基于概率随机裁剪的图像缩放算法

doi:10.11959/j.issn.1000-436x.2017127

通信学报 ›› 2017, Vol. 38 ›› Issue (6): 30-38.doi: 10.11959/j.issn.1000-436x.2017127

基于概率随机裁剪的图像缩放算法

郭迎春¹,侯骏腾¹,于明¹,王睿俐²

¹ 河北工业大学计算机科学与软件学院，天津 300401
² 梅西大学自然与数学科学系，新西兰奥克兰 4442

修回日期:2017-03-24 出版日期:2017-06-25 发布日期:2017-06-30
作者简介:郭迎春（1970-），女，河北张家口人，河北工业大学副教授，主要研究方向为数字图像处理、图像显著性检测、图像缩放、图像质量评价和人脸识别表情识别等。|侯骏腾（1990-），男，河北黄骅人，河北工业大学硕士生，主要研究方向为图像处理与模式识别。|于明（1964-），男，河北秦皇岛人，河北工业大学教授，主要研究方向为语音与图像视觉信息融合的生物特征识别、图像数学变换、图像与视频编码的高效算法和视觉计算及其应用（视频数据挖掘、人脸识别、笔迹鉴别系统及其应用）等。|王睿俐（1965-），男，新西兰奥克兰人，博士，梅西大学副教授，主要研究方向为模式识别、机器学习和复杂系统等。
基金资助:
国家自然科学基金资助项目(60302018);天津市科技计划基金资助项目(14RCGFGX00846);天津市科技计划基金资助项目(15ZCZDNC00130);河北省自然科学基金资助项目(F2015202239)

Content-aware image resizing based on random-carving with probability

Ying-chun GUO¹,Jun-teng HOU¹,Ming YU¹,Rui-li WANG²

¹ School of Computer Science and Engineering,Hebei University of Technology,Tianjin 300401,China
² Institute of Natural and Mathematical Sciences,Massey University,Auckland 4442,New Zealand

Revised:2017-03-24 Online:2017-06-25 Published:2017-06-30
Supported by:
The National Natural Science Foundation of China(60302018);The Natural Science Foundation of Hebei Province(F2015202239)

摘要/Abstract

摘要：

为提高图像缩放的速度，提出一种结合阈值学习与依概率随机裁剪的快速内容感知图像缩放算法，通过计算图像的重要度图，利用径向基函数（RBF,radial basis function）神经网络进行阈值学习求出图像的重要度阈值，根据阈值将图像分成保护区域和非保护区域，并按缩放要求为其分配不同的缩放比，分别进行依概率随机裁剪。在MSRA图像数据库上与目前流行的内容感知缩放方法进行对比，实验结果表明，所提方法的缩放时间明显低于其他算法，而且在缩放效果上有明显的优势。

关键词: 阈值学习, 径向基函数, 依概率随机裁剪, 快速内容感知图像缩放

Abstract:

To improve the running speed of image resizing,a fast content-aware image resizing algorithm was proposed based on the threshold learning and random-carving with probability.Firstly the important map was calculated by combining the graph-based visual saliency map and gradient map.Then the image threshold value was obtained by radial basis function (RBF) neural network learning.And by the threshold,the original image was separated into the protected part and the unprotected part which was corresponding to the important part and the unimportant part of the original image individually.Finally,the two parts were allocated different resizing scales and the random-carving with probability was applied to them respectively.Experiments results show that the proposed algorithm has lower time cost comparing to the state-of-arts algorithms in MSRA image database,and has a better visual perception on image resizing.

Key words: threshold learning, radial basis function, random-carving with probability, rapid content-aware image resizing

中图分类号:

TN911.73

郭迎春,侯骏腾,于明,王睿俐. 基于概率随机裁剪的图像缩放算法[J]. 通信学报, 2017, 38(6): 30-38.

Ying-chun GUO,Jun-teng HOU,Ming YU,Rui-li WANG. Content-aware image resizing based on random-carving with probability[J]. Journal on Communications, 2017, 38(6): 30-38.

图/表 7

图1

图2

图3

图4

图5

表1

表2

参考文献 21

[1]	AVIDAN S , SHAMIR A . Seam carving for content-aware image resizing[J]. ACM Transactions on Graphics, 2007,26(3): 10-18.
[2]	RUBINSTEIN M , SHAMIR A , AVIDAN S . Improved seam carving for video retargeting[J]. ACM Transactions on Graphics, 2008,27(3): 1-9.
[3]	SHI M L , PENG G Q , YANG L ,et al. Optimal bi-directional seam carving for content-aware image resizing[C]// The 5th International Conference on E-learning and Games,Edutainment. 2010: 456-467.
[4]	LIU Z , YAN H B , SHEN L Q ,et al. Adaptive image retargeting using saliency-based continuous seam carving[J]. Optical Engineering, 2010,49(1):017002.
[5]	CHO S H , CHOI H , MATSUSHITA Y ,et al. Image retargeting using importance diffusion[C]// The ICIP. 2009: 977-980.
[6]	盛国瑞, 高铁杠, 范礼 ,等. 基于扩展马尔可夫特征的 seam-carving篡改检测[J]. 通信学报, 2014,35(6): 39-46.
	SHENG G R , GAO T G , FAN L ,et al. Seam-carving forgery detection based on expanded Markov features[J]. Journal on Comunications, 2014,35(6): 39-46.
[7]	BASHA T , MOSES Y , AVIDAN S . Stereo carving a geometrically consistent approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(10): 2513-2525.
[8]	YUE B , HOU C , ZHOU Y . Improved seam carving for stereo image resizing[J]. EURASIP Journal on Wireless Communications and Networking, 2013(1): 1-6.
[9]	WANG Y S , TAI C L , SORKING O ,et al. Optimized scale-and-stretch for image resizing[J]. ACM Transactions on Graphics, 2008,27(5): 1-8.
[10]	雷励星 . 基于混合能量的内容敏感图像缩放新方法[J]. 计算机学报, 2010,33(10): 2015-2021.
	LEI L X . Content-aware image resizing based on hybrid energy[J]. Chinese Journal of Computer, 2010,33(10): 2015-2021.
[11]	DU H , LIU Z , JIANG J ,et al. Stretchability-aware block scaling for image retargeting[J]. Journal of Visual Communication ＆Image Representation, 2013,24(4): 499-508.
[12]	ZHANG L , SONG H , OU Z ,et al. Image retargeting with multifocus fisheye transformation[J]. Visual Computer, 2012,29(5): 407-420.
[13]	LIN S S , YEH I C , LIN C H ,et al. Patch-based image warping for content-aware retargeting[J]. IEEE Transactions on Multimedia, 2013,15(2): 359-368.
[14]	LIANG Y , ZHUO S U , LUO X N ,et al. Image shrinkage based on hot-target map and featured edge preservation[J]. Journal of Software, 2011,22(4): 789-800.
[15]	LIANG Y , SU Z , WANG C ,et al. Optimised image retargeting using aesthetic-based cropping and scaling[J]. IET Image Processing, 2013,7(1): 61-69.
[16]	RUBINSTEIN M , SHAMIR A , AVIDAN S . Multi-operator media retargeting[J]. ACM Transactions on Graphics, 2009,28(3):23. 1-23.11.
[17]	DONG W M , ZHOU N , PAUL J C ,et al. Optimized image resizing using seam carving and scaling[J]. ACM Transactions on Graphics, 2009,28(5):125. 1-125.10.
[18]	赵旦峰, 王博, 杨大伟 . 基于随机置乱的内容感知图像缩放算法[J]. 吉林大学学报(工学版), 2015,45(4): 1324-1328.
	ZHAO D F , WANG B , YANG D W . Content-aware image resizing based on random permutation[J]. Journal of Jilin University (Engineering and Technology Edition), 2015,45(4): 1324-1328.
[19]	王会千, 杨高波, 张兆扬 ,等. 基于重要度扩散和自适应采样的图像/视频缩放技术[J]. 通信学报, 2011,32(8): 165-170.
	WANG H Q , YANG G B , ZHANG Z Y ,et al. Image and video resizing algorithm based on importance diffusion and adaptive scaling[J]. Journal on Communications, 2011,32(8): 165-170.
[20]	HAREL J , KOCH C , PERONA P . Graph-based visual saliency[C]// Advances in Neural Information Processing Systems. 2006: 545-552.
[21]	RUBINSTEIN M , GUTIERREZ D , SORKINE O ,et al. A comparative study of image retargeting[J]. ACM Transactions on Graphics, 2010,29(6): 81-95.

方法	图片数	百分比
CARP方法	68	34%
线裁剪方法	95	47.5%
流裁剪方法	42	21%
等比例缩放方法	32	16%
本文方法	163	81.5%

方法	平均运行时间/s
CARP方法	1.09
线裁剪方法	2.56
流裁剪方法	1.75
等比例缩放方法	0.09
本文方法	0.98

基于概率随机裁剪的图像缩放算法

Content-aware image resizing based on random-carving with probability

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 21

相关文章 4

Metrics

推荐阅读 0

[1]	周志立, 王美民, 杨高波, 朱剑宇, 孙星明. 基于轮廓自动生成的构造式图像隐写方法[J]. 通信学报, 2021, 42(9): 144-154.
[2]	芮国胜, 刘歌, 田文飚, 董道广, 张雅楠. 基于二次最优阈值近似消息传递法的蒸发波导去噪重构[J]. 通信学报, 2019, 40(10): 10-19.
[3]	王金铭,叶时平,尉理哲,许森,蒋燕君. 半张量积压缩感知模型的快速重构方法[J]. 通信学报, 2018, 39(7): 26-38.
[4]	巨刚,袁亮,刘小月,岳昊恩. 基于改进SURF算法的移动目标实时图像配准方法研究[J]. 通信学报, 2017, 38(1): 177-186.