Mature Tomato Fruit Detection Algorithm Based on improved HSV and Watershed Algorithm

Abstract

Tomato is well known fruit since it has many essential and beneficial nutrients like antioxidant, vitamin C and A for human daily diet. Tomato picking by hand is both labor and time consuming. Therefore, to overcome these issues, tomato needs to be picked up automatically with the help of harvesting robot. Recently automation of fruit harvesting gains great popularity. To guide the harvesting robot to pick up the fruit correctly, it is important to correctly detect and find the location of the red mature fruit. In this study, a new mature tomato detection algorithm based on the improved HSV (Hue, Saturation, Value) color space and the improved watershed segmentation was proposed, by using a cheap and easily accessible RGB camera for guiding a robot to pick up red tomatoes automatically. For that purpose, the color images of tomato plants were captured under natural light. At the first stage, improved HSV transform was used to remove background and to detect only red tomatoes. Then the morphological operations were applied to modify the detected fruit. The second step was the separation of connected fruits, so that the harvesting robot can pick up fruit correctly. To achieve this task, the improved watershed algorithm was applied. As a result, the detection of separated red mature tomato was done by using the improved HSV and watershed, with uneven illumination and complex background. The overall red fruit detection accuracy was up to 81.6%, and it shows good potential to be used on harvesting robot.