首页 > 分享 > 基于卷积神经网络的菊花花型和品种识别

基于卷积神经网络的菊花花型和品种识别

花匠小妙招
2024-09-13 10:02

摘要: 菊花作为国内十大名花之一，具有极为重要的观赏价值和经济价值，表现为种类丰富、花样瓣形繁多的特点，这些特征对其智能识别和高效的管理带来很大挑战。目前菊花的识别和管理主要靠人工方式，效率不高。本文基于端到端的卷积神经网络技术，直接作用于菊花的原始图像数据，通过逐层进行特征学习，进而利用多层网络获取菊花的特征信息，从而避免了人工提取特征的困难和问题，在此基础上使用优化目标函数实现菊花花型的高效、智能识别。针对菊花花型之间差别细微的特点，在细粒度上实现区分相同花型和不同花型的目标函数，系统不仅能够识别菊花花型，还能给出菊花所属的概率值和该花型涵盖的菊花品种。系统的实现分为离线训练和在线识别2个阶段，训练处的模型可以离线托管在云端以便在移动环境下使用。为了训练网络模型，采集了大量的菊花图像样本，并手工标注了相关的花型和类别信息，在此数据集上，与现有的典型系统进行了对比试验，试验表明：系统平均识别率可以达到0.95左右，部分达到0.98，系统识别精度得到明显提升，除此之外系统还能提供更加详细的菊花种类信息，实现了的菊花花型和品种智能识别和高效管理，具有重要的理论和应用价值，为菊花的自动化管理提供了有力的手段。

Abstract: Abstract: Chrysanthemum is one of the top 10 traditional famous flowers in China, which has significant importance and great ornamental value and medicinal value. The chrysanthemum flowers are characterized by a large number of varieties and a wide range of petal shapes, which pose big challenges to their intelligent identification and efficient management. Currently, the identification and management of chrysanthemum mainly relies on the traditional manual way, and as a result, the efficiency is quite low. At the contemporary era, deep learning as a powerful technique in artificial intelligence field is becoming a prevalent way of identification and classification on text, image, video, and so on. Based on the end-to-end convolutional neural network deep neural network directly acting on the original chrysanthemum image dataset, this paper aims at obtaining the characteristic information of chrysanthemums through the multi-layer neural network. By this means, the problem of extracting the features manually is avoided, and then optimization target function is applied to achieve a better image recognition accuracy. Based on this, the system of chrysanthemum flower pattern intelligent recognition and breed classification is researched and implemented. In view of the subtle differences among the flower patterns of chrysanthemums, on the one hand, in order to preserve as much information as possible for the data, tensor is employed to represent the image data; on the other hand, the pairwise confusion loss function based on pair similarity is used to distinguish pattern differences and similarities. By this means, the objective function of distinguishing the different flower patterns is realized on the fine grain size. The system not only can identify the chrysanthemum pattern, but also can give the probability value of the top 3 results. In addition to this, the variety information covered by the flower pattern is also provided. The operation of the system can be divided into 2 stages: the off-line training and the online classification. Off-line models can be hosted in the cloud environment such as Amazon AWS for the easy usage on the mobile platform. Moreover, the model can be replanted and updated with little hindrance. In order to train the network model, we collected a large amount of data of real chrysanthemum image, and manually marked the relevant pattern and category information of chrysanthemum. Based on the datasets, we conducted extensive experiments with our system and made comparisons with 3 existing systems, and experimental results show that: The identification accuracy of the system has been significantly improved compared with the existing systems for chrysanthemum flower pattern. Beyond that, the system can provide more detailed chrysanthemum species information at the same time. The average recognition rate can reach about 0.95, and even surpass the rate of 0.98 for some chrysanthemum patterns. The system provides a powerful means for the automatic management of chrysanthemum and fills the gaps in chrysanthemum pattern recognition and classification. In this paper, the research on the intelligent identification and effective management of chrysanthemum flower pattern has great significance in theory and practice.

[1] 付为琳，孙桂菊. 菊花的有效成分、功效、提取工艺及开发前景[J]. 食品工业科技，2008，29(3)：296－299.Fu Weilin Sun Guiju. The composition, effect, extraction and utilization of Chrysanthemum[J]. Science and Technology of Food Industry, 2008, 29(3): 296－299. (in Chinese with English abstract) [2] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 770－778. [3] 张帅，淮永建. 基于分层卷积深度学习系统的植物叶片识别研究[J]. 北京林业大学学报，2016，38(9)：108－115.Zhang Shuai, Huai Yongjian. Study on plant leaf recognition based on stratified convolution depth learning system[J]. Journal of Beijing Forestry University, 2016, 38 (9): 108－115. (in Chinese with English abstract) [4] CLEF Initiative[N/OL]. 2017[2017-07-25]. http://www.clef- initiative.eu/. [5] LifeCLEF 2017[N/OL]. 2017[2017-07-25]. http://www.imageclef. org/lifeclef/2017. [6] Backes A R, Casanova D, Bruno O M. A complex network- based approach for boundary shape analysis[J]. Pattern Recognition, 2009, 42(1): 54－67. [7] 龚丁禧，曹长荣. 基于卷积神经网络的植物叶片分类[J]. 计算机与现代化，2014，2014(4)：12－15.Gong Dingxi, Cao Changrong. Plant leaf classification based on CNN[J] .Computer & Modern, 2014, 2014(4): 12－15. (in Chinese with English abstract) [8] 翟传敏，汪青萍，杜吉祥. 基于叶缘与叶脉分数维特征的植物叶识别方法研究[J]. 计算机科学，2014，41(2)： 170－173.Zhai Chuanmin, Wang Qingping, Du Jixiang. Plant leaf recognition method based on fractai dimension Feature of outline and venation[J]. Computer Science, 2014, 41(2): 170－173. (in Chinese with English abstract) [9] 王丽君，淮永建，彭月橙. 基于叶片图像多特征融合的观叶植物种类识别[J]. 北京林业大学学报，2015，37(1)： 55－61.Wang Lijun, Huai Yongjian, Peng Yuecheng. Leaf image recognition based on layered convolutions neural network deep learning[J]. Journal of Beijing Forestry University, 2015, 37(1): 55－61. (in Chinese with English abstract) [10] 沈萍，赵备. 基于深度学习模型的花卉种类识别[J]. 科技通报，2017，33(3)：115－119.Shen Ping, Zhao Bei. Automatic classification of flowers based on deep learning model[J]. Bulletin of Science and Technology, 2017, 33(3): 115－119. (in Chinese with English abstract) [11] 微软识花[N/OL]. 2017 [2017-07-01]. https://www.microsoft. com/en-us/research/project/flowerreco-cn/. [12] 形色[N/OL].2017 [2017-06-10]. http://www.xingseapp.com/. [13] 看图识花[N/OL].2017 [2017-05-20]. http://stu.iplant.cn/web. [14] Garden Answers[N/OL]. 2017[2017-07-20]. http://www. gardenanswers.com/. [15] 孙志远，鲁成祥，史忠植，等. 深度学习研究与进展[J]. 计算机科学，2016，43(2)：1－8.Sun Zhiyuan, Lu Chengxiang, Shi Zhongzhi. et al. Research and advances on deep learning[J]. Computer Science. 2016, 43(2): 1－8. (in Chinese with English abstract) [16] Krizhevsky A, Sutskever I, Hinton G E. Image Net classification with deep convolutional neural networks[C]//International Conference on Neural Information Processing Systems. 2012: 1097－1105. [17] Neural Nets[DB/OL]. 2017[2017-07-28]. http://jhirniak.github. io/neural_nets/. [18] Yoon S, Yoon S. DeepCCI: End-to-end deep learning forchemical-chemical interaction prediction[C]//ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics. 2017: 203－212. [19] Ren S, He K, Girshick R, et al. Object detection networks on convolutional feature maps[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(7): 1476－1481. [20] Trigeorgis G, Ringeval F, Brueckner R, et al. Adieu features? End-to-end speech emotion recognition using a deep convolutional recurrent network[C]//IEEE International Conference on Acoustics, Speech and Signal Processing. 2016: 5200－5204. [21] Tang H, Wang W, Gimpel K, et al. End-to-end training approaches for discriminative segmental models[C]//Spoken Language Technology Workshop. 2016: 496－502. [22] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition. 2015: 3431－3440. [23] Dubey A, Gupta O, Guo P, et al. Training with confusion for fine-grained visual classification[J/OL]. 2017. https://arxiv. org/abs/1705.08016. [24] Hecht-Nielsen R. Theory of the backpropagation neural network[J]. Neural Networks, 1988, 1(Supplement-1): 445－448. [25] 杨琬琪，高阳，周新民，等. 多模态张量数据挖掘算法及应用[J]. 计算机科学，2012，39(1)：9－13.Yang Wanqi, Gao Yang, Zhou Xinmin, et al. Multi- modal tensor data mining algorithms and applications[J]. Computer Science., 2012, 39(1): 9－13. (in Chinese with English abstract) [26] Hassani S. Analysis of Tensors[M]//Switzerland: Springer International Publishing, 2013: 859-911. [27] AWS 云服务[EB/OL]. 2017[2017-05-10]. https://aws.amazon. com/cn. [28] Xu B, Wang N, Chen T, et al. Empirical evaluation of rectified activations in convolutional network[J/OL]. 2015. https://arxiv. org/abs/1505.00853. [29] Hinton G E, Srivastava N, Krizhevsky A, et al. Improving neural networks by preventing co-adaptation of feature detectors[J]. Computer Science, 2012, 3(4): 212－223. [30] Cai D, Chen K, Qian Y, et al. Convolutional low-resolution fine-grained classification[J/OL]. 2017. https://arxiv.org/abs/ 1703.05393. [31] Li M, Zhang T, Chen Y, et al. Efficient mini-batch training for stochastic optimization[C]//Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2014: 661－670. [32] tensorflow[EB/OL].2017 [2017-06-15]. https://www.tensorflow. org/.