基于Otsu算法与形态学的火龙果图像分割研究

Research on pitaya image segmentation based on Otsu algorithm and morphology

图像检测识别是自动采摘技术的关键环节,本文是以火龙果为研究对象,提出一种采用最大类间方差(Otsu)法并结合数学形态学的火龙果果实图像分割方法,最终实现对火龙果果实与背景的分离,并计算果实质心,为后续的机器人采摘技术奠定基础。算法实验表明,通过联合引入Otsu阈值分割算法和数学形态学处理,所得火龙果图像更加清晰,提高了图像的可视性和准确性,效果优于只采用阈值分割。

Image detection and recognition is the key link of automatic picking technology.This paper takes Huolong fruit as the research object,and proposes a method of image segmentation of Huolong fruit by using the maximum inter class variance(Otsu)method and mathematical morphology.Accordingly,the separation of the fruit from the background is realized,and the fruit quality center is calculated,which lays the foundation for the robot picking technology.The experiment shows that the image of Huolong fruit is clearer after the Otsu threshold segmentation algorithm and mathematical morphology,which improves the visibility and accuracy of the image,and the effect is better than the threshold segmentation.