结合SFIM 和区域填充的对象场景融合

doi:10.3969/j.issn.0255-8297.2014.02.011

应用科学学报 ›› 2014, Vol. 32 ›› Issue (2): 185-190.doi: 10.3969/j.issn.0255-8297.2014.02.011

结合SFIM 和区域填充的对象场景融合

丁友东1，魏小成2，蔡喜2，章剑飞2

1. 上海大学影视艺术技术学院，上海200072
2．上海大学计算机工程与科学学院，上海200072

收稿日期:2012-01-09 修回日期:2013-01-11 出版日期:2014-03-25 发布日期:2013-01-11
作者简介:丁友东，教授，博导，研究方向：图像检索、图像分割、图像融合，E-mail: ydding@shu.edu.cn
基金资助:
上海市教委重点学科建设基金(No.J50103)；上海市教委科研创新基金(No.09YZ10)；上海大学211 工程重点学科项目基金（No.211-0-3）；上海市科委国际合作项目基金（No.09510700900）；上海市科委科技攻关重点项目基金（No.11511503300）资助

Object-Scene Fusion by Combining SFIM with Region Filling

DING You-dong1, WEI Xiao-cheng2, CAI Xi2, ZHANG Jian-fei2

1. School & Film of TV Arts and Technology, Shanghai University 200072, China
2. School of Computer Engineering and Science, Shanghai University, Shanghai 200072, China

Received:2012-01-09 Revised:2013-01-11 Online:2014-03-25 Published:2013-01-11

摘要/Abstract

摘要： 针对Poisson 融合法和现有基于IHS变换的方法存在的问题，在保留IHS 变换优势基础上提出了一种结合基于平滑滤波的亮度调制（smoothing filter-based intensity modulation, SFIM）技术和区域填充的综合改进方案. 该方案引入SFIM 来降低对象与场景融合时的颜色畸变，用色度、饱和度填充解决细节还原系数无法有效增大(对象获得足够融合光照)以及融合对象光照不一致的问题. 主观质量评价和客观质量评价均表明该方案不仅可有效解决上述问题，而且融合速度快，算法更加健壮.

关键词: 对象与场景融合, IHS 变换, SFIM 技术, 区域填充, 融合质量评价

Abstract: Considering the drawbacks of the Poisson fusion technique and an existing object-scene fusion method based on IHS transform, this paper proposes an improved scheme by combining smoothing filterbased intensity modulation (SFIM) with region filling making use of the advantages of IHS transform. The
scheme reduces color distortion in fusion of object and scene by introducing the SFIM technique. With the hue and saturation filling, it can also fix the problems that the detail recovery cannot be increased effectively to let object get enough fusion illumination so that the object may appear inconsistent in illumination. Both subjective and objective quality assessments show that the proposed scheme can solve the above-mentioned problems. It is fast and more robust.

Key words: fusion of object and scene, IHS transform, smoothing filter-based intensity modulation (SFIM) technique, region filling, fusion quality evaluation

中图分类号:

TP 391

丁友东1，魏小成2，蔡喜2，章剑飞2. 结合SFIM 和区域填充的对象场景融合[J]. 应用科学学报, 2014, 32(2): 185-190.

参考文献

[1] CHEN T, CHENG M M, TAN P, ARIEL S, HU S.M. Sketch2Photo: Internet image montage [J]. ACM Transactions on Graphics, 2009, 28(5): 1-10.

[2] 胡事民，徐昆，陈韬. 基于互联网的图像检索与融合[J]. 中国计算机学会通讯，2009, 5(12): 60-65.

   HU Shimin, XU Kun, CHEN Tao. Image retrieve and composition based on Internet[J]. Communications of the CCF, 2009, 5(12): 60-65.

[3] JIA Jia Ya, SUN Jian, TANG Chi Keung, SHUM Heung Yeung. Drag-and-drop pasting[C]//Proceedings of the SIGGRAPH Conference, Boston, MA, USA, 2006: 631-636.

[4] HAYS J, EFROS A A. Scene completion using millions of photographs[C]//Proceedings of the SIGGRAPH Conference, San Diego, CA, USA, 2007: 1-7.

[5] DING Youdong, WEI Xiaocheng, PANG Haibo, et al. A new framework for the fusion of object and scene based on IHS transform [C]//Proceedings of the ICDIP Conference, Chengdu, China, 2011: v8009: 80091W.

[6] PÉREZ P, GANGNET M, BLAKE A. Poisson image editing[C]//Proceedings of the SIGGRAPH Conference, San Diego, CA, USA, 2003: 313-318.

[7] LALONDE J F, HOIEM D, EFROS A A, et al. Photo clip art[J]. ACM Transactions on Graphics, 2007, 26(3): 1-10.

[8] TAO M W, JOHNSON M K, PARIS S. Error-tolerant image compositing[C]//Proceedings of the ECCV Conference, Heraklion, Crete, Greece: 2010: 31-44.

[9] KRISTA A, Yun Zhang, PETER D. Wavelet based image fusion techniques-an introduction, review and comparison[J]. Journal of Photogrammetry and Remote Sensing, 2007, 62(4): 249-263.

[10] 陈焕平，何明一，李旭. 基于SWT区域对比度像素提取的多聚焦图像融合[J]. 中国图象图形学报，2011, 16(5): 865-870.

    CHEN Huanping, HE Mingyi, LI Xu. Multi-focus image fusion using pixel extraction based on SWT regional contrast [J]. Journal of Image and Graphics, 2011, 16(5): 865-870.

[11] 贾永红，张晓萍，贾世锋，张谦. 利用调制传递函数滤波改进的高频调制影像融合[J]. 应用科学学报，2010, 28(4): 361-366.

    JIA Yonghong, ZHANG Xiaoping, JIA Shifeng, ZHANG Qian. Improving high frequency modulation image fusion with modulation transfer function filters [J]. Journal of Applied Sciences, 2010, 28(4): 361-366.

[12] SONG Qiang, WANG Jiawen, ZHANG Hongbin. An overview on fusion of panchromatic image and multispectral image[C]//Proceedings of the ICIECS Conference, Wuhan, China, 2009: 1-4.

[13] LIU J G. Smoothing filter-based intensity modulation:a spectral preserve image fusion technique for improving spatial details[J]. International Journal of Remote Sensing, 2000, 21(18): 3461-3472.

[14] 刘则毅，徐高奎，丁雅斌. 一种新的图像合成方法[J]. 中国图象图形学报，2007, 12(3): 432-437.

    LIU Zeyi, XU Gaokui, DING Yabin. A new method for image composition [J]. Journal of Image and Graphics, 2007, 12(3): 432-437.

[15] SHUN’ICHI K, YUTAKA S, SATORU I. Using selective correlation coefficient for robust image registration[J]. Pattern Recognition, 2003, 36(5): 1165-1173.

[16] QU Guihong, ZHANG Dali, YAN Pingfan. Information measure for performance of image fusion[J]. Electronics Letters, 2002, 38(7): 313-315.

[17] ROTHER G, KOLMOGOROV V, BLAKE A. Grabcut-interactive foreground extraction using iterated graph cuts[C]//Proceedings of the SIGGRAPH Conference, Los Angeles, CA, USA, 2004: 309-314.

[18] VICENTE S, KOLMOGOROV V, ROTHER C. Graph cut based image segmentation with connectivity priors[C]//Proceedings of the CVPR Conference, Anchorage, AK, USA, 2008.

结合SFIM 和区域填充的对象场景融合

Object-Scene Fusion by Combining SFIM with Region Filling

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价