陈娟,陈良勇,王生生,赵慧颖,温长吉.基于改进残差网络的园林害虫图像识别[J].农业机械学报,2019,50(5):187-195.
CHEN Juan,CHEN Liangyong,WANG Shengsheng,ZHAO Huiying,WEN Changji.Pest Image Recognition of Garden Based on Improved Residual Network[J].Transactions of the Chinese Society for Agricultural Machinery,2019,50(5):187-195.
摘要点击次数: 1884
全文下载次数: 1189
基于改进残差网络的园林害虫图像识别   [下载全文]
Pest Image Recognition of Garden Based on Improved Residual Network   [Download Pdf][in English]
投稿时间:2018-11-02  
DOI:10.6041/j.issn.1000-1298.2019.05.022
中文关键词:  图像识别  害虫控制  残差网络  贝叶斯方法
基金项目:吉林省科技发展计划项目(20180101334JC、20190302117GX、20160520099JH)和吉林省发展改革委创新能力建设(高技术产业部分)项目(2019C053-3)
作者单位
陈娟 吉林大学 
陈良勇 吉林大学 
王生生 吉林大学 
赵慧颖 吉林大学 
温长吉 吉林农业大学 
中文摘要:针对北方园林害虫识别问题,提出了一种基于改进残差网络的害虫图像识别方法。首先,采用富边缘检测算法,将中值滤波、Sobel算子和Canny算子相结合,对害虫图像进行边缘检测;然后,改进残差网络中的残差块,通过添加卷积层和增加通道数提取更多的害虫图像特征,并将贝叶斯方法运用于改进后的网络中,优化超参数;最后,将预处理的害虫图像输入神经网络中,利用分块共轭算法优化网络权重。对38种北方园林害虫进行了识别,试验结果表明,在相同数据集下,与3种传统害虫识别方法相比,本文方法的平均识别准确率平均提高9.6个百分点,加权平均分数分别提高16.3、10.8、4.5个百分点。
CHEN Juan  CHEN Liangyong  WANG Shengsheng  ZHAO Huiying  WEN Changji
Jilin University,Jilin University,Jilin University,Jilin University and Jilin Agricultural University
Key Words:image recognition  pest control  residual network  Bayesian method
Abstract:Plant pest and disease is one of the three major natural disasters. Pest identification tends to consume a lot of labor, and it is difficult for naked eyes to quickly and accurately identify pest species. However, there still exist some drawbacks in the traditional deep learning algorithms for pest recognition, such as gradient explosion or gradient disappearance in deep neural networks, degradation and overfitting caused by limited sample size. In order to address these problems and improve the accuracy of pest recognition, a pest image recognition method based on improved residual network was proposed. Firstly, the pest images in the data set were converted to grayscale before edge detection was performed on them by using Rich edge. To obtain a fine lined pest image, the Rich edge was combined with median filtering, Sobel operator and Canny operator to detect the edges of the pest images. Among them, the median filter effectively eliminated the salt and pepper noise, the Sobel operator accurately detected the position information, and the Canny operator detected the weak edge. The images after edge detection were quantized to be 224pixel×224pixel for training and classification. Then the obtained pest image set was used to train the deep neural network, which was a variant of standard residual network with additional convolution layers and channels for extracting more image features. And the dropout layer was added to each residual block of the network to prevent overfitting when it was trained on a relatively small data set. Besides, the regularization hyper parameters of the network were designed to be optimized by Bayesian method which adaptively adjusted the size of the hyper parameters with the adjustment of weights during network training. The weights of the proposed network were optimized through the Block cg algorithm. In the optimization algorithm, the block diagonal was used to approximate the curvature matrix, which improved the convergence of the Hessian matrix; and independent conjugate gradient update was conducted for each sub block, which divided the whole issue into certain number of sub problems and reduced the complexity of local search. Eventually the values of the weights were not updated until an ideal pest classification accuracy rate was obtained. To verify the validity and robustness of the proposed method, an image data set of 38 common garden pests in north of China was collected and experiments were carried out on this data set. Experimental results empirically demonstrated that compared with the three traditional pest recognition methods for the same data set, the proposed method could make the recognition accuracy increase by 9.6 percentage points on average and the weighted average score increase by 16.3 percentage points, 10.8 percentage points and 4.5 percentage points, respectively.

Transactions of the Chinese Society for Agriculture Machinery (CSAM), in charged of China Association for Science and Technology (CAST), sponsored by CSAM and Chinese Academy of Agricultural Mechanization Science(CAAMS), started publication in 1957. It is the earliest interdisciplinary journal in Chinese which combines agricultural and engineering. It always closely grasps the development direction of agriculture engineering disciplines and the published papers represent the highest academic level of agriculture engineering in China. Currently, nearly 8,000 papers have been already published. There are around 3,000 papers contributed to the journal each year, but only around 600 of them will be accepted. Transactions of CSAM focuses on a wide range of agricultural machinery, irrigation, electronics, robotics, agro-products engineering, biological energy, agricultural structures and environment and more. Subjects in Transactions of the CSAM have been embodied by many internationally well-known index systems, such as: EI Compendex, CA, CSA, etc.

   下载PDF阅读器