Detect Black Germ in Wheat Using Machine Vision

The objective of this research is to develop algorithm to recognize black germ wheat based on image processing. The sample used for this study involved wheat from major producing areas of China. Images of wheat were acquired with a color linear CCD machine vision system. Each image was pre-processed to correct color offset. Then double threshold method was used to segment black germ from background and other area in wheat. Combining morphological and extracted feature gave a highly acceptable classification. The high classification accuracies obtained using a small number of features indicate the potential of the algorithm for on-line inspection of black germ wheat in industrial environment. The overall average classification accuracy among the involved varieties reaches above 93%. This paper presents the significant elements of the computer vision system and emphasizes the important aspects of the image processing technique.