Abstract: A binarizationbased Faster R-CNN （Binary Faster R-CNN） region detection neural network model is proposed for the study of citrus leaf disease detection and recognition techniques in natural scenarios. The improved model transforms the original Faster R-CNN fully connected layer neural network into a binary, fully convolutional neural network. The experimental results showed that the average recognition rate of the model was 87.2%, 87.6%, 89.8%, 86.4%, and 86.6% for black spot, ulcer, citrus_greening, scab, and healthy leaves of citrus, respectively, and the overall average recognition rate of the model was 87.5%. The recognition speed of the model was improved by 0.53 s compared with the Faster R-CNN network, and the detection time up to 0.31 s per image. The model size was reduced to 153 MB, and the floatingpoint computational power was 2.58×109, while the model converged quickly, ensuring the effectiveness of detection and robustness of the model. The method has good recognition speed and robustness for citrus leaf disease detection in complex natural environments and is of great research significance for citrus disease prevention.

Key words:  Faster R-CNN, Binary Faster R-CNN, binary network, object detection, citrus, diseases and insect pests

摘要： 为研究在自然场景下柑橘叶片病害检测和识别技术，提出一种基于二值化的Faster R-CNN（Binary Faster R-CNN）区域检测神经网络模型。改进模型将原始的Faster R-CNN全连接层神经网络转变为二进制全卷积神经网络。试验结果表明，该模型对柑橘的黑斑病、溃疡病、黄龙病、疮痂病、健康叶片的平均准确率分别为87.2%、87.6%、89.8%、86.4%和86.6%，总平均准确率为87.5%；模型识别时间相较于Faster R-CNN网络提高0.53 s，每幅图像的检测时间为0.31 s，模型大小缩小到15.3 MB，FLOPs为2.58×109；同时在保证模型检测有效性的情况下可快速收敛。该方法对复杂自然环境下的柑橘叶片病害检测具有较好的识别速度和鲁棒性，对柑橘类疾病预防有重要的研究意义。

关键词: Faster R-CNN, Binary Faster R-CNN, 二进制网络, 目标检测, 柑橘, 病虫害