Recently with development of computer imaging, the application field of near infrared image processing becomes much wider. The potential of machine vision application in the determination of alkaloid in Dioscorea hispida rhizome was explored. A camera vision system used in this research is TETRACAM multispectral camera, which consists of three bands, namely red band (R), green band (G) and near infrared band (NIR). The first component is the hardware component that functions as an image acquisitioned for the system. The second component is the software part which converts data obtained from the hardware. From the design review, the images from a variety of harvested of Dioscorea hispida will be captured and the readings in multispectral wavelength index were tabulated. The statistical relationship between multispectral wavelength and alkaloid level in the fruit were determined. The development on this study is grouped as non destructive method to determine the dioscorine content which is one of the alkaloid components in the rhizome of Dioscorea hispida.