<FONT face="Verdana">基于霍特林变换的稻米彩色图像粒形检测算法</FONT>

刘璎瑛,丁为民陈建伟,沈明霞

doi:10.3969/j.issn.1001-7216.2010.03.018

中国水稻科学 >

2010 , Vol. 24 >Issue 3: 325 - 328

DOI: https://doi.org/10.3969/j.issn.1001-7216.2010.03.018

研究简报

基于霍特林变换的稻米彩色图像粒形检测算法

展开

¹南京农业大学工学院，江苏南京 210031； ²江苏省粮食局粮油质量监测所，江苏南京 210011； *通讯联系人，E-mail：wmding@jlonline.com

收稿日期: 1900-01-01

修回日期: 1900-01-01

网络出版日期: 2010-05-10

收起

A Hotelling TransformBased Algorithm for Rice Grain Type Detection with Color Images

Expand

¹College of Engineering, Nanjing Agricultural University, Nanjing 210031, China; ²Grain and Oil Quality Monitoring Institute of Grain Bureau of Jiangsu Province, Nanjing 210011, China; ^*Corresponding author, E-mail: wmding@jlonline.com

Received date: 1900-01-01

Revised date: 1900-01-01

Online published: 2010-05-10

Fold

摘要

利用稻米分割后轮廓灰度图与背景灰度图的灰度均值之差和灰度方差之差进行米粒图像分割效果定量评价，对7个彩色通道的稻米图像进行分割评判，选取I1（红色、绿色、蓝色通道的平均值）通道进行稻米图像分割。提取分割后标注的单粒米粒边界的二维坐标向量，对坐标向量进行霍特林变换，通过计算变换后米粒最小外接矩阵来表征稻米粒形，简化了现有的稻米粒形检测算法。检测稻米粒型时，算法在MATLAB 7.5.0环境下运行。该算法所得米粒长宽比与人工检测结果的平均相对误差为1.65%，每幅图像平均耗时0.323 s；而最小外接矩形算法的平均相对误差为2.24%，每幅图像平均耗时2837 s。

关键词： 霍特林变换; 稻米; 彩色图像; 颜色通道; 粒形检测

本文引用格式

刘璎瑛,丁为民陈建伟,沈明霞 . 基于霍特林变换的稻米彩色图像粒形检测算法[J]. 中国水稻科学, 2010 , 24(3) : 325 -328 . DOI: 10.3969/j.issn.1001-7216.2010.03.018

Abstract

An algorithm for rice grain type detection using color image segmentation and the Hotelling transform was proposed. The rice grain images were segmented in I1 band(the average of red, green and blue color bands) chosen from seven color bands according to quantitative analysis of segmentation performance. The coordinate vector of segmented image edge was converted by the Hotelling transform. Grain size features were extracted in the new coordinate system using minimum enclosing rectangle. This algorithm was run in MATLAB 7.5.0 to count rice grain ratio. The relative error compared with manual measurement were 1.65% and 2.24%, and the running times were 0.323 s and 2.837 s per image, respectively, for this algorithm and algorithm using minimum enclosing rectangle.

Key words： Hotelling transform; rice; color image; color bands; grain type detection

参考文献

[1]van Dalen G. Determination of the size distribution and percentage of broken kernels of rice using flatbed scanning and image analysis. Food Res Int, 2004, 37: 51-58.

[2]Zhang J, Sokhansanj S, Wu S, et al. A trainable grading system for tobacco leaves. Comp & Electron Agric, 1997, 16: 231-244.

[3]Rabiei B, Valizadeh M, Ghareyazie B, et al. Identification of QTLs for rice grain size and shape of Iranian cultivars using SSR markers. Euphytica, 2004, 137: 325-332.

[4]应义斌, 王剑平, 蒋焕煜. 水果直径和缺陷面积的机器视觉检测. 农业工程学报, 2002, 18(5): 216-220.

[5]陈鲤江, 刘铁根, 王磊, 等. 基于区域跨度搜索的稻米粒型检测方法. 光电子·激光, 2007, 18(1): 93-96.

[6]应义斌, 成芳, 马俊福. 基于最小矩形法的柑桔横径实时检测方法研究. 生物数学学报, 2004, 19(3): 352-356.

[7]陈建华, 姚青, 谢绍军, 等. 机器视觉在稻米粒型检测中的应用. 中国水稻科学, 2007, 21(6): 669-672.

[8] Gonzalez R C, Woods R E. Digital Image Processing. 2nd ed. Upper Saddle River, NJ: Prentice Hall, 2003.

[9]章毓晋. 图像分割评价技术分类和比较. 中国图像图形学报, 1996, 1(2): 151-158.

[10]Ohta Y I, Kanade I, Sakai I. Color information for region segmentation. Comp Graphics & Image Proc, 1980, 13: 222-241.

[11]章毓晋. 图像工程(中册)：图像分析. 2版. 北京: 清华大学出版社, 2005.

[12]龚声蓉, 刘纯平, 王强, 等. 数字图像处理与分析. 北京: 清华大学出版社, 2006.

[13]中华人民共和国国家标准GB/T 17891-1999(优质稻谷). 北京: 中国标准出版社, 1999.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献