基于颜色和纹理特征的青椒识别方法

doi:10.13733/j.jcam.issn.20955553.2024.12.028

摘要/Abstract

摘要：

自然环境下青椒与叶片和茎秆的颜色较为相似，为提高青椒采摘机器人在自然环境下对青椒果实的识别效率和采摘精度，提出一种基于颜色和纹理特征的青椒识别方法，在自然环境下可以达到较好的识别效果。首先，将青椒图像由RGB转换为HSV颜色空间，经过对比分析S-V分量颜色差异能够突出果实，去除部分复杂背景；然后，再提取青椒 LBP特征和 HOG特征，建立单特征和多特征融合模型；最后，使用不同的分类器SVM、AdaBoost进行特征训练，找出最适合青椒识别的分类算法。试验结果表明：LBP+HOG+AdaBoost算法的识别准确率达到99.3%，均优于其他模型。可为青椒采摘机器的智能识别提供研究基础。

关键词: 青椒识别, SVM, AdaBoost, 颜色特征, 纹理特征

Abstract:

In order to improve the recognition efficiency and picking accuracy of the green pepper picking robot on the green pepper fruit in the natural environment, a green pepper recognition method based on the color and texture characteristics is proposed, and the conventional RGB color camera can achieve a better recognition effect in the natural environment by using the conventional RGB color camera. Firstly, the green pepper image is converted from RGB to HSV color space, and after comparative analysis of the color difference of the S-V component, the fruit can be highlighted, the complex background can be removed, and then the LBP features and HOG features of the green pepper are extracted, a single feature model and a multi-feature fusion model are established, and different classifier SVM and AdaBoost are used for feature training to find out the classification algorithm that is most suitable for green pepper recognition. Experimental results show that the recognition accuracy of LBP+HOG+AdaBoost algorithm reaches 99.3%, which is better than other models. This study can provide a research basis for the intelligent identification of green pepper picking machines.

Key words: green pepper recognition, SVM, AdaBoost, color characteristics, texture characteristics

中图分类号:

S641.3

张珍, 吴雪梅, 黄华成, 吴雪君, 张大斌. 基于颜色和纹理特征的青椒识别方法[J]. 中国农机化学报, 2024, 45(12): 187-192.

Zhang Zhen, Wu Xuemei, Huang Huacheng, Wu Xuejun, Zhang Dabing. Green pepper recognition based on color and texture characteristics[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(12): 187-192.

参考文献

［1］　王瑾,王瑞荣,李晓红.番茄采摘机器人目标识别方法研究［J］. 江苏农业科学,2021,49(20):217-222.
Wang Jin, Wang Ruirong, Li Xiaohong. Research on target recognition method of tomato picking robot ［J］. Jiangsu Agricultural Sciences, 2021,49(20):217-222.
［2］　陈飞,葛云,张立新,等.红花采摘机器人集条预定位机构设计与试验［J］.农业工程学报,2021,37(15):10-19.
Chen Fei, Ge Yun, Zhang Lixin, et al. Design and experiment of the stripcollected prepositioning mechanism for safflower picking robots ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021,37(15):10-19.
［3］　张继成,李德顺.基于深度残差学习的成熟草莓识别方法［J］.中国农机化学报,2022,43(2):136-142.
Zhang Jicheng, Li Deshun. Ripe strawberry recognition method based on deep residual learning ［J］. Journal of Chinese Agricultural Mechanization,2022, 43(2):136-142.
［4］　高梦圆,马双宝,董玉婕,等.基于实例分割苹果采摘机器人视觉定位与检测［J］.江苏农业科学,2022,50(3):201-208.
Gao Mengyuan, Ma Shuangbao, Dong Yujie, et al. Visual localization and detection of apple picking robot based on case segmentation ［J］. Jiangsu Agricultural Sciences,2022,50(3):201-208.
［5］　于丰华,周传琦,杨鑫.日光温室番茄采摘机器人设计与试验［J］.农业机械学报,2022,53(1):41-49.
Yu Fenghua, Zhou Chuanqi, Yang Xin, et al. Design and experiment of tomato picking robot in solar greenhouse ［J］.Transactions of Chinese Society for Agricultural Machinery, 2022,53(1):41-49.
［6］　张勤,陈建敏,李彬,等.基于RGB-D信息融合和目标检测的番茄串采摘点识别定位方法［J］.农业工程学报,2021,37(18):143-152.
Zhang Qin, Chen Jianmin, Li Bin, et al. Method for recognizing and locating tomato cluster picking points based on RGB-D information fusion and target detection ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021,37(18):143-152.
［7］　郑嫦娥,高坡,Gan Hao,等.基于分步迁移策略的苹果采摘机械臂轨迹规划方法［J］.农业机械学报,2020,51(12):15-23.
Zheng Change, Gao Po,Gan Hao, et al. Trajectory planning method for apple picking manipulator based on stepwise migration strategy ［J］. Transactions of Chinese Society for Agricultural Machinery.2020,51(12):15-23.
［8］　麦春艳,郑立华,肖昌一,等.自然光照条件下苹果识别方法对比研究［J］.中国农业大学学报,2016,21(11):43-50.
Mai Chunyan, Zheng Lihua, Xiao Changyi, et al. Comparison of apple recognition methods under natural light ［J］. Journal of China Agricultural University, 2016,21(11):43-50.
［9］　钱建平,杨信廷,吴晓明,等.自然场景下基于混合颜色空间的成熟期苹果识别方法［J］.农业工程学报,2012,28(17):137-142.
Qian Jianping, Yang Xinting, Wu Xiaoming, et al. Mature apple recognition based on hybrid color space in natural scene ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2012,28(17):137-142.
［10］　司永胜,乔军,刘刚,等.基于机器视觉的苹果识别和形状特征提取［J］.农业机械学报,2009,40(8):161-165,73.
Si Yongsheng, Qiao Jun, Liu Gang, et al. Recognition and shape features extraction of apples based on machine vision ［J］. Transactions of Chinese Society for Agricultural Machinery,2009,40(8):161-165,73.
［11］　赵辉,乔艳军,王红君,等.基于改进YOLOv3的果园复杂环境下苹果果实识别［J］.农业工程学报,2021,37(16):127-135.
Zhao Hui, Qiao Yanjun, Wang Hongjun, et al. Apple fruit recognition in complex orchard environment based on improved YOLOv3 ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021,37(16):127-135.
［12］　张伟,周梦源,夏坚.基于改进HOG特征提取与SVM分类器的建筑裂缝识别方法［J］.南昌工程学院学报,2022,41(1):47-51.
Zhang Wei, Zhou Mengyuan, Xia Jian. Building crack recognition method based on improved HOG feature extraction with SVM classifier ［J］. Journal of Nanchang Institute of Technology, 2022,41(1):47-51.
［13］　刘庆华,李智.一种基于HOG与LBP双特征融合模型的人脸年龄估计方法［J］.江苏科技大学学报(自然科学版),2021,35(3):50-55.
Liu Qinghua, Li Zhi. Faceage estimation method based on HOG and LBP dual feature fusion model ［J］. Journal of Jiangsu University of Science and Technology, 2021,35(3):50-55.
［14］　刘栩廷,刘姣娣,王明明,等.基于SVM的蔗种坏芽检测识别［J］.石河子大学学报(自然科学版),2022(4):481-486.
Liu Xuting, Liu Jiaodi, Wang Mingming, et al. Detection and recognition of sugarcanebad bud based on SVM ［J］.Journal of Shihezi University (Natural Science Edition),2022(4):481-486.
［15］　张燕,田国英,杨英茹,等.基于SVM的设施番茄早疫病在线识别方法研究［J］.农业机械学报,2021,52(S1):125-133,206.
Zhang Yan, Tian Guoying, Yang Yingru, et al. Online detection method of tomato early blight disease based on SVM ［J］. Transactions of Chinese Society for Agricultural Machinery,2021,52(S1):125-133,206.
［16］　杨光,张洪熙,方涛,等.基于改进AdaBoost算法的秸秆识别与覆盖率检测技术［J］.农业机械学报,2021,52(7):177-183.
Yang Guang, Zhang Hongxi, Fang Tao, et al. Straw recognition and coverage rate detection technology based on improved AdaBoost algorithm ［J］. Transactions of Chinese Society for Agricultural Machinery,2021,52(7):177-183.

[1]	吴鹏, 刘金兰. 基于PCA-LDASVM算法的茶小绿叶蝉识别[J]. 中国农机化学报, 2024, 45(1): 295-300.
[2]	段东瑶, 赵丽清, 殷元元, 郑映晖, 徐鑫, 孙颖. 绿茶加工过程含水率变化规律及预测模型研究[J]. 中国农机化学报, 2022, 43(3): 75-83.
[3]	曹丽桃, 程曼, 袁洪波, 刘月琴, 随海燕, 赵晓霞. 可穿戴设备部署位置对羊只行为识别的影响与分析[J]. 中国农机化学报, 2022, 43(12): 133-141.
[4]	吴丹, 刘永华, 吴玉娟. 基于LoRa和SVM-Markov的蓝莓园精准灌溉系统研究[J]. 中国农机化学报, 2022, 43(11): 203-208.
[5]	杨英茹, 吴华瑞, 张燕, 朱华吉, 李瑜玲, 田国英, . 基于复杂环境的番茄叶部图像病虫害识别[J]. 中国农机化学报, 2021, 42(9): 177-186.
[6]	李健;熊琦;胡雅婷;. 基于改进AdaBoost算法对环柄菇毒性判别研究[J]. 中国农机化学报, 2021, 42(3): 72-77.
[7]	单慧勇;李晨阳;张程皓;赵辉;卫勇;郭旭存;. 效益优先的温室光照优化调控模型研究[J]. 中国农机化学报, 2021, 42(2): 66-73.
[8]	刘东, 曹光乔, 李亦白, 陈聪. 基于颜色特征的小麦抽穗扬花期麦穗识别计数^*[J]. 中国农机化学报, 2021, 42(11): 97-102.
[9]	李浩;徐航煌;郑恒宇;陈学永;. 基于无人机遥感图像的松材线虫病监测技术研究[J]. 中国农机化学报, 2020, 41(9): 170-175.
[10]	张国霜;王娜;李卓识;林楠;. 基于融合的DWT-LTP-IGLCM的野生食用菌纹理特征分类方法研究[J]. 中国农机化学报, 2020, 41(8): 108-115.
[11]	卢柳江;匡迎春;陈兰鑫;李国睿;. 基于级联AdaBoost分类器的农作物虫害图像识别研究[J]. 中国农机化学报, 2019, 40(8): 127-131.
[12]	李秀昊;马旭;李泽华;邓向武;李宏伟;. 基于特征融合和SVM的稻谷品种识别[J]. 中国农机化学报, 2019, 40(7): 97-102.
[13]	张娟利;宋朝阳;韩文霆;尚晓明;刘治开;. 基于RGB图像处理的烟叶水分无损检测方法研究[J]. 中国农机化学报, 2019, 40(5): 62-68.
[14]	施瑶;陈昭;. 基于SAFA优化LSSVM的粮食产量预测[J]. 中国农机化学报, 2019, 40(3): 144-148.