图像拼接质量评价方法

doi:10.3969/j.issn.1000-436x.2013.08.010

通信学报 ›› 2013, Vol. 34 ›› Issue (8): 76-81.doi: 10.3969/j.issn.1000-436x.2013.08.010

图像拼接质量评价方法

万国挺,王俊平,李锦,曹洪花,汪松,王乐,李亚宁,韦蓉

西安电子科技大学通信工程学院，陕西西安710071

出版日期:2013-08-25 发布日期:2017-08-31
基金资助:
西安市科技计划基金资助项目;国家自然科学基金资助项目;111工程基金资助项目

Method for quality assessment of image mosaic

Guo-ting WAN,Jun-ping WANG,Jin LI,Hong-hua CAO,Song WANG,Le WANG,IYA-ning L,Rong WEI

School of Communication Engineering,Xidian University,Xi’an 710071,China

Online:2013-08-25 Published:2017-08-31
Supported by:
The Science ＆ Technology Program of Xi’an;The National Natural Science Foundation of China;111 Project

摘要/Abstract

摘要：

在现有图像质量评价方法相关原理基础上，提出了一种基于图像边缘信息的拼接质量评价新方法。该方法针对图像拼接结果的特点，先对待评价图像进行边缘提取，然后利用拼接前后图像的边缘轮廓信息，综合图像像素误差信息和结构信息，根据其均值和方差等统计信息与影响图像拼接质量的主要因素（拼接错位和亮度突变）之间的关系，对拼接图像进行评价。该评价方法得出的评价结果更加符合人眼视觉对图像拼接质量的主观评价感受，较准确地反映了拼接图像的真实质量和所使用图像拼接算法的性能。

关键词: 图像拼接, 质量评价, 差分边缘谱, 边缘检测

Abstract:

On the basis of the theory of existing methods for image quality assessment,a novel method for quality assessment of mosaicked image based on the information of image edge was presented.The method was in accordance with the features of mosaicked image.Firstly,the edges of image were detected.Then according to the information of image edges,the information of pixel error and structure was considered.The mean value and variance of the difference of edge map were related with the misplacement and the brightness mutation,which influenced the quality of mosaicked image.Lastly,the evaluate procedure was done based on the relationship.The new method was more consistent with the subjective feeling to the mosaicked image quality.This method accurately reflects the real quality of mosaicked image and the performance of the algorithm of image mosaic.

Key words: image mosaic, quality assessment, difference of edge map, edge detection

万国挺,王俊平,李锦,曹洪花,汪松,王乐,李亚宁,韦蓉. 图像拼接质量评价方法[J]. 通信学报, 2013, 34(8): 76-81.

Guo-ting WAN,Jun-ping WANG,Jin LI,Hong-hua CAO,Song WANG,Le WANG,IYA-ning L,Rong WEI. Method for quality assessment of image mosaic[J]. Journal on Communications, 2013, 34(8): 76-81.

图/表 9

图1

表1

表2

图2

图3

图4

表3

图5

表4

参考文献 15

[1]	蒋刚毅, 黄大江, 王旭 ,等. 图像质量评价方法研究进展[J]. 电子与信息学报, 2010,32(1): 219-226. JIANG G Y , HUANG D J , WANG X ,et al. Overview on image quality assessment methods[J]. Journal of Electronics and Information Technology, 2010,32(1): 219-226.
[2]	HOPKINS H H . Modern methods of image assessment[A]. Proceedings of the SPIE-The International Society for Optical Engineering,Reading[C]. 1981. 2-11.
[3]	路文 . 基于视觉感知的影像质量评价方法研究[D]. 西安:西安电子科技大学, 2009. LU W . Image Quality Evaluation Method Base on Visual Perception[D]. Xi’an:Xidian University, 2009.
[4]	张桦 . 基于视觉感知的图像质量评价[D]. 浙江:浙江大学, 2009. ZHANG H . Image Quality Evaluation Base on Visual Perception[D]. Zhejiang:Zhejiang University, 2009.
[5]	蒋铭, 马兆丰, 辛宇 ,等. 基于 DWT 和视觉加权的图像质量评价方法研究[J]. 通信学报, 2011,32(9): 129-136. JIANG M , MA Z F , XIN Y ,et al. Image quality evaluation method base on digital wavelet transform and vision weighted[J]. Journal on Communications, 2011,32(9): 129-136.
[6]	BLASCH E P , GAO J B , TUNG W W . Chaos-based image assessment for THz imagery[A]. 2012 11th International Conference on Information Sciences,Signal Processing and their Applications[C]. Montreal,QC,Canada, 2012. 360-365.
[7]	SAAD M A , BOVIK ALAN C.et al . Blind image quality assessment:a natural scene statistics approach in the DCT domain[J]. IEEE Transactions on Image Processing, 2012,21(8): 3339-3352.
[8]	周景超, 戴汝为, 肖柏华 . 图像质量评价研究综述[J]. 计算机科学, 2008,35(7): 1-4. ZHOU J C , DAI R W , XIAO B H . Overview of image quality assessment[J]. Journal of Computer Science, 2008,35(7): 1-4.
[9]	MITTAL A ,et al. No-reference image quality assement in the spatial domain[J]. IEEE Transactions on Image Processing, 2012,21(12): 4695-4708.
[10]	DIMITRIEVSKI M D , IVANOVSKI Z A . No-reference image visual quality assement using nonliner regression[A]. Third International Workshop on Quality of Multimedia Experience[C]. 2011. 78-83.
[11]	BOVIK A C . Subjective image quality assessment-live image quality assessment database[EB/OL]. . 2011.10.
[12]	LEACHTENAUERL J . National imagery interpretability rating scales overview and product description[A]. ASPRS/ACSM[C]. 1996. 262-272.
[13]	HUYNH-THU Q , GHANBARI M . Scope of validity of PSNR in image/video quality assessment[J]. Electronics Letters, 2008,44(13): 800-801.
[14]	WANG Z H R , BOVIK A , SHEIKH C . Image quality assessment:From error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004,13(4): 600-612.
[15]	ZHANG X G , YANG L ,et al. Improved sobel edge detection[A]. IEEE International Conference Computer Science and Information Technology[C]. 2010. 67-71.

评价因素	μ	σ₂
错位程度	↑↑	↑↑↑
亮度差异	↑↑	↑
注：向上箭头表示正相关关系，箭头数量表示影响程度。

等级	质量准则	妨碍准则
5	非常好	丝毫看不出图像质量变坏
4	好	能看出图像质量变坏，但不妨碍观看
3	一般	清楚看出图像质量变坏，对观看稍有妨碍
2	差	妨碍观看
1	非常差	非常严重妨碍观看

评价方法	评价结果/dB
PSNR	15.589 539
SSIM	0.491 789
DoEM	0.228 463

待评价图像	PSNR/dB	SSIM/dB	DoEM/dB
图5(a)	29.841 716	0.925 038	0.877 413
图5(b)	20.905 100	0.766 055	0.689 941
图5(c)	36.623 175	0.997 253	0.959 147

图像拼接质量评价方法

Method for quality assessment of image mosaic

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 15

相关文章 5

Metrics

推荐阅读 0

[1]	万国挺，王俊平，李锦，曹洪花，汪松，王乐，李亚宁，韦蓉. 图像拼接质量评价方法[J]. 通信学报, 2013, 34(8): 10-81.
[2]	魏耀都,谢湘,匡镜明,韩辛璐. 新的全参考音视频同步感知质量评价模型[J]. 通信学报, 2012, 33(2): 182-190.
[3]	蔣铭,马兆丰,辛宇,钮心忻,杨义先. 基于DWT和视觉加权的图像质量评价方法研究[J]. 通信学报, 2011, 32(9): 129-136.
[4]	王俊平,懂帅君,任春丽,张宇. 提耿缺陷轮廓的一种新方法[J]. 通信学报, 2008, 29(11A): 139-143.
[5]	连静,王珂,李光鑫. 基于边缘的小波图像融合算法[J]. 通信学报, 2007, 28(4): 18-23.