Chemical composition-based seed inspection on a real-time, non-destructive, and precise basis is important for establishing industries that maximize product cost and quality. Among the chemical compositons of soyean, anthocyanin has many benefits for health such as antioxidants and anti-inflammatory. The objective of this study was to investigate the feasibility of near-infrared hyperspectral imaging (NIR-HSI) for the prediction of anthocyanin content in soybeans. The NIR-HSI system with a wavelength of 895-2504 nm was used to acquire images of eighty-two samples of soybean seeds. The extracted spectral data was synchronized with the soybean anthocyanin reference value, which was determined using high-performance liquid chromatography (HPLC). The calibration models revealed R2 of 0.81 with standard error (SEC) of 0.14 for the prediction of anthocyanin concentrations. This study showed the potential of NIR-HSI to be applied for the prediction of anthocyanin content in soybean seeds.