Observation and Measurement of Residual Bran on Milled Rice Using Hyperspectral Imaging

Abstract

Cereal Chem. 91(6):566-571Residual bran on milled rice is directly related to its quality. This study proposes a method to measure the residual bran patterns on a single rice grain by using hyperspectral imaging (HSI). HSI is a sensing technique that combines both spatial and spectral information and may be used for chemical compound identification and quantification. In this study, HSI was applied to assess rice bran residue nondestructively. In the experiment, rice samples were milled and scanned with an HSI system. Afterward, the rice samples were dyed to enable the residual bran to be identified with optical microscopy and image processing algorithms. Classifiers were then developed to predict the rice bran residue by using the HSI measurements as inputs. The predicted images were compared with the micrograph images for classifier performance evaluation. The proposed approach can estimate the residual bran distribution on milled rice surface with an accuracy of 93.5%.Rice (Oryza sativa) is a vital crop worldwide. It is typically consumed after milling, a process that removes the husk and bran layers from the grains. The amount of residual bran after milling substantially affects rice quality and attractiveness to consumers. Rapidly and accurately assessing the rice bran residue in commercial practice is crucial. This study developed an approach to observe the distribution of residual bran nondestructively on a single rice grain by using hyperspectral imaging (HSI).Chemical analyses have been used to determine the residual bran of milled rice. Bhattacharya and Sowbhagya (1972) applied a differential dye-staining method to estimate rice degree of milling (DOM) (USDA 1997). Hogan and Deobald (1961) designed an extraction procedure to determine the amount of bran remaining on bulk rice samples. Because bran is primarily composed of lipid, Matsler and Siebenmorgen (2005) evaluated procedures for analyzing surface lipid content (SLC) of milled rice samples with a Soxtec system. Wood et al (2012) observed the removal patterns of bran and germ by using microscopy and lipid-specific probes. Another study attempted to determine the DOM by analyzing the components that remained on rice surface after milling (Matthews and Spadaro 1980). These chemical methods typically required labor-intensive sample preparation. Although presumably accurate, they are time-consuming and not applicable for online measurement.Nondestructive methods have also been proposed to rapidly assess the rice bran residue. Siebenmorgen and Sun (1994) reported a high degree of correlation between surface fat concentration and DOM measurement from a commercial optical-based milling meter. Chen et al (1997) quantified the SLC on three rice cultivars by using visible and near-infrared (NIR) spectroscopy. Liu et al (1998) developed a procedure that quantified the percentage of the bran layer residue on a single rice grain based on machine vision and image analysis. Gangidi et al (2002) demonstrated the use of Fourier transform infrared spectroscopy for me...

Near-Infrared spectroscopy and hyperspectral imaging for non-destructive quality assessment of cereal grains

“…A comparison between the HSI prediction model and the evaluation through optical microscopy analysis resulted in an estimation accuracy of 93.5%. Statistical techniques such as PCA, SVM, and LDA were compared to verify the classification between grains with excessive residual bran and those with acceptable low bran content (60).…”