Identification and Location of Picking Tomatoes Based on Machine Vision

Through researched the method of the identification and location based on machine vision, location information of mature tomatoes has been obtained, which can be used to guide the automated picking operation of ripe tomatoes. The segmentation of visual system is based on the difference between the color characteristics of ripe tomatoes and background. Through the gray-scale method, the treatment of the color image is turned into gray image processing, and the picking tomatoes is accurately identified using mathematical morphology, object extraction, and region filling methods. Furthermore centroid of picking tomatoes is selected as match features, and the picking tomatoes location information is determined through three-dimensional reconstruction method of space point. The experimental results show that the identification of mature fruit can reach 98%, the green ripe fruit up to 89%, positioning error can be controlled within less than 15 mm, identification and location effects can satisfactorily meet actual work requirements.