An automatic foreign materials detection of barberries using red-free image processing

In this study, a new approach is introduced for automatically detecting of visual foreign materials like peduncles, leaves and blight products in mass of Barberries. The segmentation algorithm has been developed for red-free images of barberries. Cr plane of YCbCr color space is used to detect the target area of images. Because of shining of barberry´s glossy cortex during imaging, there are many pixels with the same color of the target areas in Cr plane. A simple equation using statistic parameters of binary images is used to find a compatible threshold for detecting the target areas in each image. With this algorithm, the foreign materials are acceptably detected compared to manually segmented images. This method is very useful when there are many unwanted partially big regions in the image with the same color of target areas.