徐胜勇,彭程里,陈可,王令强,任喜峰,段宏兵.基于扇环形区域图像分割的小麦秸秆截面参数测量方法[J].农业机械学报,2018,49(4):53-59.
XU Shengyong,PENG Chengli,CHEN Ke,WANG Lingqiang,REN Xifeng,DUAN Hongbing.Measurement Method of Wheat Stalks Cross Section Parameters Based on Sector Ring Region Image Segmentation[J].Transactions of the Chinese Society for Agricultural Machinery,2018,49(4):53-59.
摘要点击次数: 2279
全文下载次数: 1208
基于扇环形区域图像分割的小麦秸秆截面参数测量方法   [下载全文]
Measurement Method of Wheat Stalks Cross Section Parameters Based on Sector Ring Region Image Segmentation   [Download Pdf][in English]
投稿时间:2017-09-12  
DOI:10.6041/j.issn.1000-1298.2018.04.006
中文关键词:  小麦秸秆  显微图像  测量  图像分割
基金项目:国家自然科学基金项目(61503146)和中央高校基本科研业务费专项资金项目(2662017JC043)
作者单位
徐胜勇 华中农业大学 
彭程里 华中农业大学 
陈可 华中农业大学 
王令强 华中农业大学 
任喜峰 华中农业大学 
段宏兵 华中农业大学 
中文摘要:针对小麦秸秆截面显微图像中组织成分的结构和灰度特征,研究了一种扇环型分区域图像分割方法,用于精确分割厚壁、维管束等关键组织结构。小麦秸秆截面的内外侧轮廓构成了一个近似的环形区域。先粗略定位厚壁和维管束所属的圆环区域。依据定位信息,以截面中心为起点向圆环外轮廓画射线,将圆环划分为大量的扇环形小区域。用Otsu算法对各个小区域进行独立的阈值分割,再对分割结果进行拼接等后续处理,得到完整的厚壁或维管束,最后以此为基础精确测量秸秆截面的各种参数。实验结果表明,与传统的Otsu算法相比,该方法对显微图像采集过程中切片、染色、拍照等环节导致的低质量图像具有较高的分割准确性和鲁棒性,在提高了切片样本利用率的同时降低了人工劳动强度。该测量系统对各类参数的测量精度均大于94.6%。
XU Shengyong  PENG Chengli  CHEN Ke  WANG Lingqiang  REN Xifeng  DUAN Hongbing
Huazhong Agricultural University,Huazhong Agricultural University,Huazhong Agricultural University,Huazhong Agricultural University,Huazhong Agricultural University and Huazhong Agricultural University
Key Words:wheat stalk  micrograph  measurement  image segmentation
Abstract:The observation and analysis of microstructure of crop stalk are of great value. Based on the structure and gray features of tissues in wheat stalk micrograph, a sector ring region-based image segmentation method was proposed, by which the sclerenchyma and vascular bundles in the micrograph would be separated from the background precisely. The inner and outer contours of the wheat stalks cross-section were got from an approximate annular. The annular that the sclerenchyma and vascular bundle belonged to was firstly located roughly. On the basis of the location information, the center of the section was taken as the origin and drawn rays towards to the outer contours of the annular. By this operation, the annular was divided into many small sector ring regions. Then small regions were segmented respectively by using the Otsu algorithm. Finally, the segmentation results were processed such as superposition, and the complete sclerenchyma or vascular bundle would be obtained. Using the segmentation results all kinds of parameters of the section would be evaluated accurately. It was showed that the method presented had higher accuracy and stronger robustness than the traditional Otsu method in segmenting the low-quality image which caused by slicing, dying and photographing in the process of micrograph acquisition. It improved the utilization rate of the slice sample and reduced the labor intensity. The accuracy of all the parameters obtained by using the measurement system was more than 94.6%, which would play an important practical role in the research of wheat stalk microstructure.

Transactions of the Chinese Society for Agriculture Machinery (CSAM), in charged of China Association for Science and Technology (CAST), sponsored by CSAM and Chinese Academy of Agricultural Mechanization Science(CAAMS), started publication in 1957. It is the earliest interdisciplinary journal in Chinese which combines agricultural and engineering. It always closely grasps the development direction of agriculture engineering disciplines and the published papers represent the highest academic level of agriculture engineering in China. Currently, nearly 8,000 papers have been already published. There are around 3,000 papers contributed to the journal each year, but only around 600 of them will be accepted. Transactions of CSAM focuses on a wide range of agricultural machinery, irrigation, electronics, robotics, agro-products engineering, biological energy, agricultural structures and environment and more. Subjects in Transactions of the CSAM have been embodied by many internationally well-known index systems, such as: EI Compendex, CA, CSA, etc.

   下载PDF阅读器