浏览全部资源
扫码关注微信
Received：03 April 2019，
Revised：2019-5-30，
Accepted：06 June 2019，
Published：16 December 2019
移动端阅览
目的
2
研究不同植物形态之间的相似度是有效区分植物种类或科属的一个重要依据。目前的植物形态相似度计算方法，大多只考虑了植物拓扑结构或者外围轮廓等几何形状方面的相似性，而未涉及叶片颜色、冠层叶片的稠密状态及株型的松散状态等因素。因此，基于植物图像的形状特征和颜色特征，本文提出一种基于图像特征的植物形态相似度计算方法。
方法
2
首先，获取图像的轮廓特征和区域特征。轮廓特征用植物枝条的松散程度表示，具体包括植物的高宽比、轮廓四边形和第1个1级侧枝的高度；区域特征用叶片稠密度表示，计算叶片所占整个包围矩形面积的比例。其次，获取图像的颜色特征，使用基于HSV和YUV颜色空间的颜色直方图，统计图像的颜色分布。最后，利用信息熵分析数据的离散程度，据此确定各部分对应的权重大小，加权得到总体的相似度值。
结果
2
实验在人工采集的数据集上进行，得出松散度、稠密度和颜色对应的权重分别为0.62、0.17和0.21。在此基础上得到的相似度计算结果符合实际，可以有效度量植物之间的相似程度。同时，将提出的算法应用于图像检索，并与常见的5种方法进行比较。实验得出该算法查准率都在0.747 7以上。在同一查准率水平下，相比于其他方法，查全率也都处于较高水平。尤其在相似度阈值大于0.8时，查准率可以达到0.910 8以上。另外，该方法对植物图像缩放不敏感，同类植物的相似度依然接近于1。
结论
2
本文提出的植物形态相似度算法，结合了形状特征和颜色特征，计算结果符合人的视觉感受。与其他方法相比，可以更有效区分植物种类或科属。算法主要适用于背景单一的单株植物图像，可为研究植物形态的相似性提供技术参考。
Objective
2
Plants are one of the common natural landscapes in our daily lives
and they are an important part of natural scene modeling. Different plants have different morphological characteristics. Consequently
measuring the similarity among plants is a key problem to be resolved in the fields of plant classification
variety identification
storage
and retrieval of 3D plant models. The similarity of plant morphology is studied in this work to distinguish plant species effectively. The current method only considers the similarity of geometrical shapes
such as plant topology or edge contour. Plant topology describes the similarity between their structure and the distribution of organs
while edge contour describes the similarity of the edge contour of the plants. However
these methods do not consider intuitive factors
such as the color of the leaves
dense state of the canopy
and loose state of the plant type. This limitation results in a lack of accuracy because geometry and color are the main basis for distinguishing plant species. Therefore
this work proposes a method to calculate plant morphology similarity based on image features
particularly the shape and color characteristics of plant images.
Method
2
First
the shape features of an image
which include contour and regional features
are obtained. The contour features are expressed by the looseness of the plant shoots
which include the aspect ratio of the plant
the boundary quadrilateral
and the height of the lowest primary branch. The plant's aspect ratio describes the ratio of overall height to width of a plant. The boundary quadrilateral describes the border of the furthest point of a plant and constrains the plant's morphological distribution. The height of the lowest primary branch describes the starting position of the branch of a plant and claims the position of the canopy. The basic peripheral contour features of a plant can be described with the combination of these factors. The method will calculate the ratio of the height to width of the plant and the four internal angles of the boundary quadrilateral using the boundary points of the plant outline. The lowest primary branch of the plant will then be found
and the proportion of the height of the branch to the height of the entire plant will be calculated. The regional features are reflected in the density of the leaves
and the proportion of the surrounding rectangles of the leaves is calculated. Second
the color features of the images are obtained
in which the color histograms based on the HSV and YUV color spaces are used. The color spaces are divided into seven levels according to hue. Each level is subdivided into five levels according to the gray level. The proportion of each color section of the image is calculated to construct a 2D color matrix. Finally
appropriate weight-setting strategies are needed because the proportion of the various features in the overall similarity is different and the empirical knowledge is lacking. A high degree of data dispersion leads to a large difference among species. Specifically
obvious discrimination of the attribute value results in a considerable influence of the factor on the comprehensive evaluation result and a large corresponding weight. Otherwise
a small corresponding weight will be obtained. The degree of dispersion of the data reflects the uncertainty in the data. In information theory
entropy is used to measure uncertainty. Therefore
information entropy is used to identify the weight of each separate
and the weighting is used to obtain the overall similarity.
Result
2
An experiment is conducted on a manually collected data set. After the experiment
the weights of the looseness
density
and color are set to 0.62
0.17
and 0.21
respectively. In common plant species
the similarity calculation results are in line with reality
which can effectively distinguish plant species and measure the similarity among plants. The proposed algorithm is also applied to image retrieval. The precision of the algorithm is above 0.747 7. Under the same precision level
the recall rate is higher than the results of five ordinary methods. Especially when the similarity threshold is larger than 0.8
the precision can reach 0.910 8 or more
and the recall rate remains higher than that of other methods at the same precision level. The proposed algorithm is insensitive to plant image scaling
and the similarity of similar plants remains close to 1.
Conclusion
2
A plant morphology similarity algorithm that combines shape and color features is proposed in this work. The results of plant morphology similarity are in line with those of human visual perception. Compared with other methods
the proposed algorithm can distinguish plant species more effectively. The algorithm is mainly applied to a single plant image with a plain background
which can provide a new idea for studying the similarity of plant morphology.
Akl A and Yaacoub C. 2018. Tensor-space similarity measure for image analysis//Proceedings of the 25th International Conference on Systems, Signals and Image Processing. Maribor: IEEE: 1-5[ DOI:10.1109/IWSSIP.2018.8439205 http://dx.doi.org/10.1109/IWSSIP.2018.8439205 ]
Albanesi M G, Amadeo R, Bertoluzza S and Maggi G. 2018. A new class of wavelet-based metrics for image similarity assessment. Journal of Mathematical Imaging and Vision, 60(1):109-127[DOI:10.1007/s10851-017-0745-1]
Bougueroua S and Boucheham B. 2015. GLI-Color: gradual locality integration of color features for image retrieval//Proceedings of International Conference on Intelligent Information Processing, Security and Advanced Communication. Batna: ACM: 1-5[ DOI:10.1145/2816839.2816920 http://dx.doi.org/10.1145/2816839.2816920 ]
Ding W L, Wu S S, Max N, Wu F L and Xu L F. 2015. A calculation method of plant similarity giving consideration to different plant features. Journal of Theoretical Biology, 387:136-143[DOI:10.1016/j.jtbi.2015.09.015]
Dong H X. 2013. Researches on classification of plant leaves based on images. Changsha: Hunan University
董红霞. 2013.基于图像的植物叶片分类方法研究.长沙: 湖南大学[ DOI:10.7666/d.Y2358415 http://dx.doi.org/10.7666/d.Y2358415 ]
Emms M and Franco-Penya H H. 2013. On the expressivity of alignment-based distance and similarity measures on sequences and trees in inducing orderings//Latorre-Carmona P, Sánchez J, Fred A. Mathematical Methodologies in Pattern Recognition and Machine Learning. New York: Springer: 1-18[ DOI:10.1007/978-1-4614-5076-4_1 http://dx.doi.org/10.1007/978-1-4614-5076-4_1 ]
Ferraro P and Godin C. 2000. A distance measure between plant architectures. Annals of Forest Science, 57(5-6):445-461[DOI:10.1051/forest:2000134]
Gao X Y, Hoi S C H, Zhang Y D, Zhou J S, Wan J, Chen Z Y, Li J T and Zhu J K. 2017. Sparse online learning of image similarity//Proceedings of ACM Transactions on Intelligent Systems and Technology. New York: ACM: 1-22[ DOI:10.1145/3065950 http://dx.doi.org/10.1145/3065950 ]
Hu V H, Huu Q N and Thu H N T. 2012. Content based image retrieval with bin of color histogram//Proceedings of 2012 International Conference on Audio, Language and Image Processing. Shanghai: IEEE: 20-25[ DOI:10.1109/ICALIP.2012.6376580 http://dx.doi.org/10.1109/ICALIP.2012.6376580 ]
Huang J H, Li X W, Chen B H and Yang D Q. 2017. A comparative study on image similarity algorithms based on Hash. Journal of Dali University, 2(12):32-37
黄嘉恒, 李晓伟, 陈本辉, 杨邓奇. 2017.基于哈希的图像相似度算法比较研究.大理大学学报, 2(12):32-37[DOI:10.3969/j.issn.2096-2266.2017.12.007]
Küppers M. 1984. Carbon relations and competition between woody species in a central European hedgerow. I. Photosynthetic characteristics. Oecologia, 64(3):332-343[DOI:10.1007/BF00379130]
Li B, Wang N, Wang M H and Li L. 2010. In-field pineapple recognition based on monocular vision. Transactions of the CSAE, 26(10):345-349
李斌, Wang N, 汪懋华, 李莉. 2010.基于单目视觉的田间菠萝果实识别.农业工程学报, 26(10):345-349[DOI:10.3969/j.issn.1002-6819.2010.10.057]
Li Q, You X, Li K and Tang F. 2017. Geography image similarity measurement method based on adaptive weighting of similarity matrix. Pattern Recognition and Artificial Intelligence, 30(11):1003-1011
李钦, 游雄, 李科, 汤奋. 2017.基于相似矩阵自适应加权的实景图像相似度计算方法.模式识别与人工智能, 30(11):1003-1011[DOI:10.16451/j.cnki.issn1003-6059.201711005]
Liu F C, Wang S H, Wang J R, Pan Z G and Yi C. 2016.3D model retrieval based on fuzzy correspondences and hybrid shape features//Proceedings of 2016 International Conference on Virtual Reality and Visualization. Hangzhou: IEEE: 358-363[ DOI:10.1109/ICVRV.2016.67 http://dx.doi.org/10.1109/ICVRV.2016.67 ]
Liu S F. 2010. Grey System Theory and Applications. 5th ed. Beijing:Science Press:63
刘思峰. 2010.灰色系统理论及其应用. 5版.北京:科学出版社:63
Martinek M, Grosso R and Greiner G. 2015. Interactive partial 3D shape matching with geometric distance optimization. The Visual Computer, 31(2):223-233[DOI:10.1007/s00371-014-1040-4]
Peng M Y, Wang J H, Wen X X and Cong X Y. 2018. Shoreline detection method by combining HSV spatial water image feature. Journal of Image and Graphics, 23(4):526-533
彭明阳, 王建华, 闻祥鑫, 丛晓奕. 2018.结合HSV空间的水面图像特征水岸线检测.中国图象图形学报, 23(4):526-533[DOI:10.11834/jig.170498]
Pu H Y, Fei G L, Zhao H L, Hu G M, Jiao C B and Xu Z J. 2017. Short text similarity calculation using semantic information//Proceedings of the 3rd International Conference on Big Data Computing and Communications. Chengdu: IEEE: 144-150[ DOI:10.1109/BIGCOM.2017.53 http://dx.doi.org/10.1109/BIGCOM.2017.53 ]
Pushpalatha G, Jyothi H, Nithya S and Shakuntala C. 2017. A review of discriminant analysis algorithms for face recognition using similarity measures//Proceedings of International Conference on Recent Advances in Electronics and Communication Technology. Bangalore: IEEE: 249-253[ DOI:10.1109/ICRAECT.2017.47 http://dx.doi.org/10.1109/ICRAECT.2017.47 ]
Sarkar R and Acton S T. 2016. Slide: saliency guided image dictionary and image similarity evaluation//Proceedings of 2016 IEEE International Conference on Image Processing. Phoenix: IEEE: 216-220[ DOI:10.1109/ICIP.2016.7532350 http://dx.doi.org/10.1109/ICIP.2016.7532350 ]
Shannon C E. 1948. A mathematical theory of communication. The Bell System Technical Journal, 27(4):623-656[DOI:10.1002/j.1538-7305.1948.tb00917.x]
Tao Y T and Zhou J. 2017. Automatic apple recognition based on the fusion of color and 3D feature for robotic fruit picking. Computers and Electronics in Agriculture, 142:388-396[DOI:10.1016/j.compag.2017.09.019]
Yang L N, Tang Y Y, Lu Y and Luo H W. 2015. A fractal dimension and wavelet transform based method for protein sequence similarity analysis. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 12(2):348-359[DOI:10.1109/TCBB.2014.2363480]
Zhang H T and Mao H P. 2009. Comparison of four methods for deciding objective weights of features for classifying stored-grain insects based on extension theory. Transactions of the Chinese Society of Agricultural Engineering, 25(1):132-136
张红涛, 毛罕平. 2009.四种客观权重确定方法在粮虫可拓分类中的应用比较.农业工程学报, 25(1):132-136[DOI:10.11975/j.issn.1002-6819.2009.01.027]
Zhang K Z. 1996. A constrained edit distance between unordered labeled trees. Algorithmica, 15(3):205-222[DOI:10.1007/BF01975866]
Zhou Y and Pang Q. 2012. Plant similarity analysis based on Fourier spectrum and its angular and radial features. Computer Systems and Applications, 21(11):161-164
周游, 庞全. 2012.傅里叶频谱径角特征的植物相似性.计算机系统应用, 21(11):161-164[DOI:10.3969/j.issn.1003-3254.2012.11.037]
Zhu L, Li Z B, Yang Z X, Li C, Wu J and Yue J. 2017. Internet eggplant image retrieval method and system based on mixed features. Transactions of the Chinese Society of Agricultural Engineering, 33(S1):177-183
朱玲, 李振波, 杨照璐, 李晨, 吴静, 岳峻. 2017.基于混合特征的互联网茄子图像检索方法与系统.农业工程学报, 33(S1):177-183[DOI:10.11975/j.issn.1002-6819.2017.z1.027]
Zou C M, Xue D, Guo S S and Zhao G H. 2016. Improved image similarity algorithm. Computer Science, 43(6):72-76
邹承明, 薛栋, 郭双双, 赵广辉. 2016.一种改进的图像相似度算法.计算机科学, 43(6):72-76[DOI:10.11896/j.issn.1002-137X.2016.6.015]
相关文章
相关作者
相关机构
京公网安备11010802024621
