Login Register Cart 0
Generic placeholder image

Recent Patents on Engineering

Editor-in-Chief

ISSN (Print): 1872-2121
ISSN (Online): 2212-4047

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Research on Visual Inspection Method of Tree Whitening Quality based on Multi-level Feature Fusion

Author(s): Yangfan Cao, Wenchao Wang, Ying Zhao* and Qun Sun

Volume 18, Issue 3, 2024

Published on: 15 June, 2023

Article ID: e080523216685 Pages: 8

DOI: 10.2174/1872212118666230508163955

Price: $65

Abstract

Background: At present, the traditional manual whitewashing method is used in tree whitewashing in China. The quality of tree whitening can only be judged by the naked eye.

Objective: Up to now, the quality of tree whitewashing is still judged manually. In order to improve work efficiency, an automatic evaluation method of tree whitewashing quality based on multi-level feature fusion is proposed.

Methods: The images extract texture features from white-washed trees (gray-level co-occurrence matrix) and shape features (gradient direction histogram) from pixel-level fusion to obtain a global characteristic matrix. Using a support vector machine (SVM), random forests, and clustering algorithm (KNN), three classifiers were selected to identify the integration characteristics of the training test. In order to reduce the correlation of feature information and improve the execution efficiency of the classifier, the global feature matrix was optimized by combining principal component analysis (PCA) with pixel-level fusion and feature-level fusion.

Results: The experiment results showed that the classification accuracy of the support vector machine is 94.00%, which is higher than that of the random forest classifier (92.67) and KNN classifier (92.67%). Meanwhile, the support vector machine is superior to the other two classification algorithms in recall rate, accuracy rate, and algorithm execution efficiency. The results showed that the execution efficiency of each classification algorithm was improved after the optimization of the feature data. The support vector machine classification algorithm is more stable than the other two algorithms.

Conclusion: The feature fusion method combined with PCA can improve the execution efficiency and recognition precision of classifiers to a certain extent. For the feature matrix obtained by different data processing methods, the SVM classifier performs more stably and reliably than the random forest classifier and KNN in the inspection of tree whitening quality.

Graphical Abstract

[1]
Q. Chang, "Trunk whitening method to control pests and diseases", Deciduous Fruit Trees, vol. 47, no. 03, p. 64, 2015.
[2]
J. Lin, X. Song, and Y. Wang, "Automatic tree duster design", Value Eng., vol. 38, no. 32, pp. 153-154, 2019.
[3]
W. Yu., Research on multi-label text classification method for science and technology resources based on deep learning[D]. Uni. Electron. Sci. Technol, 2020, pp. 15-20.
[4]
Z. Hang, DU Zhilong, WU Zhanyuan, S. Cheng, GUO Nan, and Lin Yaling., Advances in the application of machine vision technology in the field of modern agricultural equipment[J]. China J. Agri. Chem., vol. 38, no. 11, pp. 86-92, 2020.
[5]
Y. Ying, W. Wei, C. Xuan, P. Feldner, and G. Heitschmidt, "Research on the detection of aflatoxin in maize based on hyperspectral imaging technique and factor discriminant analysis", J. Chin. Cereals Oils., vol. 29, no. 12, pp. 107-110+118, 2014.
[6]
Zhang Yajun., Research on image recognition of agricultural pests based on improved support vector machine algorithm[J]. Chinese Journal of Agricultural Chemistry, vol. 42. 2021, no. 02, pp. 146-152.
[7]
R. Zhu, X. Yan, and Q. Chen, "Research on excellent seed screening of soybean based on image recognition and convolutional neural network", Dadou Kexue, vol. 39, no. 02, pp. 189-197, 2020.
[8]
W. Yang, Y. Huai, and F. Zhang, "Grape seed classification based on Gabor and deep neural networks", J. Electron. Sci. Technol., vol. 49, no. 01, pp. 131-138, 2020.
[9]
Z.H.A.O. Yi, and L.I.U. Tangyou, "Research on field weed identification method based on convolutional neural network", Jisuanji Fangzhen, vol. 36, no. 04, pp. 440-444, 2019.
[10]
W. Jinxing, L. Xuemei, L. Shuangxi, Q. Zekun, X. Chunbao, and J. Hao, "Prediction of nitrogen content of apple tree leaves in each growth period based on combined color characteristics", J. Agric. Mechin., vol. 52, no. 10, pp. 272-281+376, 2021.
[11]
Yuan Jianghao, Chang Qing, Zhao Huiyi, and Tang Fang., Research on SVM-based classification method for grain mold prediction[J]. Chin. J. Cereals Oils, vol. 36, no. 9, pp. 138-144, 2021.
[12]
S. Yang, J. Xu, Y. Liu, T. Yang, W. Xie, and J. Li, "Paper-based colorimetric Hg~(2+) concentration discrimination based on SVM classification algorithm", Sensors and Microsystems, vol. 40, no. 11, pp. 13-16, 2021.
[13]
Z. Shi, W. Zhang, X. Feng, and B. Wang, "Support vector machine based classification of muscle electrical signals", Information Technology and Informatization, no. 08, pp. 175-177, 2021.
[14]
Z. Bo, "Human posture recognition based on HOG features and support vector machines", Electronic Testing, no. 21, pp. 59-61, 2021.
[15]
W. Guangyu, S. Jianguo, X. Fei, Z. Wen, L. Jiong, and C. Feixu, "A method for lithology prediction of random forests with unbalanced sample sets", Pet. Geophy. Explor., vol. 56, no. 04, pp. 679-687+669, 2021.
[16]
X. Jian, R. Qin, M. He, J. Liu, and F. Tang, "Application of improved random forest in Android malware detection", Comput. Appl. Eng. Educ., vol. 57, no. 03, pp. 130-136, 2021.
[17]
Zhang Xiongtao., Jiang Yunliang. Pan Xingguang, Hu Wenjun, Wang. Integrated TSK fuzzy classifier based on iterative fuzzy clustering algorithm with K-nearest neighbors and data dictionary [J]. J. Electron. Inform., vol. 42, no. 3, pp. 746-754, 2020.
[18]
J. Fu, W. Shi, and C. Cao, "A Chinese metaphorical phrase recognition method based on the combination of clustering and classification", J. Chinese. Inf., vol. 32, no. 02, pp. 22-28+49, 2018.
[19]
L. Chen, K. Wang, and W. Hui, "Research on wood texture classification based on BP neural networl", J. For. Eng., vol. 4, no. 01, pp. 40-42, 2007.
[20]
G.L. Du Yankai, L. Qiang, Z. Sen, and J. Zhang, "Information extraction of collapsed buildings from post-earthquake SAR images based on multi-texture feature fusion", Remote Sens., vol. 36, no. 04, pp. 865-872, 2021.
[21]
Wang W, Huang W, Yu H, and Tian X., Identification of Maize with Different Moldy Levels Based on Catalase Activity and Data Fusion of Hyperspectral Images [J]. Foods, vol. 11, no. 12, p. 1727, 2022.
[http://dx.doi.org/10.3390/foods11121727] [PMID: 35741924]
[22]
L. Zhu, W. Wang, J. Qin, K-H. Wong, K-S. Choi, and P-A. Heng, "Fast feature-preserving speckle reduction for ultrasound images via phase congruency", Signal Process., vol. 134, pp. 275-284, 2017.
[http://dx.doi.org/10.1016/j.sigpro.2016.12.011]
[23]
R. Yaping., Image based on kernel independent component analysis[D]. South China Uni. Technol., 2011.
[24]
F. Li, M.K. Chyu, J. Wang, and B. Tang, "Life grade recognition of rotating machinery based on Supervised Orthogonal Linear Local Tangent Space Alignment and Optimal Supervised Fuzzy C-Means Clustering", Measurement, vol. 73, pp. 384-400, 2015.
[http://dx.doi.org/10.1016/j.measurement.2015.05.025]
[25]
L Yingyun, X Zhongbiao, Y Peisheng, and Y Dongqin, Aerial image cloud detection based on principal component separation method[J]. Mapping Spatial Geograph. Inform., vol. 44, no. 10, pp. 89-93, 2021.

Rights & Permissions Print Cite
© 2024 Bentham Science Publishers | Privacy Policy