对数域梯度与改进Sobel算子相结合的边缘检测

任克强; 张镕

doi:10.3788/YJYXS20193403.0283

您当前的位置：

首页 >

文章列表页 >

对数域梯度与改进Sobel算子相结合的边缘检测

图像处理 | 更新时间：2020-07-05

- 对数域梯度与改进Sobel算子相结合的边缘检测
- Edge detection based on logarithmic domain gradient and improved Sobel operator
- 液晶与显示 2019年34卷第3期页码：283-290
- 作者机构：
  
  江西理工大学信息工程学院, 江西赣州 341000
- 作者简介：
  
  [ "任克强(1959-), 男, 湖南汨罗人, 硕士, 教授, 1993年于华中理工大学获得硕士学位, 主要从事图像与视频处理、信息隐藏方面的研究。E-mail:jxrenkeqiang@163.com" ]
- 基金信息：
  
  国家自然科学基金(61501210);Supported by National Natural Science Foundation of China(61501210)
- DOI：10.3788/YJYXS20193403.0283
  中图分类号： TP391
- 收稿日期：2018-10-29，
  
  录用日期：2018-12-21，
  
  纸质出版日期：2019-03
- 稿件说明：
移动端阅览
任克强, 张镕. 对数域梯度与改进Sobel算子相结合的边缘检测[J]. 液晶与显示, 2019,34(3):283-290.

Ke-qiang REN, Rong ZHANG. Edge detection based on logarithmic domain gradient and improved Sobel operator[J]. Chinese journal of liquid crystals and displays, 2019, 34(3): 283-290.
任克强, 张镕. 对数域梯度与改进Sobel算子相结合的边缘检测[J]. 液晶与显示, 2019,34(3):283-290. DOI： 10.3788/YJYXS20193403.0283.

Ke-qiang REN, Rong ZHANG. Edge detection based on logarithmic domain gradient and improved Sobel operator[J]. Chinese journal of liquid crystals and displays, 2019, 34(3): 283-290. DOI： 10.3788/YJYXS20193403.0283.

摘要

为了消除不均匀光照给图像边缘检测带来的影响，提出一种对数域梯度与改进Sobel算子相结合的边缘检测方法。该方法首先将图像变换到对数域，通过削弱低频入射分量增强高频反射分量，以提升图像亮度；然后合成改进的4方向Sobel算子，并用无穷范数表示梯度，以使需要被检测的图像更加完整；最后通过Bernsen算法得到的阈值与高斯滤波后得到的Bernsen算法阈值进行线性组合来确定最佳阈值，以使图像边缘更加连续完整。仿真实验结果表明，该方法可以有效消除不均匀光照对图像边缘检测的影响，与相关算法和文献相比，该方法对不同照度图像的边缘检测效果更好。

Abstract

In order to eliminate the influence of uneven illumination on image edge detection

an edge detection method based on logarithmic domain gradient and improved Sobel operator was proposed. Firstly

the image was transformed into logarithmic domain to enhance the brightness of the image by weakening the low-frequency incident component and enhancing the high-frequency reflection component. Then

the improved 4-direction Sobel operator was synthesized and the gradient is expressed by infinite norm

so as to make the edges of the image to be detected more complete. Finally

the threshold obtained by the Bernsen algorithm was linearly combined with the threshold of the Bernsen algorithm obtained by Gaussian filtering to determine the optimal threshold

which could make the edges of the image more continuous and complete. The simulation experiment results show that the method can effectively eliminate the influence of uneven illumination on image edge detection

and compared with related algorithms and literatures

the method has better edge detection effect on different illumination images.

关键词

Keywords

references

齐龙, 蒋郁, 李泽华, 等.基于显微图像处理的稻瘟病菌孢子自动检测与计数方法[J].农业工程学报, 2015, 31(12):186-193.

QI L, JIANG Y, LI Z H, et al . Automatic detection and counting method for spores of rice blast based on micro image processing[J]. Transactions of the Chinese Society of Agricultural Engineering , 2015, 31(12):186-193. (in Chinese)

范有臣, 赵洪利, 孙华燕, 等.激光主动成像结合距离选通技术的零时信号测量方法[J].红外与激光工程, 2016, 45(3):0306004.

FAN Y C, ZHAO H L, SUN H Y, et al . Zero signal measurement method based on laser active imaging combined with laser range-gated technology[J]. Infrared and Laser Engineering , 2016, 45(3):0306004. (in Chinese)

周同雪, 朱明.视频图像中的运动目标检测[J].液晶与显示, 2017, 32(1):40-47.

ZHOU T X, ZHU M. Moving target detection of the video images[J]. Chinese Journal of Liquid Crystals and Display , 2017, 32(1):40-47. (in Chinese)

SHI T, KONG J Y, WANG X D, et al . Improved Roberts operator for detecting surface defects of heavy rails with superior precision and efficiency[J]. High Technology Letters , 2016, 22(2):207-214.

BISWAS R, SILJ. An improved canny edge detection algorithm based on type-2 fuzzy sets[J]. Procedia Technology , 2012, 4:820-824.

徐昌荣, 王聪颖.基于Hadoop集群的Sobel边缘检测[J].江西理工大学学报, 2013, 34(3):38-41, 74.

XU C R, WANG C Y. Sobel image edge detection based on Hadoop[J]. Journal of Jiangxi University of Science and Technology , 2013, 34(3):38-41, 74. (in Chinese)

王殿伟, 王晶, 许志杰, 等.一种光照不均匀图像的自适应校正算法[J].系统工程与电子技术, 2017, 39(6):1383-1390.

WANG D W, WANG J, XU Z J, et al . Adaptive correction algorithm for non-uniform illumination images[J]. Systems Engineering and Electronics , 2017, 39(6):1383-1390. (in Chinese)

PARK S, YU S, KIM M, et al . Dual autoencoder network for retinex-based low-light image enhancement[J]. IEEE Access , 2018, 6:22084-22093.

毛东月, 谢正祥, 贺向前, 等.自适应双向保带宽对数变换及低照度图像增强[J].中国图象图形学报, 2017, 22(10):1356-1363.

MAO D Y, XIE Z X, HE X Q, et al . Adaptive bilateral logarithm transformation with bandwidth preserving and low-illumination image enhancement[J]. Journal of Image and Graphics , 2017, 22(10):1356-1363. (in Chinese)

曾凡锋, 郭玉阳, 肖珂.边缘保留的光照不均文本图像二值算法[J].计算机工程与设计, 2016, 37(3):700-704.

ZENG F F, GUO Y Y, XIAO K. Document image binarization method with reserved edge and uneven illumination[J]. Computer Engineering and Design , 2016, 37(3):700-704. (in Chinese)

李海, 张宪民, 黄沿江, 等.光学显微线条纹图像中心线提取[J].光学精密工程, 2017, 25(5):1340-1347.

LI H, ZHANG X M, HUANG Y J, et al . Centerline extraction of stripe imaged by optical microscope[J]. Optics and Precision Engineering , 2017, 25(5):1340-1347. (in Chinese)

BOONSIVANON K, MEESOMBOONA. IKDSIFT:An improved keypoint detection algorithm based-on SIFT approach for non-uniform illumination[J]. Procedia Computer Science , 2016, 86:269-272.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

RGB深度图像显著性目标检测方法设计

基于经验模态分解的激光散斑噪声抑制方法

基于深度学习的木材表面缺陷图像检测

结合图像边缘检测和最小误差替换的隐写方案

基于FPGA的实时彩色图像边缘检测算法的实现