[1]胡璟懿,匡 尧,余 铮,等.面向大光度变化图像的阈值自适应 Canny 算子[J].机械与电子,2022,(08):18-22.
　HU Jingyi,KUANG Yao,YU Zheng,et al.Improved Adaptive Canny Operator for Large Photometric Variation[J].Machinery & Electronics,2022,(08):18-22.
点击复制

面向大光度变化图像的阈值自适应 Canny 算子()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2022年08期
页码:
18-22
栏目:
设计与研究
出版日期:
2022-08-24

文章信息/Info

Title:
Improved Adaptive Canny Operator for Large Photometric Variation
文章编号:
1001-2257 ( 2022 ) 08-0018-05
作者:
胡璟懿 1 ; 匡 尧 1 ; 余 铮 2 ; 王敬靖 2 ; 张兰澜 1 ; 刘云飞 1
1. 国网湖北省电力有限公司,湖北 武汉 430077 ;
2. 国网湖北省电力有限公司信息通信公司,湖北 武汉 430000
Author(s):
HU Jingyi1 ;  KUANG Yao1 ;  YU Zheng2 ;  WANG Jingjing2 ;  ZHANG Lanlan1 ;  LIU Yunfei1
( 1.State Grid Hubei Electric Power Co. , Ltd. , Wuhan 430077 , China ; 2.Information and Communication Company of State Grid Hubei Electric Power Co. , Ltd. , Wuhan 430000 , China )
关键词:
光学字符识别; 大光度变化; Canny 算子; 自适应阈值; 图像预处理
Keywords:
optical character recognition ;  large photometric variation ;  Canny operator ;  adaptive threshold ;  image preprocessing
分类号:
TP391.1
文献标志码:
A
摘要:
传统 Canny 算子需要手动设定高低阈值,当输入图像光照均匀且均值变化较小时,可以采用预先设定阈值的方式实现,但当输入图像遭遇大光度变化,灰度值均值产生较大波动时,预先设定高低阈值往往无法适应实际工况。提出了一种通过结合图像预处理和自适应阈值来解决 Canny 算子阈值调整困难的方法,克服了大光度变化图像中的阈值设定问题,并将其应用到透视变换过程中,解决了输入图像角度问题。实验结果表明,所提方法能够很好地解决大光度变化的应用场景问题。
Abstract:
The traditional Canny operator needs to manually set the high and low thresholds.When the input image is evenly illuminated and the mean value changes little , it can be achieved by setting the thresholds in advance.However , when the input image encounters large luminosity changes and the average gray value fluctuates greatly , the preset high and low thresholds often cannot adapt to the actual working conditions.In this paper , a method to solve the difficulty of threshold adjustment of Canny operator by combining image preprocessing and adaptive threshold is proposed , which overcomes the problem of threshold setting in images with large luminosity changes , and it is applied to the process of perspective transformation to solve the problem of input Image angle problem.Experiment results show that the proposed method can solve the application scene problem with large luminosity change very well.

参考文献/References:

[ 1 ] BUI D C , TRUONG D , VO N D , et al.MC-OCR challenge 2021 : deep learning approach for vietnamese receipts OCR [ C ]// 2021RIVF International Conference on Computing and Communication Technologies( RIVF ),2021 : 1-6.

[ 2 ] 张岩,赵玉涛,李光旭,等 . 图像的边缘检测技术研究进展[ J ] . 计算机与数字工程,2020 , 48 ( 5 ): 1176-1184 , 1232.
[ 3 ] SHRIVAKSHAN G , CHANDRASEKAR C.A comparison of various edge detection techniques used in image processing [ J ] .International journal of computer science issues( IJCSI ), 2012 , 9 ( 5 ): 269.
[ 4 ] CHAPLE G N , DARUWALA R , GOFANE M S. Comparisions of robert , prewitt , sobel operator based edge detection methods for real time uses on FPGA[ C ]// 2015 International Conference on Technologies for Sustainable Development( ICTSD ), 2015 : 1-4.
[ 5 ] CANNY J.A computational approach to edge detection [ J ] .IEEE Transactions on pattern analysis and machine intelligence , 1986 ( 6 ): 679-698.
[ 6 ] PELLEGRINO F A , VANZELLA W , TORRE V. Edge detection revisited [ J ] .IEEE Transactions on systems , man , and cybernetics : Part B ( cybernetics ), 2004 , 34 ( 3 ): 1500-1518.
[ 7 ] 刘成刚,刘二林,姜香菊 . 改进 Canny 算子的列车轮对踏面边缘检测算法[ J ] . 铁道机车车辆, 2021 , 41 ( 1 ): 22-25.
[ 8 ] 李健,刘孔宇,任宪盛,等 . 基于自适应阈值的 Canny 算法在 MRI 边缘检测中的应用[ J ] . 吉林大学学报(工学版),2021 , 51 ( 2 ): 712-719.
[ 9 ] 段军,高翔 . 基于统计滤波的自适应双阈值改进 Canny 算子边缘检测算法[ J ] . 激光杂志, 2015 , 36 ( 1 ): 10-12.
[ 10 ] 王文豪,姜明新,赵文东 . 基于 Canny 算子改进的边缘检测算法[ J ] . 中国科技论文, 2017 , 12 ( 8 ): 910-915.
[ 11 ] YANG P , SONG W , ZHAO X , et al.An improved Otsu threshold segmentation algorithm [ J ] .International journal of computational science and engineering , 2020 , 22 ( 1 ): 146-153.
[ 12 ] OTHMAN Z , ABDULLAH A.An adaptive threshold based on multiple resolution levels for canny edge detection [ C ]// International Conference of Reliable Information and Communication Technology , 2017 : 316-323.
[ 13 ] RAO B S.Dynamic histogram equalization for contrast enhancement for digital images [ J ] .Applied soft computing , 2020 , 89 : 106114.
[ 14 ] JU M , DING C , ZHANG D , et al.Gamma-correction based visibility restoration for single hazy images [ J ] . IEEE Signal processing letters , 2018 , 25 ( 7 ):1084-1088.
[ 15 ] DONG X , WANG G , PANG Y , et al.Fast efficient algorithm for enhancement of low lighting video [ C ]// 2011 IEEE International Conference on Multimedia and Expo , 2011 : 1-6.
[ 16 ] ZOTIN A.Fast algorithm of image enhancement based on multi-scale Retinex [ J ] .Procedia computer science , 2018 , 131 : 6-14.
[ 17 ] TRUONG M T N , KIM S.Automatic image thresholding using Otsus method and entropy weighting scheme for surface defect detection [ J ] .Soft computing , 2018 , 22 ( 13 ): 4197-4203.
[ 18 ] FAN P , ZHOU RG , HU W W , et al.Quantum image edge extraction based on Laplacian operator and zero cross method [ J ] .Quantum information processing , 2019 , 18 ( 1 ): 1-23.
[ 19 ] VAIRALKAR M K , NIMBHORKAR S.Edge detection of images using Sobel operator [ J ] .International journal of emerging technology and advanced engineering , 2012 , 2 ( 1 ): 291-293.

备注/Memo

备注/Memo:
收稿日期: 2022-03-08
基金项目:国网湖北省电力有限公司科技项目( 52153320002G )
作者简介:胡璟懿 ( 1977- ),男,湖北宜昌人,学士,高级经济师,研究方向为数字化审计;匡 尧 ( 1984- ),男,湖北荆门人,硕士,高级工程师,研究方向为数字化审计;余 铮 ( 1984- ),男,湖北武汉人,硕士,高级工程师,研究方向为模式识别与智能系统;王敬靖 ( 1992- ),男,湖北襄阳人,硕士,工程师,研究方向为大数据。
更新日期/Last Update: 2022-08-26