基于数字图像处理的凤梨花卉品质参数检测的研究  

Bromeliad Quality Parameters Detection Based on Digital Image Processing

作　　者：熊宇鹏[1] 毛罕平[1] 左志宇[1] 张晓东[1] 姚舟华[1] 

机构地区：[1]江苏大学现代农业装备与技术省部共建教育部/江苏省重点实验室,江苏镇江212013

出　　处：《农机化研究》2013年第9期163-168,共6页Journal of Agricultural Mechanization Research

基　　金：国家自然科学基金项目(61233006;31201659);江苏省科技支撑项目(BE2011338;BE2012390);江苏高校优势学科建设工程项目(苏财教[2011]8号)

摘　　要：使用数字图像处理技术对影响设施花卉品质的各参数进行了描述与检测。通过分析凤梨花卉的形态及颜色特征,提出了采用R-G特征加抗干扰滤波分割大花和小花,2G-R-B特征提取出株冠部分;给出了花盖度、小花占大花比例和花序直立程度等3个凤梨品质参数的算法。结果表明,花盖度的检测相对误差≤2.3%。本研究所提出的方法能对小花占大花比例和花序直立程度等进行定量判断,而人工目测只能给出定性判断结果。This paper is based on digital image processing to describe and detect the influencing factor of bromeliad quality.In consideration of the characteristics that the shape and color of the bromeliad,this paper presents some methods that to use R-G color channel operation and anti-interference image filtering to finish the image segmentation of the bromeliad＇s spica and stamen,to use 2G-R-B color channel operation to segment the bromeliad＇s plant crown.And this paper also presents image processing algorithms to calculate the characteristics value of three quality influencing parameters： the size of the flower surface,the ratio of area of the spica and stamen,upright or not of the inflorescence.The characteristics value of size inspection of the flower surface with error rate of 2.3% or less.The research results get a quantitative characteristics value of the ratio and state,but the common visual inspection can only get some qualitative results.

关 键 词：数字图像处理 凤梨 品质检测 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]