基于DCT域纹理特征的多聚焦图像融合

doi:10.3969/j.issn.0255-8297.2015.06.006

应用科学学报 ›› 2015, Vol. 33 ›› Issue (6): 628-636.doi: 10.3969/j.issn.0255-8297.2015.06.006

基于DCT域纹理特征的多聚焦图像融合

唐振华^1,2, 梁聪¹, 区骋³, 黄旭方¹, 覃团发^1,2

1. 广西大学计算机与电子信息学院, 南宁 530004;
2. 广西大学广西高校多媒体通信与信息处理重点实验室, 南宁 530004;
3. 中国铁塔广西区分公司, 南宁 530007

收稿日期:2015-09-16 修回日期:2015-11-10 出版日期:2015-11-30 发布日期:2015-11-30
作者简介:唐振华,博士,副教授,研究方向:图像/视频处理与编码,E-mail:tangedward@126.com
基金资助:
国家自然科学基金(No.61461006, No.61261023);广西省自然科学基金(No.2013GXNSFBA019271)资助

Multi-focus Image Fusion Based on Texture Features in DCT Domain

TANG Zhen-hua^1,2, LIANG Cong¹, OU Cheng³, HUANG Xu-fang¹, QIN Tuan-fa^1,2

1. School of Computer and Electronics Information, Guangxi University, Nanning 530004, China;
2. Guangxi Colleges and Universities Key Laboratory of Multimedia Communications and Information Processing, Guangxi University, Nanning 530004, China;
3. China Tower Guangxi Branch Company, Nanning 530007, China

Received:2015-09-16 Revised:2015-11-10 Online:2015-11-30 Published:2015-11-30

摘要/Abstract

摘要： 现有的基于离散余弦变换(discrete cosine transform, DCT)的多聚焦图像融合算法容易使融合图像出现块效应和伪影,为此提出一种基于DCT域纹理特征的图像融合算法.该算法以8×8 DCT块中反映能量方向性的纹理区域作为图像融合单位,根据纹理区域的频谱相似度,选择能量较大的区域或以区域加权叠加的方式获得融合区域.实验结果表明,与现有基于DCT域的多聚焦图像融合算法相比,该算法获得的融合图像主观质量较好,能有效避免明显的块效应与伪影.

关键词: 多聚焦, 图像融合, DCT域, 纹理特征

Abstract: Exiting multi-focus image fusion methods based on discrete cosine transform (DCT) domain cause blocking effects and artifacts in the fused images. To address this problem, an image fusion algorithm concentrated on texture features in the DCT domain is proposed. The proposed method separates each 8×8 DCT block into several texture regions having various directivity of energy distribution in the source images. Similarity of the frequency spectra for the two texture regions are calculated. The part of the fused image is obtained by selecting the one with more energy, or using the weighted result. Experimental results show that the proposed algorithm can effectively reduce blocking effects and artifacts. Compared with exiting approaches in DCT domain, the proposed algorithm can provide fused images with better subjective quality.

Key words: multi-focus, image fusion, DCT domain, texture features

中图分类号:

TP391

唐振华, 梁聪, 区骋, 黄旭方, 覃团发. 基于DCT域纹理特征的多聚焦图像融合[J]. 应用科学学报, 2015, 33(6): 628-636.

TANG Zhen-hua, LIANG Cong, OU Cheng, HUANG Xu-fang, QIN Tuan-fa. Multi-focus Image Fusion Based on Texture Features in DCT Domain[J]. Journal of Applied Sciences, 2015, 33(6): 628-636.

参考文献

[1] Li S, Yang B. Multifocus image fusion using region segmentation and spatial frequency[J]. Image and Vision Computing, 2008, 26(7):971-979.

[2] Li X J, Wang M H. Research of multi-focus image fusion algorithm based on Gabor filter bank[C]//Proceedings of 12th International Conference on Signal Processing, 2014:693-697.

[3] Tian J, Chen L. Multi-focus image fusion using wavelet-domain statistics[C]//Proceedings of 17th IEEE International Conference on Image Processing, 2010:1205-1208.

[4] Gao G R, Xu L P, Feng D Z. Multi-focus image fusion based on non-subsampled shearlet transform[J]. IET Image Processing, 2013, 7(6):633-639.

[5] Yang Y, Tong S, Huang S Y, Lin P. Multifocus image fusion based on NSCT and focused area detection[J]. IEEE Sensors Journal, 2015, 15(5):2824-2838.

[6] Phamila Y A V, Amutha R. Discrete cosine transform based fusion of multi-focus images for visual sensor networks[J]. Signal Process, 1995, 95:161-170.

[7] Tang J. A contrast based image fusion technique in the DCT domain[J]. Digit Signal Process, 2004, 14(3):218-226.

[8] Haghighat M B A, Aghagolzadeh A, Seyedarabi H. Multi-focus image fusion for visual sensor networks in DCT domain[J]. Computers and Electrical Engineering, 2011, 37(5):789-797.

[9] Cao L, Jin L, Tao H. Multi-focus image fusion based on spatial frequency in discrete cosine transform domain[J]. IEEE Signal Processing Letters, 2015, 22(2):220-224.

[10] 桑庆兵,齐会新,吴小俊,李朝锋.基于DCT系数无参考模糊图像质量评价方法[J].仪器仪表学报, 2013, 34(11):2599-2604. Sang Q B, Qi H X, Wu X J, Li C F. No-reference image blur assessment method based on DCT coefficients[J]. Chinese Journal of Scientific Instrument, 2013, 34(11):2599-2604. (in Chinese)

[11] 黄祥林,沈兰荪.基于DCT压缩域的纹理图像分类[J].电子与信息学报, 2002, 24(2):216-221. Huang X L, Shen L S. Texture image classification based on DCT domain[J]. Journal of Electronics and Information Technology, 2002, 24(2):216-221. (in Chinese)

[12] 玉振明,毛士艺,高飞.用局部傅里叶变换进行图像融合[J].信号处理, 2004, 20(3):227-230. Yu Z M, Mao S Y, Gao F. Image fusion via localized Fourier transform[J]. Signal Processing, 2004, 20(3):227-230. (in Chinese)

[13] Xydeas C S, Petrovic V. Objective image fusion performance measure[J]. Electronics Letter, 2000, 36(4):308-309.

[14] Haghighat M, Razian M A. Fast-FMI:non-reference image fusion metric[C]//IEEE 8th International Conference on Application of Information and Communication Technologies, 2014:1-3.

[15] Wang Z, Bovik A C, Sheikh H R, Simoncelli E P. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600- 612.

基于DCT域纹理特征的多聚焦图像融合

Multi-focus Image Fusion Based on Texture Features in DCT Domain

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	王灿军, 廖鑫, 陈嘉欣, 秦拯, 刘绪崇. 基于卷积神经网络的面部图像修饰检测[J]. 应用科学学报, 2019, 37(5): 618-630.
[2]	楼建强, 戴文战, 李俊峰. 基于非下采样Contourlet变换的自适应医学图像融合算法[J]. 应用科学学报, 2017, 35(6): 763-774.
[3]	刘洋, 徐洪平, 易航, 施清平, 夏伟强, 康健. 基于有约束CNMF的遥感高光谱多光谱图像融合[J]. 应用科学学报, 2016, 34(6): 651-660.
[4]	潘瑜，王静，孙权森，夏德深. 结合图像质量评价参数的多尺度分解融合策略[J]. 应用科学学报, 2011, 29(2): 159-168.
[5]	石丹;李庆武;范新南;霍冠英. 曲波变换域侧扫声纳图像海底底质分类[J]. 应用科学学报, 2009, 27(5): 498-501.