基于计算机视觉的水果直径检测方法的研究

Research on Fruit Diameter Detecting by Using Computer Vision

利用机器视觉对水果进行自动分级是国内研究热点。在水果分级中,按直径大小对水果进行分类是自动分级技术的一个关键部分,然而目前通过图像对水果直径检测存在着精度与计算量之间的突出矛盾。针对这一问题,本文介绍了一种水果边界快速提取的方法,并在此基础上提出了一种新的水果直径检测的快速算法:该方法通过对水果图像进行分割,并计算各个区域内水果的最大半径,进而计算出水果的最大直径。通过实验表明,与传统方法相比较,该算法能够在较小的计算量下得到较高的计算精度,可应用于工业实际生产中。

It＇s a hotspot on fruit sorting using computer vision. It is a key point to classify fruits according to fruit diameter during the sorting process. However, there is an obvious contradiction between accuracy and the amount of calculation in the fruit diameter detection using image analysis. Concerning about this problem, this paper has introduced a fast method for fruit border extraction method and based on it, a new fast algorithm for fruit diameter detecting was proposed： Segmenting fruit image, calculating the longest radius of each regions, then obtaining the longest diameter of the fruit. Campared with the other traditional methods, it can be found that the new algorithm has a good performance on the accuracy with little time, so it is can be used for industry application.