Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (10): 3191-3199.DOI: 10.11772/j.issn.1001-9081.2023101496
• Multimedia computing and computer simulation • Previous Articles Next Articles
Cheng WANG1(), Yang WANG1, Yingjiao RONG2
Received:
2023-11-06
Revised:
2024-01-11
Accepted:
2024-01-17
Online:
2024-10-15
Published:
2024-10-10
Contact:
Cheng WANG
About author:
WANG Yang, born in 1998, M. S. His research interests include image processing, deep learningSupported by:
通讯作者:
王呈
作者简介:
王呈(1983—),男,江苏无锡人,副教授,博士,主要研究方向:非线性系统建模与控制、机器学习、数据挖掘 Wangc@jiangnan.edu.cnCLC Number:
Cheng WANG, Yang WANG, Yingjiao RONG. YOLOv7-MSBP target location algorithm for character recognition of power distribution cabinet[J]. Journal of Computer Applications, 2024, 44(10): 3191-3199.
王呈, 王炀, 荣英佼. 面向配电柜字符识别的YOLOv7-MSBP目标定位算法[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3191-3199.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2023101496
分支 | 初始锚框大小 | 本文锚框大小 |
---|---|---|
P2 | / | 4×5、8×10、22×18 |
P3 | 12×16、19×36、40×28 | 10×13、16×30、33×23 |
P4 | 36×75、76×55、72×146 | 30×61、62×45、59×119 |
P5 | 142×110、192×243、459×401 | 116×90、159×198、373×326 |
Tab. 1 Each branch anchor box setting
分支 | 初始锚框大小 | 本文锚框大小 |
---|---|---|
P2 | / | 4×5、8×10、22×18 |
P3 | 12×16、19×36、40×28 | 10×13、16×30、33×23 |
P4 | 36×75、76×55、72×146 | 30×61、62×45、59×119 |
P5 | 142×110、192×243、459×401 | 116×90、159×198、373×326 |
模型 | Recall | mAP@0.5 |
---|---|---|
YOLOv7(基线模型) | 0.886 | 0.889 |
YOLOv7+SENet | 0.892 | 0.894 |
YOLOv7+CBAM | 0.904 | 0.896 |
YOLOv7+ Syn-CBAM | 0.905 | 0.902 |
Tab. 2 Performance comparison of different attention mechanisms
模型 | Recall | mAP@0.5 |
---|---|---|
YOLOv7(基线模型) | 0.886 | 0.889 |
YOLOv7+SENet | 0.892 | 0.894 |
YOLOv7+CBAM | 0.904 | 0.896 |
YOLOv7+ Syn-CBAM | 0.905 | 0.902 |
模型 | 参数量/106 | GFLOPs | FPS/(frame·s-1) | 体积/MB |
---|---|---|---|---|
基线模型(Baseline) | 37.62 | 120.80 | 22.5 | 74.8 |
Baseline+DWConv | 34.55 | 98.70 | 19.1 | 65.3 |
Baseline+ELAN-PC | 32.86 | 84.70 | 30.3 | 60.2 |
YOLOv7-MSB | 40.42 | 148.70 | 17.7 | 82.3 |
YOLOv7-MSBP | 33.59 | 87.76 | 23.9 | 64.3 |
Tab. 3 Experimental comparison of model lightweight modules
模型 | 参数量/106 | GFLOPs | FPS/(frame·s-1) | 体积/MB |
---|---|---|---|---|
基线模型(Baseline) | 37.62 | 120.80 | 22.5 | 74.8 |
Baseline+DWConv | 34.55 | 98.70 | 19.1 | 65.3 |
Baseline+ELAN-PC | 32.86 | 84.70 | 30.3 | 60.2 |
YOLOv7-MSB | 40.42 | 148.70 | 17.7 | 82.3 |
YOLOv7-MSBP | 33.59 | 87.76 | 23.9 | 64.3 |
Micro-branch | BiFPN | Syn-CBAM | ELAN-PC | AP | mAP@0.5 | Precision | Recall | FPS | |||
---|---|---|---|---|---|---|---|---|---|---|---|
Label | Led | Point | Switch | ||||||||
0.979 | 0.910 | 0.992 | 0.676 | 0.889 | 0.897 | 0.886 | 22.5 | ||||
√ | 0.986 | 0.933 | 0.990 | 0.715 | 0.906 | 0.893 | 0.905 | 20.5 | |||
√ | √ | 0.986 | 0.934 | 0.990 | 0.713 | 0.906 | 0.894 | 0.905 | 30.2 | ||
√ | √ | 0.988 | 0.906 | 0.995 | 0.794 | 0.921 | 0.925 | 0.906 | 18.7 | ||
√ | √ | √ | 0.988 | 0.913 | 0.995 | 0.778 | 0.919 | 0.916 | 0.900 | 24.9 | |
√ | √ | √ | 0.985 | 0.934 | 0.991 | 0.830 | 0.935 | 0.888 | 0.940 | 17.7 | |
√ | √ | √ | √ | 0.983 | 0.938 | 0.995 | 0.812 | 0.932 | 0.914 | 0.930 | 23.9 |
Tab. 4 Ablation experimental results of power distribution cabinet character positioning model
Micro-branch | BiFPN | Syn-CBAM | ELAN-PC | AP | mAP@0.5 | Precision | Recall | FPS | |||
---|---|---|---|---|---|---|---|---|---|---|---|
Label | Led | Point | Switch | ||||||||
0.979 | 0.910 | 0.992 | 0.676 | 0.889 | 0.897 | 0.886 | 22.5 | ||||
√ | 0.986 | 0.933 | 0.990 | 0.715 | 0.906 | 0.893 | 0.905 | 20.5 | |||
√ | √ | 0.986 | 0.934 | 0.990 | 0.713 | 0.906 | 0.894 | 0.905 | 30.2 | ||
√ | √ | 0.988 | 0.906 | 0.995 | 0.794 | 0.921 | 0.925 | 0.906 | 18.7 | ||
√ | √ | √ | 0.988 | 0.913 | 0.995 | 0.778 | 0.919 | 0.916 | 0.900 | 24.9 | |
√ | √ | √ | 0.985 | 0.934 | 0.991 | 0.830 | 0.935 | 0.888 | 0.940 | 17.7 | |
√ | √ | √ | √ | 0.983 | 0.938 | 0.995 | 0.812 | 0.932 | 0.914 | 0.930 | 23.9 |
模型 | AP | mAP@0.5 | Precision | Recall | FPS | |||
---|---|---|---|---|---|---|---|---|
Label | Led | Point | Switch | |||||
YOLOv3[ | 0.977 | 0.804 | 0.986 | 0.333 | 0.775 | 0.744 | 0.792 | 17.7 |
YOLOv4-tiny | 0.974 | 0.000 142 | 0.873 | 0.018 4 | 0.466 | 0.475 | 0.467 | 87.6 |
Faster R-CNN | 0.985 | 0.917 | 0.979 | 0.439 | 0.830 | 0.853 | 0.818 | 8.5 |
YOLOv5s | 0.988 | 0.660 | 0.995 | 0.421 | 0.766 | 0.751 | 0.782 | 67.2 |
YOLOv7 | 0.979 | 0.910 | 0.992 | 0.676 | 0.889 | 0.897 | 0.886 | 22.5 |
YOLOv8s | 0.973 | 0.932 | 0.953 | 0.721 | 0.895 | 0.901 | 0.898 | 48.3 |
YOLOv7-Cherry[ | 0.974 | 0.922 | 0.945 | 0.779 | 0.905 | 0.915 | 0.910 | 18.5 |
改进YOLOv7的小目标算法[ | 0.980 | 0.931 | 0.962 | 0.799 | 0.918 | 0.920 | 0.917 | 23.0 |
轻量化YOLO-v7数显仪表检测[ | 0.965 | 0.909 | 0.910 | 0.583 | 0.842 | 0.866 | 0.836 | 30.5 |
YOLOv7-MSBP | 0.983 | 0.938 | 0.995 | 0.812 | 0.932 | 0.914 | 0.930 | 23.9 |
Tab. 5 Comparison experimental results of different power distribution cabinet character positioning models
模型 | AP | mAP@0.5 | Precision | Recall | FPS | |||
---|---|---|---|---|---|---|---|---|
Label | Led | Point | Switch | |||||
YOLOv3[ | 0.977 | 0.804 | 0.986 | 0.333 | 0.775 | 0.744 | 0.792 | 17.7 |
YOLOv4-tiny | 0.974 | 0.000 142 | 0.873 | 0.018 4 | 0.466 | 0.475 | 0.467 | 87.6 |
Faster R-CNN | 0.985 | 0.917 | 0.979 | 0.439 | 0.830 | 0.853 | 0.818 | 8.5 |
YOLOv5s | 0.988 | 0.660 | 0.995 | 0.421 | 0.766 | 0.751 | 0.782 | 67.2 |
YOLOv7 | 0.979 | 0.910 | 0.992 | 0.676 | 0.889 | 0.897 | 0.886 | 22.5 |
YOLOv8s | 0.973 | 0.932 | 0.953 | 0.721 | 0.895 | 0.901 | 0.898 | 48.3 |
YOLOv7-Cherry[ | 0.974 | 0.922 | 0.945 | 0.779 | 0.905 | 0.915 | 0.910 | 18.5 |
改进YOLOv7的小目标算法[ | 0.980 | 0.931 | 0.962 | 0.799 | 0.918 | 0.920 | 0.917 | 23.0 |
轻量化YOLO-v7数显仪表检测[ | 0.965 | 0.909 | 0.910 | 0.583 | 0.842 | 0.866 | 0.836 | 30.5 |
YOLOv7-MSBP | 0.983 | 0.938 | 0.995 | 0.812 | 0.932 | 0.914 | 0.930 | 23.9 |
模型 | 定位mAP | 识别mAP |
---|---|---|
YOLOv5s+Paddle OCR | 0.775 | 0.892 |
YOLOv7+Paddle OCR | 0.889 | 0.944 |
YOLOv7-MSPBP+ Paddle OCR | 0.932 | 0.995 |
Tab. 6 Comparison experiment results of combined models
模型 | 定位mAP | 识别mAP |
---|---|---|
YOLOv5s+Paddle OCR | 0.775 | 0.892 |
YOLOv7+Paddle OCR | 0.889 | 0.944 |
YOLOv7-MSPBP+ Paddle OCR | 0.932 | 0.995 |
1 | 杨典,李小燕,刘培焱,等. 基于OpenCV的变电站仪表识别方法研究[J]. 自动化与仪表, 2022, 37(4): 75-80. |
YANG D, LI X Y, LIU P Y, et al. Research on the recognition method of substation instruments based on OpenCV[J]. Automation and Instrumentation, 2022, 37(4): 75-80. | |
2 | 陈莉珺. 变电站智能巡检应用现状及解决措施[J]. 低碳世界, 2020, 10(11): 144-145. |
CHEN L J. Application status and solutions of intelligent inspection in substation[J]. Low Carbon World, 2020, 10(11): 144-145. | |
3 | VÁZQUEZ-FERNÁNDEZ E, DACAL-NIETO A, GONZÁLEZ-JORGE H, et al. A machine vision system for the calibration of digital thermometers[J]. Measurement Science and Technology, 2009, 20(6): No.065106. |
4 | 朱柏林,郭亮,吴清文. 基于ORB和改进Hough变换的指针仪表智能识读方法[J]. 仪表技术与传感器, 2017(1): 29-33, 73. |
ZHU B L, GUO L, WU Q W. Intelligent recognition method for pointer meters based on ORB and improved Hough transform[J]. Instrument Technique and Sensor, 2017(1): 29-33, 73. | |
5 | 林剑萍,廖一鹏. 基于OpenCV和LSSVM的数字仪表读数自动识别[J]. 微型机与应用, 2017, 36(2): 37-40. |
LIN J P, LIAO Y P. Automatic recognition of digital meter readings based on OpenCV and LSSVM[J]. Microcomputer and Its Applications, 2017, 36(2): 37-40. | |
6 | REDMON J, DIVVALA S, IRSHICK R, et al. You only look once: unified, real-time object detection[C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2016: 779-788. |
7 | REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards realtime object detection with region proposal networks[C]// Proceedings of the 28th International Conference on Neural Information Processing Systems — Volume 1. Cambridge: MIT Press, 2015, 1:91-99. |
8 | GIRSHICK R. Fast RCNN[C]// Proceedings of the 2015 IEEE International Conference on Computer Vision. Piscataway: IEEE, 2015: 1440-1448. |
9 | GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587. |
10 | LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]// Proceedings of the 2016 European Conference on Computer Vision, LNCS 9905. Cham: Springer, 2016: 21-37. |
11 | 刘雨青,隋佳蓉,魏星,等. 基于轻量级YOLOv4的小目标实时检测[J]. 激光与光电子学进展, 2023, 60(6): No.0610009. |
LIU Y Q, SUI J R, WEI X, et al. Real-time detection of small targets based on lightweight YOLOv4[J]. Laser and Optoelectronics Progress, 2023, 60(6): No.0610009. | |
12 | 牛为华,殷苗苗. 基于改进YOLO v5的道路小目标检测算法[J]. 传感技术学报, 2023, 36(1): 36-44. |
NIU W H, YIN M M. Road small target detection algorithm based on improved YOLO v5[J]. Chinese Journal of Sensors and Actuators, 2023, 36(1): 36-44. | |
13 | 侯卓成,欧阳华,胡鑫,等. 基于改进的YOLOv4彩色数字仪表读数识别方法[J]. 电子测量技术, 2022, 45(6): 124-129. |
HOU Z C, OUYANG H, HU X, et al. Improved YOLOv4 color digital instrument reading recognition method[J]. Electronic Measurement Technology, 2022, 45(6): 124-129. | |
14 | 孙顺远,杨挺. 基于深度学习的仪表目标检测算法[J]. 仪表技术与传感器, 2021(6): 104-108. |
SUN S Y, YANG T. Instrument target detection algorithm based on deep learning[J]. Instrument Technique and Sensor, 2021(6): 104-108. | |
15 | 郑玉珩,黄德启. 改进MobileViT与YOLOv4的轻量化车辆检测网络[J]. 电子测量技术, 2023, 46(2): 175-183. |
ZHENG Y H, HUANG D Q. Lightweight vehicle detection network based on MobileViT and YOLOv4[J]. Electronic Measurement Technology, 2023, 46(2): 175-183. | |
16 | 林文树,张金生,何乃磊. 基于改进YOLO v4的落叶松毛虫侵害树木实时检测方法[J]. 农业机械学报, 2023, 54(4): 304-312, 393. |
LIN W S, ZHANG J S, HE N L. Real-time detection method of Dendrolimus superans-infested Larix gmelinii trees based on improved YOLO v4[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(4): 304-312, 393. | |
17 | 郝帅,张旭,马旭,等. 基于CBAM-YOLOv5的煤矿输送带异物检测[J]. 煤炭学报, 2022, 47(11): 4147-4156. |
HAO S, ZHANG X, MA X, et al. Foreign object detection in coal mine conveyor belt based on CBAM-YOLOv5[J]. Journal of China Coal Society, 2022, 47(11): 4147-4156. | |
18 | 赵霖,王素珍,邵明伟,等. 基于改进YOLOv5的输电线路鸟巢缺陷检测方法[J]. 电子测量技术, 2023, 46(3): 157-165. |
ZHAO L, WANG S Z, SHAO M W, et al. Improved YOLOv5-based bird’s nest defect detection method for transmission lines[J]. Electronic Measurement Technology, 2023, 46(3): 157-165. | |
19 | WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention[C]// Proceedings of the 2018 European Conference on Computer Vision, LNCS 11211. Cham: Springer, 2018: 3-19. |
20 | LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]// Proceedings of the 2017 IEEE Conference on Computer Version and Pattern Recognition. Piscataway: IEEE, 2017: 936-944. |
21 | 张明路,郭策,吕晓玲,等. 改进的轻量化YOLOv4用于电子元器件检测[J]. 电子测量与仪器学报, 2021, 35(10): 17-23. |
ZHANG M L, GUO C, LYU X L, et al. Improved lightweight YOLOv4 for electronic components inspection[J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(10): 17-23. | |
22 | 王卫星,刘泽乾,高鹏,等. 基于改进YOLO v4的荔枝病虫害检测模型[J]. 农业机械学报, 2023, 54(5): 227-235. |
WANG W X, LIU Z Q, GAO P, et al. Detection of litchi diseases and insect pests based on improved YOLO v4 model[J]. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(5): 227-235. | |
23 | 龙凌,陈浩,梁昊,等. 基于轻量化YOLO网络的实时X射线焊缝缺陷检测[J]. 网络新媒体技术, 2023, 12(2): 30-38. |
LONG L, CHEN H, LIANG H, et al. Real-time X-ray weld defect detection based on lightweight YOLO network[J]. Network New Media Technology, 2023, 12(2): 30-38. | |
24 | 吴志高,陈明. 基于改进YOLO v7的微藻轻量级检测方法[J]. 大连海洋大学学报, 2023, 38(1): 129-139. |
WU Z G, CHEN M. Lightweight detection method for microalgae based on improved YOLO v7[J]. Journal of Dalian Ocean University, 2023, 38(1): 129-139. | |
25 | CHEN J, KAO S H, HE H, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]// Proceedings of the 2023 IEEE/CVF Conference on Computer Version and Pattern Recognition. Piscataway: IEEE, 2023: 12021-12031. |
26 | KANAGARATHINAM K, SEKAR K. Text detection and recognition in raw image of seven segment digital energy meter display[J]. Energy Reports, 2019, 5:842-845. |
27 | 朱立倩. 基于深度学习的数显仪表字符识别[J]. 计算机技术与发展, 2020, 30(6):141-144. |
ZHU L Q. Character recognition of digital display instrument based on deep learning[J]. Computer Technology and Development, 2020, 30(6):141-144. | |
28 | HOWARD A, SANGLER M, CHEN B, et al. Searching for MobileNetV3[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision. Piscataway: IEEE, 2019:1314-1324. |
29 | 徐宏强,徐望明,王望,等. 多干扰环境下段码液晶显示仪表读数的鲁棒识别方法[J]. 武汉科技大学学报, 2022, 45(5):394-400. |
XU H Q, XU W M, WANG W, et al. Robust recognition method for seven-segment LCD meter readings in multi-interference environment[J]. Journal of Wuhan University of Science and Technology, 2022, 45(5):394-400. | |
30 | WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time objectors[C]// Proceedings of the 2023 IEEE/CVF International Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2023:7464-7475. |
31 | SIMONYAN K, ZSSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. (2015-04-10) [2023-10-22].. |
32 | 盖荣丽,孔祥宙,秦山,等. 基于YOLOv7改进的夜间樱桃检测方法: YOLOv7-Cherry[J/OL]. 计算机工程与应用, 2023:1-11 [2023-10-22].. |
GAI R L, KONG X Z, QIN S, et al. Improved cherry detection method at night based on YOLOv7: YOLOv7-Cherry[J/OL]. Computer Engineering and Applications, 2023: 1-11 [2023-10-22]. . | |
33 | 李安达,吴瑞明,李旭东. 改进YOLOv7的小目标检测算法研究[J]. 计算机工程与应用, 2024, 60(1):122-134. |
LI A D, WU R M, LI X D. Research on improving YOLOv7’s small target detection algorithm[J]. Computer Engineering and Applications, 2024, 60(1):122-134. | |
34 | 章芮宁, 闫坤, 叶进. 轻量化YOLO-v7的数显仪表检测及读数[J]. 计算机工程与应用, 2024, 60(8): 192-201. |
ZHANG R N, YAN K, YE J. Lightweight YOLO-v7 for digital instrumentation detection and reading[J]. Computer Engineering and Applications, 2024, 60(8): 192-201. |
[1] | Zhiqiang ZHAO, Peihong MA, Xinhong HEI. Crowd counting method based on dual attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2886-2892. |
[2] | Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974. |
[3] | Liting LI, Bei HUA, Ruozhou HE, Kuang XU. Multivariate time series prediction model based on decoupled attention mechanism [J]. Journal of Computer Applications, 2024, 44(9): 2732-2738. |
[4] | Kaipeng XUE, Tao XU, Chunjie LIAO. Multimodal sentiment analysis network with self-supervision and multi-layer cross attention [J]. Journal of Computer Applications, 2024, 44(8): 2387-2392. |
[5] | Pengqi GAO, Heming HUANG, Yonghong FAN. Fusion of coordinate and multi-head attention mechanisms for interactive speech emotion recognition [J]. Journal of Computer Applications, 2024, 44(8): 2400-2406. |
[6] | Zhonghua LI, Yunqi BAI, Xuejin WANG, Leilei HUANG, Chujun LIN, Shiyu LIAO. Low illumination face detection based on image enhancement [J]. Journal of Computer Applications, 2024, 44(8): 2588-2594. |
[7] | Shangbin MO, Wenjun WANG, Ling DONG, Shengxiang GAO, Zhengtao YU. Single-channel speech enhancement based on multi-channel information aggregation and collaborative decoding [J]. Journal of Computer Applications, 2024, 44(8): 2611-2617. |
[8] | Li LIU, Haijin HOU, Anhong WANG, Tao ZHANG. Generative data hiding algorithm based on multi-scale attention [J]. Journal of Computer Applications, 2024, 44(7): 2102-2109. |
[9] | Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199. |
[10] | Dahai LI, Zhonghua WANG, Zhendong WANG. Dual-branch low-light image enhancement network combining spatial and frequency domain information [J]. Journal of Computer Applications, 2024, 44(7): 2175-2182. |
[11] | Wenliang WEI, Yangping WANG, Biao YUE, Anzheng WANG, Zhe ZHANG. Deep learning model for infrared and visible image fusion based on illumination weight allocation and attention [J]. Journal of Computer Applications, 2024, 44(7): 2183-2191. |
[12] | Wu XIONG, Congjun CAO, Xuefang SONG, Yunlong SHAO, Xusheng WANG. Handwriting identification method based on multi-scale mixed domain attention mechanism [J]. Journal of Computer Applications, 2024, 44(7): 2225-2232. |
[13] | Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072. |
[14] | Dianhui MAO, Xuebo LI, Junling LIU, Denghui ZHANG, Wenjing YAN. Chinese entity and relation extraction model based on parallel heterogeneous graph and sequential attention mechanism [J]. Journal of Computer Applications, 2024, 44(7): 2018-2025. |
[15] | Yan ZHOU, Yang LI. Rectified cross pseudo supervision method with attention mechanism for stroke lesion segmentation [J]. Journal of Computer Applications, 2024, 44(6): 1942-1948. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||