【摘要】 以自然环境下采集到的生姜病害图片为基础,对炭疽病、姜瘟病、根结线虫病和白星病进行研究分析,提出一种基于卷积神经网络的生姜病害识别系统。首先是对收集来的图片进行二值化和轮廓分割等预处理,从而增强数据的可靠性。其次,将处理后的图像数据交由优化后的卷积神经网络模型进行分析、学习,并在Caffe框架下进行模拟仿真。最后,在已训练好的网络模型基础上利用Qt软件设计人机交互界面,从而达到数据可视化提高系统使用的便捷性。结果表明优化后的模型识别率达到了96%,可以较好地预测和识别生姜的相关病害。更多还原

【Abstract】 Based on the images of ginger diseases collected in natural environment,anthracnose,ginger blast,root knot nematode and white star disease were studied and analyzed.A ginger disease recognition system based on convolution neural network was proposed.Firstly,the collected images were pre-processed by binarization and contour segmentation,so as to enhance the reliability of the data.Secondly,the processed image data were handed over to the optimized convolutional neural network model for analysis and learning,and simulated in the framework of Caffe.Finally,on the basis of the trained network model,it was used Qt software to design human-computer interaction interface,so as to achieve data visualization and improve the convenience of the system.The results showed that the recognition rate of the optimized model reached 96%.The system can better predict and identify the related diseases of ginger.更多还原