Research on peanut seeds selection based on color segmentation and PSO-RELM algorithm

doi:10.13733/j.jcam.issn.2095-5553.2024.09.014

Abstract

Abstract:

Aiming at the problems of large workload and low efficiency in the process of peanut seeds manual selection，a peanut seed selection algorithm based on color segmentation and improved ELM was put forward. Based on clustering characteristics of peanut image，peanut image was segmented by limiting the color range in RGB and HSV color space，to obtain the peanut seeds of image target area. The feature of peanut image was described by using color，shape，improvement of HU moment， based on improved HU moment translation，rotation and scaling invariance，to expand the image characteristics of quantity and get the peanut image data sets. Golden section method was used to select number of hidden layer neurons quickly. Introducing the regularization parameter，the weights matrix stability was improved of the ELM algorithm between neurons in hidden layer and output layer connection. Using PSO algorithm to obtain the optimal input weights and threshold of the hidden layer neurons，on the basis，the PSO-RELM algorithm model was set up，and comparing with BP，ELM，RELM algorithm. Experimental results showed that PSO-RELM had a high recognition accuracy，not only for the intact peanut（100%），but also for the damage peanut（96. 71%），average test time was 0. 006 8 s，root mean square error was 0. 052 0，determination coefficient was 0. 987 4，which can meet the real.time requirements for peanut seeds.

Key words: peanut seeds selection, color segmentation, extreme learning machine, regularization parameter, particle swarm optimization

摘要：

针对花生种子人工筛选存在工作量大、效率低等的问题，提出一种基于颜色分割和改进 ELM的花生种子筛选算法。根据花生图像的聚类特性，采用限定 RGB和 HSV颜色空间中颜色范围的方法对花生图像进行颜色分割，获取花生种子图像目标区域。采用颜色、形状、改进 HU矩特征对花生图像进行描述，结合改进 HU矩平移、旋转和缩放不变性，对提取到的花生图像特征进行数量扩充，获得花生图像数据集。采用黄金分割法，确定隐含层神经元个数。引入正则化参数，提高 ELM算法隐含层神经元与输出层之间连接权值矩阵的稳定性；采用 PSO算法，获取最优输入权值和隐含层神经元阈值，构建 PSO-RELM算法模型，并与 BP、ELM、RELM算法进行比较。试验结果表明，PSO-RELM算法不仅对完好花生有很高的识别准确率（100%），还对破损花生也有很高的识别准确率（96. 71%），平均测试时间为 0. 006 8 s，均方根误差为 0. 052 0，决定系数达 0. 987 4，能够满足花生种子筛选的实时性要求。

关键词: 花生种子筛选, 颜色分割, 极限学习机, 正则化参数, 粒子群算法

CLC Number:

Yang Li, Xue Yaxu, Li Pengfei, Peng Xinjie. Research on peanut seeds selection based on color segmentation and PSO-RELM algorithm[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(9): 89-96.

杨丽, 薛亚许, 李鹏飞, 彭信杰. 基于颜色分割和 PSO-RELM算法的花生种子筛选研究[J]. 中国农机化学报, 2024, 45(9): 89-96.

References

［ 1］申志超，赵志衡，卢雷，等 .基于颜色分割与 GA-SVM的花生表皮破损识别［ J］.中国粮油学报， 2021，36（3）： 140-147.

Shen Zhichao， Zhao Zhiheng， Lu Lei， et al. Peanut′s cuticle damage recognition based on color segmentation and GA-SVM［J］. Journal of the Chinese Cereals and Oils Association，2021，36（3）：140-147.

［ 2］韩仲志，赵友刚 .基于计算机视觉的花生品质分级检测研究［ J］.中国农业科学， 2010，43（18）：3882-3891.

Han Zhongzhi，Zhao Yougang. Quality grade detection in peanut using computer vision［J］. Scientia Agricultura Sinica，2010，43（18）：3882-3891.

［ 3］张永超，赵录怀，卜光苹 .基于卷积神经网络的花生种子筛选识别算法［ J］.江西农业学报， 2020，32（1）：77-82.

Zhang Yongchao，Zhao Luhuai，Bu Guangping. Screening and recognition algorithm of peanut seed based on convolutional neural network［J］. Acta Agriculturae Jiangxi，2020，32（1）：77-82.

［ 4］赵志衡，宋欢，朱江波，等 .基于卷积神经网络的花生籽粒完整性识别算法及应用［ J］.农业工程学报， 2018，34（21）：195-201.

Zhao Zhiheng， Song Huan， Zhu Jiangbo， et al. Identification algorithm and application of peanut kernel integrity based on convolution neural network［J］. Transactions of the Chinese Society of Agricultural Engineering，2018，34（21）：195-201.

［ 5］Yang H，Ni J，Gao J，et al. A novel method for peanut variety identification and classification by improved VGG16［J］. Scientific Reports，2021，11（1）：1-17.

［ 6］Zou Z，Wang L，Chen J，et al. Research on peanut variety classification based on hyperspectral image［J］. Food Science and Technology，2022，42.

［ 7］Yu H，Erasmus S W，Wang Q，et al. Rapid classification of peanut varieties for their processing into peanut butters based on near.infrared spectroscopy combined with machine learning［J］. Journal of Food Composition and Analysis， 2023：105348.

［ 8］Balasubramaniyan M， Navaneethan C. Color contour texture based peanut classification using deep spread spectral features classification model for assortment identification［J］. Sustainable Energy Technologies and Assessments，2022，54：102524.

［ 9］Huang G B， Zhu Q Y， Siew C K. Extreme learning machine： A new learning scheme of feedforward neural networks［C］. 2004 IEEE International Joint Conference On Neural Networks. IEEE，2004，2：985-990.

［10］Huang G B， Zhu Q Y， Siew C K. Extreme learning machine：Theory and applications［J］. Neurocomputing， 2006，70（1）：489-501.

［11］梁秀满，姚珊珊，牛福生，等 .基于 HSV颜色空间的矿物识别研究［ J］.有色金属（选矿部分），2022（6）：1-8. Liang Xiuman，Yao Shanshan，Niu Fusheng，et al. Study on color mineral recognition in HSV color space［J］. Nonferrous Metals（Mineral Processing Section）， 2022（6）：1-8.

［12］李祥光，赵伟，赵雷雷 .缺株玉米行中心线提取算法研究［J］.农业工程学报， 2021，37（18）：203-210.

Li Xiangguang， Zhao Wei， Zhao Leilei. Extraction algorithm of the center line of maize row in case of plants lacking［J］. Transactions of the Chinese Society of Agricultural Engineering，2021，37（18）：203-210.

［13］曹鹏辉，吕书强，汪万福，等 .基于光谱降维与 Hu矩的壁画颜料层脱落区域提取方法［ J］.图学学报， 2020，41（6）：930-938.

Cao Penghui， Lü Shuqiang， Wang Wanfu， et al. Extraction of mural paint loss regions based on spectral dimensionality reduction and Hu moment［J］. Journal of Graphics，2020，41（6）：930-938.

［14］蒲兴成，王涛，张毅 .基于改进 Hu矩算法的 Kinect手势识别［ J］.计算机工程， 2016，42（7）：165-172，180.

Pu Xingcheng， Wang Tao， Zhang Yi. Kinect gesture recognition based on improved Hu moment algorithm［J］. Computer Engineering，2016，42（7）：165-172，180.

［15］樊宇星，任妮，田港陆，等 .基于 DeepAR.RELM的池塘溶解氧时空预测方法研究［ J］.农业机械学报， 2020，51（S1）：405-412.

Fan Yuxing，Ren Ni，Tian Ganglu，et al. Spatio.temporal prediction method of dissolved oxygen in ponds based on DeepAR-RELM［J］. Transactions of the Chinese Society for Agricultural Machinery，2020，51（S1）：405-412.

［16］赵林锁，陈泽，丁琳琳，等 .基于 RELM的时间序列数据加权集成分类方法［ J］.计算机工程与科学， 2022，44（3）：545-553.

Zhao Linsuo，Chen Ze，Ding Linlin，et al. A weighted ensemble classification method for time series data based on regularized extreme learning machine［J］. Computer Engineering & Science，2022，44（3）：545-553.

［17］陈聪聪，李程 .基于 PSO.ELM算法的民航客运量预测［ J］.控制工程， 2022，29（11）：2042-2047.

Chen Congcong，Li Cheng. Passenger traffic forecast of civil aviation based on PSO.ELM algorithm［J］. Control Engineering of China，2022，29（11）：2042-2047.

［18］周彦，王山亮，杨威，等 .基于 PSO-ELM的卫星导航欺骗式干扰检测［J］.导航定位与授时， 2022，9（5）：153-161.

Zhou Yan，Wang Shanliang，Yang Wei，et al. Deceptive jamming detection of satellite navigation based on PSO-ELM［J］. Navigation Positioning and Timing， 2022，9（5）：153-161.

［19］洪艳，潘东方，姚海峰，等 .基于黄金分割搜索的光伏阵列最大功率点跟踪方法［ J］.合肥工业大学学报（自然科学版），2014，37（4）：416-419，443.

Hong Yan，Pan Dongfang，Yao Haifeng，et al. Method of photovoltaic array maximum power point tracking based on golden section search［J］. Journal of Hefei University of Technology（Natural Science），2014，37（4）：416-419，443.

[1]	Zou Yuhang, Wang Mingfei, Zhang Xin, Wang Lichun, Wei Xiaoming, Zheng Wengang. Control method of factory mushroom room air conditioning based on model predictive control [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 98-105.
[2]	Wang Hongxuan, Yu Zhenzhen, Li Hailiang, Wang Chun, Yan Xiaoli, Zou Huafen. Fresh corn yield prediction based on GA-BP neural network [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(6): 156-162.
[3]	Wei Peili, Lu Linfei, Huang Yiqi. Research on tractor ABS based on IPSO-PID special road pneumatic braking system [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(12): 99-106.
[4]	Li Jingzhu, Liu Qiuju, Wang Zhongying, . Prediction of soil fertilizer for optimizing extreme learning machine based on improved SSA algorithm [J]. Journal of Chinese Agricultural Mechanization, 2023, 44(10): 174-184.
[5]	Chen Yuanling, Jin Yaguang, Yan Mingyang, Chen Haonan. Gao Xiaoqing.. Decision support system for operation parameters of key components of sugarcane combine harvester [J]. Journal of Chinese Agricultural Mechanization, 2022, 43(8): 119-127.
[6]	Zhi Jinning, Jia Xufeng, Liu Chao, Xie Hu, Shi Qinglu.. Time optimal motion planning of threearm excavator under leveling condition [J]. Journal of Chinese Agricultural Mechanization, 2022, 43(11): 146-154.
[7]	Chai Shanpeng, Yao Lijian, Xu Lijun, Chen Qinhan, Xu Taotao, Yang Yankun. Research on greenhouse agricultural machinery path tracking based on dynamic look ahead distance pure pursuit model [J]. Journal of Chinese Agricultural Mechanization, 2021, 42(11): 58-64.