基于邊緣增強(qiáng)引導(dǎo)濾波的光場(chǎng)全聚焦圖像融合

武迎春; 王玉梅; 王安紅; 趙賢凌

doi:10.11999/JEIT190723

基于邊緣增強(qiáng)引導(dǎo)濾波的光場(chǎng)全聚焦圖像融合

doi: 10.11999/JEIT190723

太原科技大學(xué)電子信息工程學(xué)院太原 030024

基金項(xiàng)目: 國(guó)家自然科學(xué)基金(61601318)，山西省青年科技研究基金(201601D021078)，山西省重點(diǎn)學(xué)科建設(shè)經(jīng)費(fèi)，山西省互聯(lián)網(wǎng)+3D打印協(xié)同創(chuàng)新中心，山西省1331工程重點(diǎn)創(chuàng)新團(tuán)隊(duì)，山西省科技創(chuàng)新團(tuán)隊(duì)(201705D131025)，太原科技大學(xué)博士啟動(dòng)基金(20132023)，國(guó)家留學(xué)基金

詳細(xì)信息

作者簡(jiǎn)介:
武迎春：女，1984年生，副教授，研究方向?yàn)楣鈭?chǎng)信息獲取與處理、光學(xué)3維傳感

王玉梅：女，1995年生，碩士生，研究方向?yàn)楣庑畔@取與處理

王安紅：女，1972年生，教授，研究方向?yàn)橐曨l通信、圖像識(shí)別、3D數(shù)據(jù)分析理解

趙賢凌：女，1978年生，講師，研究方向?yàn)楣鈭?chǎng)信息獲取與處理、光學(xué)3維傳感

通訊作者:
王玉梅　1954569241@qq.com

中圖分類號(hào): TN911.73
計(jì)量
- 文章訪問(wèn)數(shù): 1665
- HTML全文瀏覽量: 616
- PDF下載量: 81
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2019-09-17
- 修回日期: 2020-07-13
- 網(wǎng)絡(luò)出版日期: 2020-07-22
- 刊出日期: 2020-09-27

Light Field All-in-focus Image Fusion Based on Edge Enhanced Guided Filtering

School of Electronic and Information Engineering, Taiyuan University of Science and Technology, Taiyuan 030024, China

Funds: The National Natural Science Foundation of China (61601318), The Shanxi Science Foundation of Applied Foundational Research (201601D021078), The Fund of Shanxi Key Subjects Construction, The Collaborative Innovation Center of Internet+3D Printing in Shanxi Province, The Key Innovation Team of Shanxi 1331 Project, The Scientific and Technological Innovation Team of Shanxi Province (201705D131025), The Youth Foundation of Taiyuan University of Science and Technology (20132023), The Foundation of China Scholarship Council

摘要

摘要: 受光場(chǎng)相機(jī)微透鏡幾何標(biāo)定精度的影響，4D光場(chǎng)在角度方向上的解碼誤差會(huì)造成積分后的重聚焦圖像邊緣信息損失，從而降低全聚焦圖像融合的精度。該文提出一種基于邊緣增強(qiáng)引導(dǎo)濾波的光場(chǎng)全聚焦圖像融合算法，通過(guò)對(duì)光場(chǎng)數(shù)字重聚焦得到的多幅重聚焦圖像進(jìn)行多尺度分解、特征層決策圖引導(dǎo)濾波優(yōu)化來(lái)獲得最終全聚焦圖像。與傳統(tǒng)融合算法相比，該方法對(duì)4D光場(chǎng)標(biāo)定誤差帶來(lái)的邊緣信息損失進(jìn)行了補(bǔ)償，在重聚焦圖像多尺度分解過(guò)程中增加了邊緣層的提取來(lái)實(shí)現(xiàn)圖像高頻信息增強(qiáng)，并建立多尺度圖像評(píng)價(jià)模型實(shí)現(xiàn)邊緣層引導(dǎo)濾波參數(shù)優(yōu)化，可獲得更高質(zhì)量的光場(chǎng)全聚焦圖像。實(shí)驗(yàn)結(jié)果表明，在不明顯降低融合圖像與原始圖像相似性的前提下，該方法可有效提高全聚焦圖像的邊緣強(qiáng)度和感知清晰度。
- 4D光場(chǎng) /
- 全聚焦圖像融合 /
- 引導(dǎo)濾波 /
- 邊緣增強(qiáng) /
- 參數(shù)優(yōu)化
Abstract: Affected by the micro-lens geometric calibration accuracy of the light field camera, the decoding error of the 4D light field in the angular direction will cause the edge information loss of the integrated refocused image, which will reduce the accuracy of the all-in-focus image fusion. In this paper, a light field all-in-focus image fusion algorithm based on edge-enhanced guided filtering is proposed. Through multi-scale decomposition of the digital refocused images and guided filtering optimization of the feature layer decision map, the final all-in-focus image is obtained. Compared with the traditional fusion algorithm, the edge information loss caused by the 4D light field calibration error is compensated in the presented method. In the step of multi-scale decomposition of the refocused image, the edge layer extraction is added to accomplish the high-frequency information enhancement. Then the multi-scale evaluation model is established to optimize the edge layer’s guided filtering parameters to obtain a better light field all-in-focus image. The experimental results show that the edge intensity and the perceptual sharpness of the all-in-focus image can be improved without significantly reducing the similarity between the all-in-focus image and the original image.
- 4D light field /
- All-in-focus image fusion /
- Guided filtering /
- Edge enhancement /
- Parameter optimization

HTML全文

圖 1 光場(chǎng)數(shù)字重聚焦幾何模型

下載: 全尺寸圖片幻燈片

圖 2 2D光場(chǎng)原圖的解碼及積分

下載: 全尺寸圖片幻燈片

圖 3 邊緣增強(qiáng)引導(dǎo)濾波算法流程

下載: 全尺寸圖片幻燈片

圖 4 邊緣增強(qiáng)引導(dǎo)濾波的參數(shù)優(yōu)化

下載: 全尺寸圖片幻燈片

圖 5 光場(chǎng)原圖及重聚焦圖像

下載: 全尺寸圖片幻燈片

圖 6 特征層分解

下載: 全尺寸圖片幻燈片

圖 7 初步?jīng)Q策圖的獲取

下載: 全尺寸圖片幻燈片

圖 8 初步融合決策圖的優(yōu)化

下載: 全尺寸圖片幻燈片

圖 9 光場(chǎng)全聚焦圖像融合

下載: 全尺寸圖片幻燈片

圖 10 Cup圖像融合實(shí)驗(yàn)結(jié)果對(duì)比

下載: 全尺寸圖片幻燈片

表 1 Flower圖像不同融合算法性能評(píng)價(jià)指標(biāo)比較

Flower	IE	EI	FMI	PSI
PCA	7.7027	34.8908	0.6903	0.1806
WT	7.7178	39.4788	0.6343	0.1973
Laplace	7.6965	39.3516	0.7317	0.1867
BF	7.6929	39.0181	0.7521	0.1873
GFF	7.7081	38.6164	0.7333	0.1860
G-GRW	7.7047	38.8265	0.7435	0.1851
DSIFT	7.7054	39.4555	0.7494	0.1921
本文	7.7099	40.3353	0.6482	0.2330

下載: 導(dǎo)出CSV

表 2 Cup圖像不同融合算法性能評(píng)價(jià)指標(biāo)比較

Cup	IE	EI	FMI	PSI
PCA	7.6366	39.7368	0.6145	0.1991
WT	7.6453	47.2613	0.5609	0.2768
Laplace	7.6172	46.1445	0.6891	0.2473
BF	7.6191	45.9757	0.6976	0.2478
GFF	7.6365	45.6423	0.6916	0.2400
G-GRW	7.6366	45.7279	0.6976	0.2467
DSIFT	7.6366	45.8104	0.6984	0.2474
本文	7.6366	47.2942	0.6392	0.2857

下載: 導(dǎo)出CSV

表 3 Runner圖像不同融合算法性能評(píng)價(jià)指標(biāo)比較

Runner	IE	EI	FMI	PSI
PCA	7.4581	67.7672	0.7363	0.2844
WT	7.4673	76.1906	0.7286	0.3307
Laplace	7.4664	75.9168	0.7774	0.3260
BF	7.4606	74.4269	0.7834	0.3291
GFF	7.4653	74.4718	0.7835	0.3157
G-GRW	7.4654	74.4898	0.8285	0.3191
DSIFT	7.4664	74.9858	0.8293	0.3247
本文	7.4723	77.5482	0.7610	0.3497

下載: 導(dǎo)出CSV

參考文獻(xiàn)(21)

LIU Yu, CHEN Xun, PENG Hu, et al. Multi-focus image fusion with a deep convolutional neural network[J]. Information Fusion, 2017, 36: 191–207. doi: 10.1016/j.inffus.2016.12.001

WU Gaochang, MASIA B, JARABO A, et al. Light field image processing: An overview[J]. IEEE Journal of Selected Topics in Signal Processing, 2017, 11(7): 926–954. doi: 10.1109/JSTSP.2017.2747126

GOSHTASBY A A and NIKOLOV S. Image fusion: Advances in the state of the art[J]. Information Fusion, 2007, 8(2): 114–118. doi: 10.1016/j.inffus.2006.04.001

劉帆, 裴曉鵬, 張靜, 等. 基于優(yōu)化字典學(xué)習(xí)的遙感圖像融合方法[J]. 電子與信息學(xué)報(bào), 2018, 40(12): 2804–2811. doi: 10.11999/JEIT180263

LIU Fan, PEI Xiaopeng, ZHANG Jing, et al. Remote sensing image fusion based on optimized dictionary learning[J]. Journal of Electronics &Information Technology, 2018, 40(12): 2804–2811. doi: 10.11999/JEIT180263

謝穎賢, 武迎春, 王玉梅, 等. 基于小波域清晰度評(píng)價(jià)的光場(chǎng)全聚焦圖像融合[J]. 北京航空航天大學(xué)學(xué)報(bào), 2019, 45(9): 1848–1854. doi: 10.13700/j.bh.1001-5965.2018.0739

XIE Yingxian, WU Yingchun, WANG Yumei, et al. Light field all-in-focus image fusion based on wavelet domain sharpness evaluation[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(9): 1848–1854. doi: 10.13700/j.bh.1001-5965.2018.0739

肖斌, 唐翰, 徐韻秋, 等. 基于Hess矩陣的多聚焦圖像融合方法[J]. 電子與信息學(xué)報(bào), 2018, 40(2): 255–263. doi: 10.11999/JEIT170497

XIAO Bin, TANG Han, XU Yunqiu, et al. Multi-focus image fusion based on Hess matrix[J]. Journal of Electronics &Information Technology, 2018, 40(2): 255–263. doi: 10.11999/JEIT170497

ZHANG Yu, BAI Xiangzhi, and WANG Tao. Boundary finding based multi-focus image fusion through multi-scale morphological focus-measure[J]. Information Fusion, 2017, 35: 81–101. doi: 10.1016/j.inffus.2016.09.006

SUN Jianguo, HAN Qilong, KOU Liang, et al. Multi-focus image fusion algorithm based on Laplacian pyramids[J]. Journal of the Optical Society of America A, 2018, 35(3): 480–490. doi: 10.1364/JOSAA.35.000480

WAN Tao, ZHU Chenchen, and QIN Zengchang. Multifocus image fusion based on robust principal component analysis[J]. Pattern Recognition Letters, 2013, 34(9): 1001–1008. doi: 10.1016/j.patrec.2013.03.003

LIU Yu, LIU Shuping, and WANG Zengfu. Multi-focus image fusion with dense SIFT[J]. Information Fusion, 2015, 23: 139–155. doi: 10.1016/j.inffus.2014.05.004

LI Shutao, KANG Xudong, and HU Jianwen. Image fusion with guided filtering[J]. IEEE Transactions on Image Processing, 2013, 22(7): 2864–2875. doi: 10.1109/TIP.2013.2244222

MA Jinlei, ZHOU Zhiqiang, WANG Bo, et al. Multi-focus image fusion based on multi-scale focus measures and generalized random walk[C]. The 36th Chinese Control Conference, Dalian, China, 2017: 5464–5468. doi: 10.23919/ChiCC.2017.8028223.

NG R, LEVOY M, BREDIF M, et al. Light field photography with a hand-held plenoptic camera[R]. Stanford Tech Report CTSR 2005-02, 2005.

SOTAK JR G E and BOYER K L. The laplacian-of-gaussian kernel: A formal analysis and design procedure for fast, accurate convolution and full-frame output[J]. Computer Vision, Graphics, and Image Processing, 1989, 48(2): 147–189. doi: 10.1016/s0734-189x(89)80036-2

HE Kaiming, SUN Jian, and TANG Xiaoou. Guided image filtering[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(6): 1397–1409. doi: 10.1109/TPAMI.2012.213

YOON Y, JEON H G, YOO D, et al. Light-field image super-resolution using convolutional neural network[J]. IEEE Signal Processing Letters, 2017, 24(6): 848–852. doi: 10.1109/LSP.2017.2669333

SCHMIDT M, LE ROUX N, and BACH F. Minimizing finite sums with the stochastic average gradient[J]. Mathematical Programming, 2017, 162(1/2): 83–112. doi: 10.1007/s10107-016-1030-6

LIU Zheng, BLASCH E, XUE Zhiyun, et al. Objective assessment of multiresolution image fusion algorithms for context enhancement in night vision: A comparative study[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(1): 94–109. doi: 10.1109/tpami.2011.109

JUNEJA M and SANDHU P S. Performance evaluation of edge detection techniques for images in spatial domain[J]. International Journal of Computer Theory and Engineering, 2009, 1(5): 614–621. doi: 10.7763/IJCTE.2009.V1.100

HAGHIGHAT M and RAZIAN M A. Fast-FMI: Non-reference image fusion metric[C]. The 8th IEEE International Conference on Application of Information and Communication Technologies, Astana, Kazakhstan, 2014: 1–3. doi: 10.1109/ICAICT.2014.7036000.

FEICHTENHOFER C, FASSOLD H, and SCHALLAUER P. A perceptual image sharpness metric based on local edge gradient analysis[J]. IEEE Signal Processing Letters, 2013, 20(4): 379–382. doi: 10.1109/LSP.2013.2248711

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問(wèn)統(tǒng)計(jì)