结合图像分割的改进导引滤波

王健博; 杨航; 吴笑天

doi:10.3788/YJYXS20173205.0380

您当前的位置：

首页 >

文章列表页 >

结合图像分割的改进导引滤波

显示与图像 | 更新时间：2020-07-07

- 结合图像分割的改进导引滤波
- Segmentation based improved guided filter
- 液晶与显示 2017年32卷第5期页码：380-386
- 作者机构：
  
  1.北京航天发射技术研究所, 北京 100076
  2.中国科学院长春光学精密机械与物理研究所图像部, 吉林长春 130033
- 作者简介：
  
  [ "王健博 (1984-)，男，吉林白山人，博士，工程师，主要从事嵌入式系统、目标跟踪及图像处理研究。E-mail：mypostwww@163.com" ]
  [ "杨航 (1985-)，男，吉林长春人，博士，助理研究员，主要从事图像复原、图像增强等方面的研究。E-mail: yhang3109@163.com" ]
- 基金信息：
  
  国家自然科学基金(61401425);National Natural Science Foundation of China(61401425)
- DOI：10.3788/YJYXS20173205.0380
  中图分类号： TP394.1;TH691.9
- 收稿日期：2016-10-10，
  
  录用日期：2016-12-26，
  
  纸质出版日期：2017-05
- 稿件说明：
移动端阅览
王健博, 杨航, 吴笑天. 结合图像分割的改进导引滤波[J]. 液晶与显示, 2017,32(5):380-386.

Jian-bo WANG, Hang YANG, Xiao-tian Wu. Segmentation based improved guided filter[J]. Chinese journal of liquid crystals and displays, 2017, 32(5): 380-386.
王健博, 杨航, 吴笑天. 结合图像分割的改进导引滤波[J]. 液晶与显示, 2017,32(5):380-386. DOI： 10.3788/YJYXS20173205.0380.

Jian-bo WANG, Hang YANG, Xiao-tian Wu. Segmentation based improved guided filter[J]. Chinese journal of liquid crystals and displays, 2017, 32(5): 380-386. DOI： 10.3788/YJYXS20173205.0380.

摘要

为了更好地对图像进行平滑同时保持边缘不模糊，设计一种新的滤波方法。对基于该方法的图像滤波、细节增强等算法进行研究。首先，根据图像的亮度和颜色对图像进行分割，将图像分成不同的区域。接着，在不同的区域进行导引滤波，得到互不交叠的多个滤波子图像。然后，将这些子图融合，得到基于分割的改进导引滤波结果。最后，利用提出的改进导引滤波方法提出一种多尺度的细节增强方法。实验结果表明，在图像光滑和细节增强方面，提出的方法都要好于传统的导引滤波：提出的方法不仅能较好的光滑图像，同时保持边缘清晰，减少了传统滤波方法在边缘处的光晕现象。

Abstract

In order to smooth image detail and preserve edge information well

a new edge-preserving filter is proposed in this paper. The filtering and detail enhancement method based on the proposed filter is studied. First

based on image intensity and color

the mean shift method is used for image segmentation

and we obtain several areas. Second

the guided image filter is used for each area

and several filtered images are separated with each other. Third

we fuse these filtered images to obtain a final result. Finally

a multi-scale detail enhancement method based on improved guided filter is proposed. Experimental results indicate that the proposed filter approach can obtain edge-preserving smoothed image

and detail enhanced image with less hole than guided filter. The proposed filter can obtain better results than guided filter in smoothing and detail enhancement.

关键词

Keywords

references

芮杰, 吴冰, 秦志远, 等.一种稳健的自适应图像平滑算法[J].中国图象图形学报, 2005, 10(1):54-58.

RUI J, WU B, QIN Z Y, et al. A robust adaptive image smoothing algorithm[J].Journal of Image and Graphics, 2005, 10(1):54-58. (in Chinese)

贾宏光, 吴泽鹏, 朱明超, 等.基于广义线性运算和双边滤波的红外图像增强[J].光学精密工程, 2013, 21(12):3272-3282.

JIA H G, WU Z P, ZHU M C, et al. Infrared image enhancement based on generalized linear operation and bilateral filter[J]. Optics and Precision Engineering, 2013, 21(12):3272-3282. (in Chinese)

刘海波, 杨杰, 吴正平, 等.改进的基于雾气理论的视频去雾[J].光学精密工程, 2016, 24(7):1789-1798.

LIU H B, YANG J, WU Z P, et al. Improved video defogging based on fog theory[J]. Optics andPrecision Engineering, 2016, 24(7):1789-1798. (in Chinese)

欧海燕, 郭太良, 姚剑敏, 等.基于分层色调映射的LED背光调制算法[J].液晶与显示, 2011, 26(2):246-249.

OU H Y, GUO T L, YAO J M, et al. Modulation of LED backlight based on hierarchical tone mapping algorithm[J]. Chinese Journal of Liquid Crystals and Displays, 2011, 26(2):246-249. (in Chinese)

谷雨, 刘晶红, 孙明超, 等.基于分形特征和导引滤波的可见光与红外图像融合算法[J].光电工程, 2015, 42(4):62-67.

GU Y, LIU J H, SUN M C, et al. Visible and infrared image fusion algorithm by fractal feature and guided filtering[J]. Opto-Electronic Engineering, 2015, 42(4):62-67. (in Chinese)

TOMASI C, MANDUCHI R. Bilateral filtering for gray and color images[C]//Proceedings of the Sixth International Conference on Computer Vision.Bombay:IEEE, 1998:839-846.

BUADES A, COLL B, MOREL J M. A non-local algorithm for image denoising[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). San Diego, CA, USA:IEEE, 2005, 2:60-65.

GASTAL E S L, OLIVEIRA M M. Domain transform for edge-aware image and video processing[J]. ACM Transactions on Graphics, 2011, 30(4):Article No. 69.

XU L, LU C W, XU Y, etal. Image smoothing via L 0 gradient minimization[J].ACM Transactions on Graphics, 2011, 30(6):Article No. 174.

PARIS S, HASINOFF S W, KAUTZ J.Local Laplacian filters:edge-aware image processing with a Laplacian pyramid[J].ACM Transactions on Graphics, 2011, 30(4):Article No. 68.

RUDIN L I, OSHER S, FATEMI E. Nonlinear total variation based noise removal algorithms[J]. Physica D:Nonlinear Phenomena, 1992, 60(1/4):259-268.

HE K M, SUN J, TANG X O. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6):1397-1409.

HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12):2341-2353.

COMANICIU D, MEER P. Mean shift:a robust approach toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5):603-619.

ZHOU Q, CHEN S F, LIU J Z, et al. Edge-preserving single image super-resolution[C]//Proceedings of the 19th ACM International Conference on Multimedia. New York, NY, USA:ACM, 2011:1037-1040.

ZHANG Z B, MA S L, HAN X. Multiscale feature extraction of finger-vein patterns based on curvelets and local interconnection structure neural network[C]//Proceedings of the 18th International Conference on Pattern Recognition (ICPR'06). Hong Kong:IEEE, 2006, 4:145-148.

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

基于边缘增强和特征融合的伪装目标分割

基于图像分割的点云去噪方法

基于NODE-UNet++和标记分水岭算法的红细胞图像分割

自适应动态肤色检测技术研究进展

基于Faster R-CNN的仪表识别方法