基于卷积神经网络的国兰种类识别系统
Chinese Orchid Species Recognition System Based on Convolutional Neural Network

DOI: 10.12677/CSA.2020.1012248, PP. 2346-2353

Keywords: 国兰，Inception-ResNet-v2网络，图像识别，Android
Chinese Orchid, Inception-Resnet-V2 Network, Image Identification, Android

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对兰花品种众多，外表相似，导致没法准确识别兰花的种类这一问题，本文构建了基于卷积神经网络的国兰识别模型，设计并实现了模型在移动端的应用。文中通过多种途径完成常见国兰数据集的创建，进而以Inception-ResNet-v2为卷积神经网络预训练模型，使用迁移学习技术完成模型训练，并基于Android平台完成系统的开发和测试。测试结果显示，对传统国兰图像分类识别准确率达到91.51%。
Aiming at the problem that there are many varieties of orchids with similar appearances, which makes it impossible to accurately identify the types of orchids, a Chinese orchid recognition model based on convolutional neural network is constructed, and its transplantation to the mobile terminal is designed and implemented. First, this paper completes the creation of the common Chinese orchid data set through multiple channels, and then uses the Inception-ResNet-v2 convolutional neural network as the pretraining model, uses the transfer learning technology to complete the model construction, and develops and tests the system based on the Android platform. Through experiments and actual tests, the accuracy of classification and recognition of traditional Chinese orchid images reached 91.51%.

References

[1]	邵伟丽. 福建省野生兰科植物种质资源调查与保育策略研究[D]: [硕士学位论文]. 福州: 福建农林大学, 2008.
[2]	Szegedy, C., Ioffe, S., Vanhoucke, V., et al. (2016) Inception-v4, Inception-ResNet and the Impact of Re-sidual Connections on Learning. Thirty-First AAAI Conference on Artificial Intelligence, 4278-4284.
[3]	He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Com-puter Vision and Pattern Recognition, Las Vegas, NV, 770-778. https://doi.org/10.1109/CVPR.2016.90
[4]	杨明欣, 张耀光, 刘涛. 基于卷积神经网络的玉米病害小样本识别研究[J/OL]. 石家庄: 中国生态农业学报(中英文): 1-9. https://doi.org/10.13930/j.cnki.cjea.200375, 2020-11-19.
[5]	汤烨, 陆卫忠, 陈成, 等. 基于Adam算法和神经网络的照度计算方法[J]. 照明工程学报, 2019, 30(2): 50-54.
[6]	郭子琰, 舒心, 刘常燕, 等. 基于ReLU函数的卷积神经网络的花卉识别算法[J]. 计算机技术与发展, 2018, 28(5): 154-157.
[7]	周毅敏, 陈榕. Dalvik虚拟机进程模型分析[J]. 计算机技术与发展, 2010, 20(2): 83-86.
[8]	Sivkov, S., Novikov, L., Romanova, G., et al. (2020) The Algorithm Development for Operation of a Computer Vision System via the OpenCV Library. Procedia Computer Science, 169, 662-667. https://doi.org/10.1016/j.procs.2020.02.193
[9]	岳智慧. Android平台上的细分插值算法研究[D]: [硕士学位论文]. 郑州: 郑州大学, 2019.
[10]	李群. 基于OkHttp的文件传输设计与实现[J]. 电子技术与软件工程, 2018(13): 180-181.

Full-Text