[1]李颀,王康,强华,等.基于颜色和纹理特征的异常玉米种穗分类识别方法[J].江苏农业学报,2020,(01):24-31.[doi:doi:10.3969/j.issn.1000-4440.2020.01.004]
　LI Qi,WANG Kang,QIANG Hua,et al.Classification and recognition method of abnormal corn ears based on color and texture features[J].,2020,(01):24-31.[doi:doi:10.3969/j.issn.1000-4440.2020.01.004]
点击复制

基于颜色和纹理特征的异常玉米种穗分类识别方法()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2020年01期
页码:
24-31
栏目:
遗传育种·生理生化
出版日期:
2020-02-29

文章信息/Info

Title:
Classification and recognition method of abnormal corn ears based on color and texture features
作者:
李颀; 王康; 强华; 马琳
(陕西科技大学电气与控制工程学院，陕西西安710021)
Author(s):
LI Qi; WANG Kang; QIANG Hua; MA Lin
（College of Electrical and Control Engineering, Shaanxi University of Science and Technology, Xi′an 710021, China)
关键词:
玉米种穗; 计算机视觉; 颜色特征; 纹理特征; 分类识别
Keywords:
corn ears; computer vision; color features; texture features; classification and recognition
分类号:
S126;TP391.41
DOI:
doi:10.3969/j.issn.1000-4440.2020.01.004
文献标志码:
A
摘要:
针对玉米选种过程中异常种穗的外观缺陷难以准确识别的问题，以玉米种穗为研究对象，通过计算机视觉技术快速识别杂色、缺粒、虫蛀、籽粒杂乱4种异常种穗。选择单目视觉采集装置，采集任意姿态玉米种穗图像，利用凹点匹配算法分割粘连玉米种穗；采用HSV和CLBP（完全局部二值模式）方法提取玉米种穗的颜色和纹理特征，利用匹配得分融合算法融合玉米种穗的颜色和纹理特征，建立玉米种穗分类模型，利用SVM实现4种异常玉米种穗的快速分类。试验结果表明，该方法相对于传统玉米种穗检测技术能快速有效识别出4种异常玉米种穗，对杂色、缺粒、虫蛀、籽粒杂乱玉米种穗的识别正确率分别达到了96.0%、94.7%、93.6%和95.3%，玉米种穗在有粘连和无粘连情况下平均识别速度分别为每穗1.180 s和0.985 s，能够满足异常种穗分类识别的需求。
Abstract:
This study aims at the problem that it is difficult to accurately identify the appearance defects of abnormal corn ears during corn selection. Taking the whole corn ear as the research object, the four kinds of abnormal corn ears(variegated corn ear, missing corn ear, worm-eaten corn ears and untidy corn ears) were quickly identified by computer vision technology. The monocular visual image acquisition device was selected to collect the image of the corn ear in arbitrary posture, and the pit matching algorithm was used to complete the rapid segmentation of the cohesive corn ear. The HSV color model and complete local binary pattern(CLBP) method were used to extract color and texture features of corn ear, and the matching score fusion algorithm was used to fuse the color and texture features of corn ear. At the same time, an abnormal corn ears classification model was established. Finally, the rapid classification of four abnormal corn ears was achieved by support vector machine(SVM). The experimental results showed that this method could quickly and effectively identify four abnormal corn ears compared with traditional corn ear measurement technology. The correct recognition rate of this method was 96.0%, 94.7%, 93.6% and 95.3% for the variegated corn ears, missing corn ears, worm-eaten corn ears and untidy corn ears. The average recognition speed of maize seed ear in the presence of adhesion and non-adhesion was 1.180 seconds per ear and 0.985 seconds per ear. This method can provide a basis for the identification of abnormal ears during the intelligent corn ear sorting process.

参考文献/References:

[1]刘长青,陈兵旗. 基于机器视觉的玉米果穗参数的图像测量方法[J].农业工程学报,2014,30(6):131-138.
[2]杜建军,郭新宇,王传宇,等. 基于分级阈值和多级筛分的玉米果穗穗粒分割方法[J].农业工程学报,2015,31(15):140-146.
[3]SUN X H, GUO M, MA M, et al. Identification and classification of damaged corn kernels with impact acoustics multi-domain patterns[J]. Computers and Electronics in Agriculture,2018,150:152-161.
[4]张玉荣,王伟宇,周显青,等. 基于外观特征识别玉米不完善粒检测方法[J].河南工业大学学报(自然科学版),2015,36(2):1-7.
[5]周金辉,马钦,朱德海,等. 基于机器视觉的玉米果穗产量组分性状测量方法[J].农业工程学报,2015,31(3):221-227.
[6]李伟,胡艳侠,吕岑. 基于HSV空间的玉米果穗性状的检测[J].湖南农业大学学报(自然科学版),2017,43(1):112-116.
[7]张帆,李绍明,刘哲,等. 基于机器视觉的玉米异常果穗筛分方法[J].农业机械学报,2015,46(S1):45-49.
[8]王慧慧,孙永海,张婷婷,等. 鲜食玉米果穗外观品质分级的计算机视觉方法[J].农业机械学报,2010,41(8):156-159.
[9]崔欣,张鹏,赵静,等. 基于机器视觉的玉米种粒破损识别方法研究[J].农机化研究,2019,41(2):28-33.
[10]ZINEB Y, LARBI B, ABDELHANI B. Human ear recognition based on local multi-scale LBP features withcity-block distance[J]. Multimedia Tools and Applications,2019,78(11): 14425-14441.
[11]周宇旋,吴秦,梁久祯,等. 判别性完全局部二值模式人脸表情识别[J].计算机工程与应用,2017,53(4):163-169.
[12]WANG X L, ZHU Q, CUI J R, et al. Sparse representation method based on Gabor and CLBP[J]. Optik-International Journal for Light and Electron Optics,2013,124(22): 5843-5850.
[13]范朝冬,欧阳红林,肖乐意. 基于空间截面投影的Otsu图像分割算法[J].通信学报,2014,35(5):70-78.
[14]王小鹏,姚丽娟,文昊天,等. 形态学多尺度重建结合凹点匹配分割枸杞图像[J].农业工程学报,2018,34(2):212-218.

相似文献/References:

[1]任守纲,朱勇杰,顾兴健,等.基于稀疏实例与位置感知卷积的植物叶片实时分割方法[J].江苏农业学报,2024,(03):478.[doi:doi:10.3969/j.issn.1000-4440.2024.03.010]
　REN Shou-gang,ZHU Yong-jie,GU Xing-jian,et al.Real-time segmentation of plant leaves based on sparse instances and position aware convolution[J].,2024,(01):478.[doi:doi:10.3969/j.issn.1000-4440.2024.03.010]

备注/Memo

备注/Memo:
收稿日期：2019-08-25基金项目：陕西省科技厅农业科技攻关计划项目(2015NY028)作者简介：李颀(1973-)，女，陕西西安人，博士，教授，主要从事工业自动化与智能控制等方面的教学与科学工作。(E-mail）liqidq@sust.edu.cn通讯作者：王康，(E-mail)1115673101@qq.com
更新日期/Last Update: 2020-03-13