1

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

In Animal Science and Zoology

In Plant Science

Citations in the corpus

Detection of citrus canker using hyperspectral reflectance imaging with spectral information divergence (2009, background): “, 2007), bruises on apples (Lu, 2003) and cucumbers (Ariana et al., 2006), rottenness on citrus (Gómez-Sanchis et al.”
Prediction of white button mushroom (Agaricus bisporus) moisture content using hyperspectral imaging (2009, methodology): “The corrected reflectance value (R) was calculated from the measured signal (‘I’) on a pixel-by-pixel basis as shown below [30]:”
Application of Hyperspectral Imaging in Food Safety Inspection and Control: A Review (2012, background): “Moreover, in terms of bruise inspection, some other fruits and vegetables were also studied including cucumber (Ariana et al., 2006), strawberry (Nagata et al., 2006), and mushroom (Gowen et al., 2008).”
Comparison of Partial Least Squares Regression (PLSR) and Principal Components Regression (PCR) Methods for Protein and Hardness Predictions using the Near-Infrared (NIR) Hyperspectral Images of Bulk Samples of Canadian Wheat (2014, methodology): “In the last decade, hyperspectral imaging was used to detect bruises on pickling cucumbers (Ariana et al. 2006) and apples (Xing et al. 2005), to determine starch indices in apples (Peirs et al. 2003), to detect fecal and ingesta contaminations in poultry carcasses (Park et al. 2002), and to…”
Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality Assessment (2012, background): “Ariana et al. (2006) presented an integrated approach using multispectral imaging in reflectance and fluorescence modes to acquire images of three varieties of apples (Honeycrisp, Redcort and Red Delicious) to distinguish various defects on apples.”
Application of Visible Hyperspectral Imaging for Prediction of Springiness of Fresh Chicken Meat (2015, unknown): “During the last two decades, HSI as a novel and promising analytical tool has been widely used for quality evaluation of different food products such as vegetable (Ariana et al. 2006), beef (ElMasry et al.”
Principles and Applications of Hyperspectral Imaging in Quality Evaluation of Agro-Food Products: A Review (2012, methodology): “Multivariate classification methods applied in hyperspectral data are numerous such as PCA (Xing et al., 2005; 2007), LDA (Park et al., 2007; Mehl et al., 2002), PLSDA (Ariana and Lu, 2008), ANN (Elmasry et al., 2009; Nagata et al., 2006), SVM (Fletcher and Kong, 2003; Nakariyakul and Casasent, 2008”
Application of NIR hyperspectral imaging for discrimination of lamb muscles (2011, background): “Using fewer wavelengths is preferable for online application in order to accelerate image acquisition and subsequent analysis process (Ariana et al., 2006; Nakariyakul and Casasent, 2008).”
Detection of blueberry internal bruising over time using NIR hyperspectral reflectance imaging with optimum wavelengths (2017, methodology): “This method has been successfully used to detect fecal contaminants on apples (Liu et al., 2007), physical damages of pears (Lee et al., 2014), bruises in cucumbers (Ariana et al., 2006), bacterial diseases in onions (Wang et al., 2012a), and common defects of peaches (Li et al., 2016).”
Recent Developments in Hyperspectral Imaging for Assessment of Food Quality and Safety (2014, background): “Hyperspectral imaging systems based on InGaAs camera may provide increased accuracy for assessment and analysis of food quality and safety [30,35,36], but the cost of NIR cameras is higher than for VIS/NIR cameras, which may affect the application of NIR hyperspectral imaing.”
Molecular approaches for enhancing sweetness in fruits and vegetables. (2010, methodology): “, 2007; Ariana et al., 2006; Fu et al., 2008). However, a greater spectral region beyond 1100nm appears to give improved prediction results in sugar content and other quality attributes (Moons et al., 1997; Lu et al., 2000). Lammertyn et al. (2000) established a relationship between the reflectance ”