融合矢量结构特征的复杂建筑物形状识别方法

doi:10.11947/j.AGCS.2026.20250445

测绘学报 ›› 2026, Vol. 55 ›› Issue (5): 838-849.doi: 10.11947/j.AGCS.2026.20250445

融合矢量结构特征的复杂建筑物形状识别方法

周旭升¹^,²^,³^,⁴(), 谭永滨¹^,²^,³^,⁴(), 于忠海⁵, 王维¹^,²^,³^,⁴, 肖青云²

^1.东华理工大学江西省流域生态过程与信息重点实验室，江西　南昌　330013
^2.东华理工大学测绘与空间信息工程学院，江西　南昌　330013
^3.东华理工大学自然资源部环鄱阳湖区域矿山环境监测与治理重点实验室，江西　南昌　330013
^4.东华理工大学南昌市景观过程与国土空间生态修复重点实验室，江西　南昌　330013
^5.济南市勘察测绘研究院，山东　济南　250101

收稿日期:2025-10-23 修回日期:2026-04-20 出版日期:2026-06-23 发布日期:2026-06-23
通讯作者: 谭永滨 E-mail:2022120416@ecut.edu.cn;tyb@ecut.edu.cn
作者简介:周旭升（2000—），男，硕士，研究方向为城市地理空间智能与空间信息可视化。　E-mail：2022120416@ecut.edu.cn
基金资助:
国家自然科学基金(42361067; 42261078)

A complex building shape recognition method integrating vector structural features

Xusheng ZHOU¹^,²^,³^,⁴(), Yongbin TAN¹^,²^,³^,⁴(), Zhonghai YU⁵, Wei WANG¹^,²^,³^,⁴, Qingyun XIAO²

^1.Jiangxi Key Laboratory of Watershed Ecological Process and Information, East China University of Technology, Nanchang 330013, China
^2.School of Surveying and Spatial Informatics Engineering, East China University of Technology, Nanchang 330013, China
^3.Key Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake of Ministry of Natural Resources, East China University of Technology, Nanchang 330013, China
^4.Nanchang Key Laboratory of Landscape Process and Territorial Spatial Ecological Restoration, East China University of Technology, Nanchang 330013, China
^5.Jinan Geotechnical Investigation and Surveying Research Institute, Jinan 250101, China

Received:2025-10-23 Revised:2026-04-20 Online:2026-06-23 Published:2026-06-23
Contact: Yongbin TAN E-mail:2022120416@ecut.edu.cn;tyb@ecut.edu.cn
About author:ZHOU Xusheng (2000—), male, master, majors in urban geospatial intelligence and spatial information visualization.　E-mail: 2022120416@ecut.edu.cn
Supported by:
The National Natural Science Foundation of China(42361067; 42261078)

摘要/Abstract

摘要：

建筑物形状识别与分类作为城市空间分析、智能制图与三维城市建模的关键环节，对高精度地图构建和智慧城市治理具有重要意义。然而，现有方法在应对复杂多样的建筑形态时仍面临显著挑战。基于人工定义几何特征的方法普遍存在泛化能力不足的问题；而采用栅格化处理的方法则容易引入几何失真，难以准确保留建筑矢量轮廓的拓扑结构与精细特征。为此，本文提出一种面向矢量建筑物轮廓的端到端自动特征学习方法。该方法将建筑轮廓抽象为角点图结构，以实现建筑物轮廓的结构化表示；并设计结构特征模块嵌入图卷积网络（GCN）中，用于捕获凹凸转折、分支等形态特征，从而增强模型对复杂几何结构的判别能力。试验结果显示，该方法在公开及其扩展数据集上的准确率分别为99.20%和99.03%，Kappa系数均超过0.989，展现出优异的性能。试验误判分析表明，模型混淆主要集中于几何或拓扑高度相似的类别（如E/U形、X/O形），反映出其在细粒度结构建模与全局语义融合方面仍有提升空间。本文为矢量建筑轮廓的高精度识别提供了一种无须人工特征、具备良好泛化性的解决方法。

关键词: 建筑物形状分类, 矢量轮廓, 图神经网络, 自动特征学习, 城市空间分析

Abstract:

Building shape recognition and classification serve as pivotal components in urban spatial analysis, intelligent cartography, and 3D city modeling, playing a critical role in high-precision map construction and smart city governance. However, existing approaches still face significant challenges when dealing with the complex and diverse morphologies of buildings. Methods based on handcrafted geometric features often suffer from limited generalization capability, while rasterization-based approaches tend to introduce geometric distortions and struggle to preserve the topological structure and fine details of vectorized building outlines. To address these issues, this paper proposes an end-to-end automatic feature learning framework tailored for vectorized building contours. The method represents building outlines as corner-point graph structures to achieve a structured representation of building shapes. Furthermore, a dedicated structural feature module is integrated into a graph convolutional network (GCN) to effectively capture morphological characteristics such as concave-convex transitions and branching patterns, thereby enhancing the model's discriminative power for complex geometric structures. Experimental results demonstrate that the proposed method achieves classification accuracies of 99.20% and 99.03% on public and extended datasets, respectively, with Kappa coefficients exceeding 0.989, indicating superior performance. Error analysis reveals that misclassifications primarily occur between geometrically or topologically highly similar categories (e.g., E/U-shaped or X/O-shaped buildings), suggesting room for improvement in fine-grained structural modeling and global semantic integration. This study provides a robust, fully automatic, and generalizable solution for high-precision recognition of vectorized building contours without reliance on manual feature engineering.

Key words: building shape classification, vector outline, graph neural network, automatic feature learning, urban spatial analysis

中图分类号:

P208

周旭升, 谭永滨, 于忠海, 王维, 肖青云. 融合矢量结构特征的复杂建筑物形状识别方法[J]. 测绘学报, 2026, 55(5): 838-849.

Xusheng ZHOU, Yongbin TAN, Zhonghai YU, Wei WANG, Qingyun XIAO. A complex building shape recognition method integrating vector structural features[J]. Acta Geodaetica et Cartographica Sinica, 2026, 55(5): 838-849.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://xb.chinasmp.com/CN/10.11947/j.AGCS.2026.20250445

http://xb.chinasmp.com/CN/Y2026/V55/I5/838

图/表 14

图1

图2

图3

图4

表1

图5

表2

表3

表4

表5

表6

表7

图6

图7

参考文献 37

[1]	晏雄锋, 袁拓, 杨敏, 等. 建筑物形状特征分析表达与自适应化简方法[J]. 测绘学报, 2022, 51(2): 269-278. DOI: . doi: 10.11947/j.AGCS.2022.20210302
	YAN Xiongfeng, YUAN Tuo, YANG Min, et al. An adaptive building simplification approach based on shape analysis and representation[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(2): 269-278. DOI: . doi: 10.11947/j.AGCS.2022.20210302
[2]	苏友能, 徐青, 孙群, 等. 邻近边约束下的建筑物自动合并方法[J]. 测绘学报, 2025, 54(3): 563-576. DOI: . doi: 10.11947/j.AGCS.2025.20240138
	SU Youneng, XU Qing, SUN Qun, et al. A method for automatic buildings aggregation constrained by proximity edges[J]. Acta Geodaetica et Cartographica Sinica, 2025, 54(3): 563-576. DOI: . doi: 10.11947/j.AGCS.2025.20240138
[3]	刘昌振, 马威, 马红, 等. 建筑物轮廓方向计算和规则化的向量重组算法[J]. 测绘学报, 2023, 52(9): 1584-1594. DOI: . doi: 10.11947/j.AGCS.2023.20220082
	LIU Changzhen, MA Wei, MA Hong, et al. Vector reconstruction algorithm for building footprints orientation calculation and regularization[J]. Acta Geodaetica et Cartographica Sinica, 2023, 52(9): 1584-1594. DOI: . doi: 10.11947/j.AGCS.2023.20220082
[4]	ZHUO Li, SHI Qingli, ZHANG Chenyang, et al. Identifying building functions from the spatiotemporal population density and the interactions of people among buildings[J]. ISPRS International Journal of Geo-Information, 2019, 8(6): 247.
[5]	DENG Yingbin, CHEN Renrong, YANG Ji, et al. Identify urban building functions with multisource data: a case study in Guangzhou, China[J]. International Journal of Geographical Information Science, 2022, 36(10): 2060-2085.
[6]	YAN Xiongfeng, AI Tinghua, YANG Min, et al. A graph convolutional neural network for classification of building patterns using spatial vector data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 150: 259-273.
[7]	WANG Chaofeng, YU Qian, LAW K H, et al. Machine learning-based regional scale intelligent modeling of building information for natural hazard risk management[J]. Automation in Construction, 2021, 122: 103474.
[8]	AFZAL S, ZIAPOUR B M, SHOKRI A, et al. Building energy consumption prediction using multilayer perceptron neural network-assisted models; comparison of different optimization algorithms[J]. Energy, 2023, 282: 128446.
[9]	CHEN Hongxing, WU Bin, YU Bailang, et al. A new method for building-level population estimation by integrating LiDAR, nighttime light, and POI data[J]. Journal of Remote Sensing, 2021, 2021: 9803796.
[10]	GARTNER G. Underpinning aspects of developing a cartographic curriculum[J]. Journal of Geodesy & Geoinformation Science, 2022, 5(3): e0001.
[11]	MENG L. Proliferation of cartographic education in the age of big data[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(3): 7.
[12]	张自强, 刘涛. 图注意力神经网络支持下的建筑物形状识别[J]. 测绘科学, 2024, 49(9): 125-133.
	ZHANG Ziqiang, LIU Tao. Building shape recognition supported by graph attention networks[J]. Science of Surveying and Mapping, 2024, 49(9): 125-133.
[13]	晏雄锋, 艾廷华, 杨敏. 居民地要素化简的形状识别与模板匹配方法[J]. 测绘学报, 2016, 45(7): 874-882. DOI: . doi: 10.11947/j.AGCS.2016.20150162
	YAN Xiongfeng, AI Tinghua, YANG Min. A simplification of residential feature by the shape cognition and template matching method[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(7): 874-882. DOI: . doi: 10.11947/j.AGCS.2016.20150162
[14]	李驿言. 顾及局部特征的大比例尺建筑物化简方法[D]. 兰州: 兰州交通大学, 2023.
	LI Yiyan. Simplification methods for large-scale buildings considering local features[D]. Lanzhou: Lanzhou Jiatong University, 2023.
[15]	师尚杰, 李文德, 闫浩文, 等. 图对比学习支撑下的矢量建筑物形状相似性度量[J]. 地球信息科学学报, 2024, 26(12): 2659-2672.
	SHI Shangjie, LI Wende, YAN Haowen, et al. Vector buildings shape similarity measure supported by graph contrastive learning[J]. Journal of Geo-information Science, 2024, 26(12): 2659-2672.
[16]	LI Qingyu, MOU Lichao, SUN Yao, et al. A review of building extraction from remote sensing imagery: geometrical structures and semantic attributes[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 4702315.
[17]	ALIDOOST F, AREFI H. A CNN-based approach for automatic building detection and recognition of roof types using a single aerial image[J]. PFG-Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 2018, 86(5): 235-248.
[18]	PARTOVI T, FRAUNDORFER F, AZIMI S, et al. Roof type selection based on patch-based classification using deep learning for high resolution satellite imagery[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017, XLII-1/W1: 653-657.
[19]	焦洋洋, 刘平芝, 刘爱龙, 等. AlexNet支持下的地图建筑物形状分类方法[J]. 地球信息科学学报, 2022, 24(12): 2333-2341.
	JIAO Yangyang, LIU Pingzhi, LIU Ailong, et al. Map building shape classification method based on AlexNet[J]. Journal of Geo-information Science, 2022, 24(12): 2333-2341.
[20]	YAN Xiongfeng, AI Tinghua, YANG Min, et al. Graph convolutional autoencoder model for the shape coding and cognition of buildings in maps[J]. International Journal of Geographical Information Science, 2021, 35(3): 490-512.
[21]	于洋洋, 贺康杰, 武芳, 等. 面状居民地形状分类的图卷积神经网络方法[J]. 测绘学报, 2022, 51(11): 2390-2402. DOI: . doi: 10.11947/j.AGCS.2022.20210134
	YU Yangyang, HE Kangjie, WU Fang, et al. Graph convolution neural network method for shape classification of areal settlements[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(11): 2390-2402. DOI: . doi: 10.11947/j.AGCS.2022.20210134
[22]	ZHANG Ya, LIU Jiping, WANG Yong, et al. Graph isomorphism network with weighted multi-aggregators for building shape classification[J]. Transactions in GIS, 2024, 28(6): 1883-1904.
[23]	张付兵, 孙群, 马京振, 等. 融合全局和局部特征的建筑物形状智能分类方法[J]. 测绘学报, 2024, 53(9): 1842-1852. DOI: . doi: 10.11947/j.AGCS.2024.20240040
	ZHANG Fubing, SUN Qun, MA Jingzhen, et al. An intelligent classification method for building shape based on fusion of global and local features[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(9): 1842-1852. DOI: . doi: 10.11947/j.AGCS.2024.20240040
[24]	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. [2025-10-29]. https://arxiv.org/abs/1609.02907.
[25]	HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 770-778.
[26]	VELICKOVIC P, CUCURULL G, CASANOVA A, et al. Graph attention networks[C]//Proceedings of 2018 International Conference on Learning Representations. [S.l.]: IEEE, 2018.
[27]	HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[EB/OL]. [2025-10-29]. https://arxiv.org/abs/1706.02216.
[28]	XU K, HU Weihua, LESKOVEC J, et al. How powerful are graph neural networks?[EB/OL]. [2025-10-29]. https://arxiv.org/abs/1810.00826.
[29]	WU F, SOUZA A, ZHANG T, et al. Simplifying graph convolutional networks[C]//Proceedings of 2019 International Conference on Machine Learning. [S.l.]: PMLR, 2019: 6861-6871.
[30]	NT H, MAEHARA T, MURATA T. Revisiting graph neural networks: graph filtering perspective[C]//Proceedings of the 25th International Conference on Pattern Recognition. Milan: IEEE, 2021: 8376-8383.
[31]	LI Guohao, MULLER M, THABET A, et al. DeepGCNs: can GCNs go as deep as CNNs?[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2019: 9266-9275.
[32]	WANG Yifan, LUO Xiao, CHEN Chong, et al. DisenSemi: semi-supervised graph classification via disentangled representation learning[J]. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(5): 8192-8204.
[33]	YING R, YOU Jiaxuan, MORRIS C, et al. Hierarchical graph representation learning with differentiable pooling[C]//Proceedings of 2018 Neural Information Processing Systems. [S.l.]: IEEE, 2018.
[34]	XIE Yu, LIANG Yanfeng, GONG Maoguo, et al. Semisupervised graph neural networks for graph classification[J]. IEEE Transactions on Cybernetics, 2023, 53(10): 6222-6235.
[35]	AMOUZAD A, DEHGHANIAN Z, SARAVANI S, et al. Graph isomorphism U-net[J]. Expert Systems with Applications, 2024, 236: 121280.
[36]	XU Yuhua, WANG Junli, GUANG Mingjian, et al. Graph multi-convolution and attention pooling for graph classification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(12): 10546-10557.
[37]	WU Z, ZHANG Z, FAN J. Graph convolutional kernel machine versus graph convolutional networks[J]. Advances in Neural Information Processing Systems, 2023, 36: 19650-19672.

形状	数量	形状	数量
E形	500	U形	500
F形	500	Y形	500
H形	500	Z形	500
I形	500	K形	507
L形	500	X形	532
O形	500	++形	500
T形	500

真实	公共	扩展	真实	公共	扩展	真实	公共	扩展
L	I	\	U	L	\	K	\	++
E	F	U	E	\	U	T	\	F
Z	L	\	E	\	U	Y	\	T
O	I	I	L	\	F	H	\	T
O	U	\	E	\	Z	L	\	U
Y	H	\	++	\	X	X	\	O
Y	U	F	I	\	O	K	\	F
U	E	\	++	\	X	L	\	I
I	L	\	X	\	O	E	\	F

模型	公共数据集				扩展数据集
模型	准确率/（%）	精确率/（%）	F₁值/（%）	Kappa系数	准确率/（%）	精确率/（%）	F₁值/（%）	Kappa系数
本文模型	99.20	99.20	99.20	0.991 1	99.03	99.05	99.03	0.989 5
GCN^[25]	92.13	92.15	92.12	0.912 6	95.11	95.18	95.12	0.947 0
GAT^[26]	93.21	93.26	93.20	0.922 8	94.58	94.63	94.59	0.939 8
GraphSAGE^[27]	94.33	94.34	94.32	0.937 0	95.77	95.87	95.78	0.954 2
GIN^[28]	94.07	94.10	94.07	0.934 1	95.72	95.78	95.73	0.953 6
SGC^[29]	91.27	91.40	91.25	0.903 0	92.81	92.83	92.80	0.922 1
GFNN^[30]	91.67	91.71	91.66	0.909 6	92.76	92.89	92.77	0.921 6
DeepGCN^[31]	93.60	93.69	93.60	0.928 9	94.70	94.71	94.68	0.942 6
DisenSemi^[32]	90.27	90.54	90.31	0.891 9	92.05	92.20	92.07	0.913 9
DiffPool^[33]	77.07	79.00	77.23	0.745 2	78.80	80.26	78.71	0.770 3
SemiGraph^[34]	91.20	91.24	91.17	0.902 2	94.70	94.78	94.71	0.942 6
GIUnet^[35]	80.87	81.02	80.85	0.787 4	85.98	86.16	85.96	0.848 2
GMCAP^[36]	87.33	87.27	87.22	0.859 3	91.08	91.16	91.08	0.903 4
GCKM^[37]	67.87	69.45	68.09	0.643 0	71.05	72.55	70.95	0.686 4
MLP	74.47	74.64	74.44	0.716 3	80.33	80.29	80.24	0.786 9

模块组合	公共数据集				扩展数据集
模块组合	准确率/（%）	精确率/（%）	F₁值/（%）	Kappa系数	准确率/（%）	精确率/（%）	F₁值/（%）	Kappa系数
本文模型	99.20	99.20	99.20	0.991 1	99.03	99.05	99.03	0.989 5
无特征映射	98.67	98.68	98.67	0.985 2	98.98	98.99	98.98	0.989 0
无节点特征	97.60	97.64	97.60	0.973 3	98.62	98.64	98.62	0.985 1
无结构特征	95.67	95.75	95.68	0.951 9	95.82	95.87	95.87	0.958 7
无平均聚合	98.73	98.74	98.73	0.985 9	98.83	98.84	98.83	0.987 3
无最大聚合	98.13	98.16	98.14	0.979 3	97.96	97.98	97.96	0.977 9
无ResNet	97.00	97.05	97.00	0.966 7	97.60	97.61	97.61	0.974 0

卷积层数	公共数据集				扩展数据集
卷积层数	准确率/（%）	精确率/（%）	F₁值/（%）	Kappa系数	准确率/（%）	精确率/（%）	F₁值/（%）	Kappa系数
1	95.60	95.63	95.60	0.951 1	96.43	96.46	96.43	0.961 3
2	97.47	97.51	97.47	0.971 9	97.81	97.82	97.81	0.976 3
3	98.80	98.81	98.80	0.986 7	98.67	98.69	98.68	0.985 6
4	99.20	99.20	99.20	0.991 1	99.03	99.05	99.03	0.989 5
5	99.13	99.14	99.13	0.990 4	98.93	98.95	98.93	0.988 4

融合矢量结构特征的复杂建筑物形状识别方法

A complex building shape recognition method integrating vector structural features

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 37

相关文章 6

编辑推荐

Metrics

本文评价

真实	公共	扩展	真实	公共	扩展	真实	公共	扩展
L	I	\	U	L	\	K	\	++
E	F	U	E	\	U	T	\	F
Z	L	\	E	\	U	Y	\	T
O	I	I	L	\	F	H	\	T
O	U	\	E	\	Z	L	\	U
Y	H	\	++	\	X	X	\	O
Y	U	F	I	\	O	K	\	F
U	E	\	++	\	X	L	\	I
I	L	\	X	\	O	E	\	F

卷积层维度	公共数据集				扩展数据集
卷积层维度	准确率/（%）	精确率/（%）	F₁值/（%）	Kappa系数	准确率/（%）	精确率/（%）	F₁值/（%）	Kappa系数
32	91.33	91.51	91.31	0.903 7	93.27	93.33	93.25	0.927 1
64	98.27	98.28	98.27	0.980 7	98.52	98.54	98.53	0.984 0
128	99.20	99.20	99.20	0.991 1	99.03	99.05	99.03	0.989 5
256	98.87	98.87	98.87	0.987 4	98.93	98.94	98.93	0.988 4
512	99.07	99.07	99.07	0.989 6	98.47	98.48	98.47	0.983 4

试验区	10类				13类
试验区	准确率/（%）	精确率/（%）	F₁值/（%）	Kappa系数	准确率/（%）	精确率/（%）	F₁值/（%）	Kappa系数
济南市中心区	93.78	93.89	93.46	0.882 6	94.56	94.73	94.27	0.897 2
厦门岛	93.58	93.67	93.48	0.899 6	95.45	95.55	95.32	0.928 5

[1]	张付兵, 孙群, 徐青, 马京振, 黄文君, 陈若虚. 随机森林和图神经网络支持下的河系自动分级与选取方法[J]. 测绘学报, 2025, 54(9): 1697-1711.
[2]	黄哲琨, 钱海忠, 蔡中祥, 王骁, 王俊威, 孔令辉. 基于图神经网络的多尺度网状河系分类匹配方法[J]. 测绘学报, 2025, 54(2): 371-384.
[3]	唐佳怡, 童晓冲, 邱春平, 雷亚现, 雷毅, 宋好帅. 基于场景图的遥感场景检索方法[J]. 测绘学报, 2025, 54(1): 123-135.
[4]	张付兵, 孙群, 马京振, 孙士杰, 温伯威. 融合全局和局部特征的建筑物形状智能分类方法[J]. 测绘学报, 2024, 53(9): 1842-1852.
[5]	孔博, 艾廷华, 杨敏, 吴昊, 余华飞, 肖天元. 等高线形态知识与图神经网络联合作用下的黄土地貌类型识别[J]. 测绘学报, 2024, 53(6): 1154-1164.
[6]	陈占龙, 鲁谢春, 徐永洋. 基于图顶点深度聚类的建筑物合并方法[J]. 测绘学报, 2024, 53(4): 736-749.

真实	公共	扩展	真实	公共	扩展	真实	公共	扩展
L	I	\	U	L	\	K	\	++
E	F	U	E	\	U	T	\	F
Z	L	\	E	\	U	Y	\	T
O	I	I	L	\	F	H	\	T
O	U	\	E	\	Z	L	\	U
Y	H	\	++	\	X	X	\	O
Y	U	F	I	\	O	K	\	F
U	E	\	++	\	X	L	\	I
I	L	\	X	\	O	E	\	F

真实	公共	扩展	真实	公共	扩展	真实	公共	扩展
L	I	\	U	L	\	K	\	++
E	F	U	E	\	U	T	\	F
Z	L	\	E	\	U	Y	\	T
O	I	I	L	\	F	H	\	T
O	U	\	E	\	Z	L	\	U
Y	H	\	++	\	X	X	\	O
Y	U	F	I	\	O	K	\	F
U	E	\	++	\	X	L	\	I
I	L	\	X	\	O	E	\	F