Automatic segmentation method for multi-tomato images under various growth conditions

It is fundamental to realize intelligent fruit-picking that mature fruits are distinguished from complicated backgrounds and their three-dimensional locations are determined. Various methods for fruitidentification can be found from the literature. However, surprisingly little attention has been paid to imagesegmentation of multi-fruits which growth morphologies are connected, overlapped and partially covered by branches andleaves of plant under natural illumination conditions. In this paper the authorspresent an automatic segmentation method that comprises three main steps. First, Red and Green component images are extracted from RGBcolor image, and Green component subtracted from Red component gives RG of coloraberration gray-levelimage. Gray-level value between objects and background has obvious differencein RG image. By the feature,Ostu's threshold method is applied to do adaptive RG image segmentation. And then, controlled-watershedsegmentation based on morphological grayscale reconstruction is applied into Redcomponent image to searchedge boundary of connected or overlapped tomatoes. Finally, intersection operation is done by operation resultsof above two steps to obtain black and white image of final segmentation. The tests show that the automaticsegmentation method has satisfactory effects upon multi-tomato images of various growth morphologies under natural illumination conditions. Meanwhile, it is very robust for different maturities of multi-tomato images.