College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling, Shaanxi, China.
Key Laboratory of Agricultural Internet of Things, Ministry of Agriculture and Rural Affairs, Yangling, Shaanxi, China.
J Sci Food Agric. 2019 Nov;99(14):6234-6240. doi: 10.1002/jsfa.9896. Epub 2019 Aug 8.
The application of exogenous plant growth regulator, for example forchlorfenuron (CPPU), on kiwifruits has become an important factor that influences kiwifruit economic efficiency and the health development of the kiwifruit industry. Owing to the slight difference in calyx shape between the kiwifruits treated with CPPU (CPPU-treated kiwifruits) and the kiwifruits without CPPU treatment (CPPU-untreated kiwifruits), this study aims to provide a cheap, quick, convenient, and non-destructive method for identifying CPPU-treated kiwifruits based on the images of kiwifruits captured at visible lights.
The identification method includes three steps. Firstly, the kiwifruit was extracted from the background by using Otsu algorithm, hole filling operation and 'bwareaopen' function. Secondly, the calyx was extracted by using corrosion, image enhancement, hole filling and closing operations. Finally, the length/width ratio of the minimum enclosing rectangle of calyx region was calculated. The kiwifruit was regarded as a CPPU-treated kiwifruit if the length/width ratio of the rectangle was higher than 1.6. Otherwise, the kiwifruit was regarded as a CPPU-untreated one. The method had the total identification accuracy rate of 90.0% when the kiwifruit images were captured either by utilizing a smartphone at normal lighting condition or by using an image acquisition system.
The programs run on computer and smartphone were developed, and they could realize kiwifruit identification in 0.6 s and 2 s, respectively. The study makes identifying CPPU-treated kiwifruits in online processing be realizable, and offers a convenient method for kiwifruit consumers. © 2019 Society of Chemical Industry.
外源植物生长调节剂，例如氯吡脲（CPPU），在猕猴桃上的应用已成为影响猕猴桃经济效益和猕猴桃产业健康发展的重要因素。由于 CPPU 处理的猕猴桃（CPPU 处理猕猴桃）和未用 CPPU 处理的猕猴桃（CPPU 未处理猕猴桃）之间的花萼形状略有差异，本研究旨在提供一种基于可见光拍摄的猕猴桃图像识别 CPPU 处理猕猴桃的廉价、快速、方便且无损的方法。
该识别方法包括三个步骤。首先，使用 Otsu 算法、空洞填充操作和'bwareaopen'函数从背景中提取猕猴桃。其次，通过腐蚀、图像增强、空洞填充和闭合操作提取花萼。最后，计算花萼区域最小外接矩形的长/宽比。如果矩形的长/宽比高于 1.6，则认为猕猴桃是 CPPU 处理过的；否则，猕猴桃被认为是未经 CPPU 处理的。当使用智能手机在正常光照条件下或使用图像采集系统拍摄猕猴桃图像时，该方法的总识别准确率为 90.0%。
开发了可在计算机和智能手机上运行的程序，分别可在 0.6 s 和 2 s 内实现猕猴桃的识别。该研究使 CPPU 处理猕猴桃的在线处理成为可能，为猕猴桃消费者提供了一种便捷的方法。 © 2019 化学工业协会。
