Soybean in various colour is easy to identify using human eyes. However, it is hard to perform manual method for on-line production. Therefore, detection of colour for sorting the soybean is important especially for industries which require a rapid and real-time task. This research was conducted to study the potency of a modular type of VIS/NIR spectroscopy at wavelength of 350-1000 nm to classify black, green, and yellow of soybean seed and flour. Principal component analysis (PCA) and PCA Linear discriminant analysis (PCA-LDA) were used based on various spectra pre-processing techniques. Results showed that PCA-LDA model was able to classify soybean seeds of 97% accuracy and soybean flour of 100% accuracy.

The purpose of this study was to use study the potency of the modular Vis/NIR spectroscopy for determining viability of soybean seeds. Vis/NIR spectra of soybean seeds were collected and analysed using partial least squares discriminant analysis (PLS-DA) for discriminating non-viable soybean seeds from viable ones. The optimal classification models developed were compared with various spectral pre-processing methods. The result showed that the modular Vis/NIR spectroscopy performed perfectly (Accuracy and Reliability of 100%) in detecting soybean viability. The study showed that the Vis/NIR spectroscopy coupled with chemometric analysis are potential for rapid detection of viability of soybean seeds.