基于稻穗几何形态模式识别的在穗籽粒数估测
|
摘要
基于稻穗几何形态特征和在穗籽粒数二者之间的映射关系,提出基于稻穗图像形态学特征机器学习的在穗籽粒测量新方法.首先,利用图像处理方法提取一次枝梗的面积、骨架长度、周长、骨架距离均值等形态特征.其次,针对一次枝梗识别,提出基于局部距离方差的提取方法,获取一次枝梗骨架.最后,使用改进的支持向量机构建稻穗几何形态特征和在穗籽粒数两者之间的映射关系.实验结果表明,用以上特征训练的分类器,预测稻穗籽粒数的相对误差平均值为6.72%,可以有效解决测量在穗籽粒数时遇到的遮挡和粘连问题.研究结果表明,稻穗形态学特征与在穗籽粒数存在确定性内蕴映射关系,该映射能够被多分类集成支持向量机训练策略描述,且识别精度高于现有回归方法.
The seed number of panicle is an important index of crop breeding. Manual measurement is with a low efficiency, and the automatic counting method based on the traditional image segmentation algorithm is difficult to solve the occlusion and adhesion problems of panicle seeds. Based on the mapping relationship between panicle morphological features and panicle seed numbers, this paper puts forward a new method to measure panicle seed numbers using image morphological features and machine learning algorithm. Firstly, the image processing method is used to extract the morphological features of the primary branch, such as area, perimeter, skeleton length, mean distance on skeleton. Secondly, aiming to the primary branch recognition, this paper puts forward a method based on the local distance deviation. Thirdly, a mapping relationship is constructed between the seed numbers and panicle morphological features using an improved support vector machine(SVM) classifier. The experimental results show that the classifier trained by above features gives 6.72% average relative error for panicle seed numbers prediction, hence the method can effectively solve the occlusion and adhesion problems. The results show that the panicle morphology features and the panicle seed numbers exists deterministic intrinsic mapping relationship which can be described by multi-class SVM training strategy, and the recognition accuracy is higher than the existing regression method.
The seed number of panicle is an important index of crop breeding. Manual measurement is with a low efficiency, and the automatic counting method based on the traditional image segmentation algorithm is difficult to solve the occlusion and adhesion problems of panicle seeds. Based on the mapping relationship between panicle morphological features and panicle seed numbers, this paper puts forward a new method to measure panicle seed numbers using image morphological features and machine learning algorithm. Firstly, the image processing method is used to extract the morphological features of the primary branch, such as area, perimeter, skeleton length, mean distance on skeleton. Secondly, aiming to the primary branch recognition, this paper puts forward a method based on the local distance deviation. Thirdly, a mapping relationship is constructed between the seed numbers and panicle morphological features using an improved support vector machine(SVM) classifier. The experimental results show that the classifier trained by above features gives 6.72% average relative error for panicle seed numbers prediction, hence the method can effectively solve the occlusion and adhesion problems. The results show that the panicle morphology features and the panicle seed numbers exists deterministic intrinsic mapping relationship which can be described by multi-class SVM training strategy, and the recognition accuracy is higher than the existing regression method.
引文
[1]REBOLLEDO M C, PE?A A L, JORGE D, et al. Combining image analysis, genome wide association studies and different field trials to reveal stable gene-tic regions related to panicle architecture and the number of spikelets per panicle in rice[J]. Frontiers in Plant Science, 2016, 7:1384.
[2]WENG X, WANG L, WANG J, et al. Grain number, plant height, and heading date7 is a central re-gulator of growth, development, and stress response[J]. Plant Physiology, 2014, 164(2):735.
[3]CROWELL S, FALCAO A X, SHAH A, et al. High-resolution inflorescence phenotyping using a novel image-analysis pipeline, panorama[J]. Plant Physiology, 2014, 165(2):479-495.
[4]HUANG C L, YANG W N, DUAN L F, et al. Rice panicle length measuring system based on dual-camera imaging[J]. Computers&Electronics in Agriculture, 2013, 98:158-165.
[5]GUO W, FUKATSU T, NINOMIYA S. Automated characterization of flowering dynamics in rice using field-acquired time-series rgb images[J]. Plant me-thods, 2015, 11(1):7.
[6]MA Z, MAO Y, GONG L, et al. Smartphone-based visual measurement and portable instrumentation for crop seed phenotyping[J]. Ifac Papersonline, 2016, 49(16):259-264.
[7]GRANIER C, AGUIRREZABAL L, CHENV K, et al. PHENOPSIS, an automated platform for reproducible phenotyping of plant responses to soil water deficit in Arabidopsis thaliana permitted the identification of an accession with low sensilivity to water deficit[J]. New Phytologist, 2006, 169(3):623-635.
[8]ADAGALE S S, PAWAR S S. Image segmentation using PCNN and template matching for blood cell counting[C]//IEEE International Conference on Computational Intelligence and Computing Research. Madurai:IEEE, 2013:1-5.
[9]李小龙,马占鸿,孙振宇,等.基于图像处理的小麦条锈病菌夏孢子模拟捕捉的自动计数[J].农业工程学报, 2013, 29(2):199-206. LI Xiaolong, MA Zhanhong, SUN Zhenyu, et al. Automatic counting for trapped urediospores of Puccinia striiformis f. sp. tritici based on image processing[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(2):199-206.
[10]ALTAM F, ADAM H, ANJOS A D, et al. P-TRAP:A panicle trait phenotyping tool[J]. Bmc Plant Biology, 2013, 13(1):122.
[11]许杰,周子力,潘大宇,等.水稻穗部籽粒参数快速无损获取方法研究[J].计算机工程与应用, 2017, 53(8):203-208. XU Jie, ZHOU Zili, PAN Dayu, et al. Study on fast and nondestructive method of rice grain parameters acquisition of rice panicle[J]. Computer Engineering and Applications, 2017, 53(8):203-208.
[12]赵三琴,李毅念,丁为民,等.稻穗结构图像特征与籽粒数相关关系分析[J].农业机械学报, 2014, 45(12):323-328. ZHAO Sanqin, LI Yinian, DING Weimin, et al. Relative analysis between image characteristics of panicle structure and spikelet number[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(12):323-328.
[13]SCHARR H, MINERVINI M, KLUKAS C, et al. Leaf segmentation in plant phenotyping:A collation study[J]. Machine Vision&Applications, 2016, 27(4):1-22.
[14]NAVARRO P J, FERNANDO P, JULIA W, et al. Machine learning and computer vision system for phenotype data acquisition and analysis in plants[J]. Sensors, 2016, 16(5):641.
[15]NASERI M, HEIDARI S, GHEIBI R, et al. A novel quantum binary images thinning algorithm:A quantum version of the Hilditch’s algorithm[J]. Optik-International Journal for Light and Electron Optics, 2017, 131:678-686.
[16]MAJI S, BERG A C, MALIK J. Efficient classification for additive kernel svms[J]. IEEE Transactions on Pattern Analysis&Machine Intelligence, 2013, 35(1):66-77.
[17]YUAN M S, YANG Z J, HUANG G Z, et al. Feature selection by maximizing correlation information for integrated high-dimensional protein data[J]. Pattern Recognition Letters, 2017, 92:17-24.
[2]WENG X, WANG L, WANG J, et al. Grain number, plant height, and heading date7 is a central re-gulator of growth, development, and stress response[J]. Plant Physiology, 2014, 164(2):735.
[3]CROWELL S, FALCAO A X, SHAH A, et al. High-resolution inflorescence phenotyping using a novel image-analysis pipeline, panorama[J]. Plant Physiology, 2014, 165(2):479-495.
[4]HUANG C L, YANG W N, DUAN L F, et al. Rice panicle length measuring system based on dual-camera imaging[J]. Computers&Electronics in Agriculture, 2013, 98:158-165.
[5]GUO W, FUKATSU T, NINOMIYA S. Automated characterization of flowering dynamics in rice using field-acquired time-series rgb images[J]. Plant me-thods, 2015, 11(1):7.
[6]MA Z, MAO Y, GONG L, et al. Smartphone-based visual measurement and portable instrumentation for crop seed phenotyping[J]. Ifac Papersonline, 2016, 49(16):259-264.
[7]GRANIER C, AGUIRREZABAL L, CHENV K, et al. PHENOPSIS, an automated platform for reproducible phenotyping of plant responses to soil water deficit in Arabidopsis thaliana permitted the identification of an accession with low sensilivity to water deficit[J]. New Phytologist, 2006, 169(3):623-635.
[8]ADAGALE S S, PAWAR S S. Image segmentation using PCNN and template matching for blood cell counting[C]//IEEE International Conference on Computational Intelligence and Computing Research. Madurai:IEEE, 2013:1-5.
[9]李小龙,马占鸿,孙振宇,等.基于图像处理的小麦条锈病菌夏孢子模拟捕捉的自动计数[J].农业工程学报, 2013, 29(2):199-206. LI Xiaolong, MA Zhanhong, SUN Zhenyu, et al. Automatic counting for trapped urediospores of Puccinia striiformis f. sp. tritici based on image processing[J]. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(2):199-206.
[10]ALTAM F, ADAM H, ANJOS A D, et al. P-TRAP:A panicle trait phenotyping tool[J]. Bmc Plant Biology, 2013, 13(1):122.
[11]许杰,周子力,潘大宇,等.水稻穗部籽粒参数快速无损获取方法研究[J].计算机工程与应用, 2017, 53(8):203-208. XU Jie, ZHOU Zili, PAN Dayu, et al. Study on fast and nondestructive method of rice grain parameters acquisition of rice panicle[J]. Computer Engineering and Applications, 2017, 53(8):203-208.
[12]赵三琴,李毅念,丁为民,等.稻穗结构图像特征与籽粒数相关关系分析[J].农业机械学报, 2014, 45(12):323-328. ZHAO Sanqin, LI Yinian, DING Weimin, et al. Relative analysis between image characteristics of panicle structure and spikelet number[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(12):323-328.
[13]SCHARR H, MINERVINI M, KLUKAS C, et al. Leaf segmentation in plant phenotyping:A collation study[J]. Machine Vision&Applications, 2016, 27(4):1-22.
[14]NAVARRO P J, FERNANDO P, JULIA W, et al. Machine learning and computer vision system for phenotype data acquisition and analysis in plants[J]. Sensors, 2016, 16(5):641.
[15]NASERI M, HEIDARI S, GHEIBI R, et al. A novel quantum binary images thinning algorithm:A quantum version of the Hilditch’s algorithm[J]. Optik-International Journal for Light and Electron Optics, 2017, 131:678-686.
[16]MAJI S, BERG A C, MALIK J. Efficient classification for additive kernel svms[J]. IEEE Transactions on Pattern Analysis&Machine Intelligence, 2013, 35(1):66-77.
[17]YUAN M S, YANG Z J, HUANG G Z, et al. Feature selection by maximizing correlation information for integrated high-dimensional protein data[J]. Pattern Recognition Letters, 2017, 92:17-24.