Leaf image recognition based on layered convolutions neural network deep learning.
-
摘要: 深度学习已成为图像识别领域的研究热点。本文以植物叶片图像识别为研究对象,对单一背景和复杂背景图像分别给出了优化预处理方案;设计了一个8层卷积神经网络深度学习系统分别对Pl@antNet叶片库和自扩展的叶片图库中33 293张简单背景和复杂背景叶片图像进行训练和识别,并与传统基于植物叶片多特征的识别方法进行了比较分析。实验证明:本文提供的CNN+SVM和CNN+Softmax分类器识别方法对单一背景叶片图像识别率高达91.11%和90.90%,识别复杂背景叶片图像的识别率也能高达34.38%,取得了较好的识别效果。利用本文实现的分层卷积深度学习识别系统在数据量大而无法做出更多优化的情况下,叶片图像的识别率更高,尤其是针对复杂背景下的叶片图像,取得了极佳的识别效果。Abstract: Deep learning has been recently becoming research hotspot in the field of image recognition. In this study, plant leaf images were used as recognition objects. Plant leaf images were divided into single and complex background and were treated by using image segmentation method. We design a deep learning system which includes eight layers of Convolution Neural Network (CNNs) to identify leaf images. And then the deep learning system was tested with 33 293 leaf sample images which come from Pl@antNet libraries and our extending leaf libraries for image training and recognition. Compared with the traditional identification methods, the classifier provided in this paper has achieved better recognition effect. For CNN+SVM and CNN+Softmax recognition system, the simple background leaf recognition rate reaches 91.11% and 90.90%, and the recognition rate of complex background reaches 34.38%. The system has higher recognition rate for the large amount of leaf images with no more optimization, and has a higher recognition rate especially for the recognition of complex background images.
-
Keywords:
- plant recognition /
- leaf image /
- feature extraction /
- SVM /
- deep learning
-
-
[1] WANG L J, HUAI Y J, PENG Y C. Method of identification of foliage from plants based on extraction of multiple features of leaf images[J]. Journal of Beijing Forestry University, 2015, 37(1):55-61.
[1] 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. [2] 杨天天,潘晓星,穆立蔷. 基于叶片图像特征数字化信息识别7种柳属植物[J]. 东北林业大学学报,2014,42(12):75-79. [3] YANG T T, PAN X X, MU L Q.Identification of seven Salix species using digital information analysis of leaf image characteristics[J]. Journal of Northeast Forestry University, 2014,42(12):75-79.
[4] 张宁, 刘文萍. 基于克隆选择算法和K近邻的植物叶片识别方法[J]. 计算机应用, 2013,33(7) : 2009-2013. [5] ZHANG N, LIU W P.Plant leaf recognition method based on clonal selection algorithm and K nearest neighbor[J]. Journal of Computer Applications, 2013,33(7):2009-2013.
[6] 邓立苗,唐俊,马文杰. 基于图像处理的玉米叶片特征提取与识别系统[J]. 中国农机化学报,2014,35(6):72-75,79. [7] DENG L M, TANG J, MA W J.Feature extraction and recognition system of maize leaf based on image processing[J]. Journal of Chinese Agricultural Mechanization, 2014, 35(6): 72-75,79.
[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. [9] ZHAI C M, WANG Q P, DU J X. Plant leaf recognition method based on fractal dimension feature of outline and venation[J]. Computer Science, 2014,41(2):170-173.
[10] 邹秋霞,郜鲁涛,盛立冲. 基于Android手机和图像特征识别技术的植物叶片分类系统的研究[J]. 安徽农业科学,2015,43(11):367-369. [11] ZOU Q X, GAO L T, SHENG L C.Study on plant leaves classification system based on android mobile phone and image feature recognition technology[J]. Journal of Anhui Agricultural Sciences, 2015,43(11):367-369.
[12] VILLENA-ROMN J, LANA-SERRANO S, CRISTBAL J C G. Daedalus at ImageCLEF 2011 plant identification task: using SIFT keypoints for object detection[C]∥Conference and Labs of the Evaluation forum 2011. Amsterdam: Clef Labs Workshop, 2011.
[13] 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.
[14] GHAZI M M, YANIKOGLU B, APTOULA E, et al. Sabanci-okan system in LifeCLEF 2015 plant identification competition[C]∥Conference and Labs of the Evaluation forum 2015. [2015-10-20]. http:∥ceur-ws.org/Vol-1391/43-CR.pdf.
[15] YANIKOGLU B, APTOULA E, TIRKAZ C. Sabanci-okan system at ImageClef 2012: combining features and classifiers for plant identification[C]∥Conference and Labs of the Evaluation forum 2012. Rome: Clef, 2012.
[17] OTSU N. An automatic threshold selection method based on discriminate and least squares criteria[J]. Denshi Tsushin Gakkai Ronbunshi, 1979, 63:349-356.
[18] BOSCH A, ZISSERMAN A, MUOZ X. Image classification using random forests and Ferns[C]∥IEEE International Conference on Computer Vision. Rio de Janeiro:IEEE, 2007:1-8.
[19] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25(2):1106-1114.
[20] LCUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[22] LECUN Y, BENGIO Y, HINTON G. Deep learning.[J]. Nature, 2015, 521:436-444.
[23] LYU S, SIMONCELLI E P. Nonlinear image representation using divisive normalization[C]∥IEEE Conference on Computer Vision and Pattern Recognition. Anchorage:IEEE, 2008:1-8.
[24] GOLD S, RANGARAJAN A. Softmax to softassign: neural network algorithms for combinatorial optimization[J]. Journal of Artificial Neural Networks, 1995, 2(4):381-399.
[25] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报,2000,26(1):32-42. [26] ZHANG X G. Introduction to statistical learning theory and support vector machines[J]. Acta Automatica Sinica, 2000,26(1):32-42.
[28] HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets [J]. Neural Computation, 2006, 18(7):1527-1554.
-
期刊类型引用(6)
1. 赵尧，付伟莲，关惠元. T型圆竹家具构件力学性能研究. 林产工业. 2024(10): 42-46 . 
百度学术
2. 朱旭，吴新凤，郝景新，徐大鹏. 无框瓦楞夹芯板极限抗拔力及家具角部结合性能的研究. 林产工业. 2024(11): 20-25 . 百度学术
3. 马青原，王华. 板式家具五金件的发展与应用. 家具. 2023(04): 7-10+6 . 百度学术
4. 陈炳睿，胡文刚. 一种可拆装式椭圆榫节点的设计与性能分析. 木材科学与技术. 2022(02): 65-70+86 . 百度学术
5. 胡强利，纪佳俊，冉雪蕾，王梦蕾. 杨木和辐射松树脂浸渍材金属空套螺母抗拔力研究. 中国人造板. 2022(06): 16-20 . 百度学术
6. 胡文刚，白珏，关惠元. 一种速生材榫接合节点增强方法. 北京林业大学学报. 2017(04): 101-107 . 本站查看
其他类型引用(10)
计量
- 文章访问数: 3014
- HTML全文浏览量: 345
- PDF下载量: 102
- 被引次数: 16
下载:
