《電子技術(shù)應(yīng)用》
您所在的位置:首頁(yè) > 其他 > 設(shè)計(jì)應(yīng)用 > 基于NSST和NLMF的多聚焦圖像融合
基于NSST和NLMF的多聚焦圖像融合
信息技術(shù)與網(wǎng)絡(luò)安全
吳 劍1,,吳曉紅1,,何小海1,,李林怡2,卿粼波1
(1.四川大學(xué) 電子信息學(xué)院 圖像信息研究所,,四川 成都610065,; 2.中國(guó)民航局第二研究所,四川 成都610041)
摘要: 為對(duì)融合圖像的信息豐富度,、邊緣清晰度以及視覺(jué)效果作進(jìn)一步的提升,,設(shè)計(jì)了一種基于非下采樣剪切波變換(NSST)結(jié)合非局部均值濾波(NLMF)的多聚焦圖像融合算法。首先,,將源圖像通過(guò)NSST變換進(jìn)行多尺度,、多方向分解得到高、低頻子帶系數(shù),。其次,,對(duì)低頻子帶系數(shù)采用局部區(qū)域的改進(jìn)拉普拉斯能量和以及非局部均值濾波融合方法構(gòu)建低頻子帶系數(shù)融合權(quán)重;對(duì)高頻子帶系數(shù)采用基于相關(guān)系數(shù)的空間頻率與能量相結(jié)合的融合規(guī)則,再加以相位一致性規(guī)則,,構(gòu)建高頻子帶系數(shù)融合權(quán)重,;最后,通過(guò)NSST反變換得到最終融合圖像,。從三組不同聚焦圖像的實(shí)驗(yàn)結(jié)果來(lái)看,,所提算法不論是在主觀視覺(jué)上,還是在客觀評(píng)價(jià)上,,融合圖像的輪廓,、紋理等信息保留度以及視覺(jué)清晰度都有較好的提升。
中圖分類號(hào): TP391.41
文獻(xiàn)標(biāo)識(shí)碼: A
DOI: 10.19358/j.issn.2096-5133.2021.05.007
引用格式: 吳劍,,吳曉紅,,何小海,等. 基于NSST和NLMF的多聚焦圖像融合[J].信息技術(shù)與網(wǎng)絡(luò)安全,,2021,,40(5):39-44.
Multi-focus image fusion based on NSST and NLMF
Wu Jian1,,Wu Xiaohong1,He Xiaohai1,,Li Linyi2,,Qing Linbo1
(1.Institute of Image Information,School of Electronics and Information Engineering,, Sichuan University,,Chengdu 610065,China,; 2.The Second Research Institute of CAAC,,Chengdu 610041,China)
Abstract: In order to further improve the information richness, edge clarity and visual effect of the fused image, a multi-focus image fusion algorithm based on non-downsampling shear wave transform(NSST) combined with non-local mean filtering(NLMF) was designed. Firstly, the source image was multi-scale and multi-directionally decomposed by NSST transform to obtain high and low frequency subband coefficients. Secondly, the improved Sum Modified Laplacian and the non-local mean filter fusion method were used for the low-frequency subband coefficients to construct the fusion weights of low-frequency subband coefficient; For the high-frequency subband coefficients, fusion rules based on the combination of spatial frequency and energy based on correlation coefficients were used, and then phase consistency rules were added to construct the fusion weights of high-frequency subband coefficient; Finally, the final fusion image was obtained by inverse NSST transformation. The experimental results from three sets of different focused images show that: Whether the algorithm in this paper is in subjective vision or objective evaluation, the information retention and visual clarity of the fusion image′s contour and texture have been improved.
Key words : multi-focus image fusion,;non-local mean filtering;phase consistency,;correlation coefficient

0 引言

圖像技術(shù)的不斷發(fā)展以及現(xiàn)代光學(xué)成像設(shè)備的聚焦范圍局限性,,很難保證成像圖像都位于聚焦區(qū)域。多聚焦圖像融合技術(shù)將同一場(chǎng)景通過(guò)相同傳感器得到的不同聚焦信息有效地整合在一起,,形成一幅內(nèi)容豐富,、信息飽和的聚焦圖像,可應(yīng)用在遙感技術(shù),、醫(yī)學(xué)圖像和攝影等方面,。

基于變換域的融合方法將源圖像通過(guò)各種變換以得到多尺度、多方向的多幅子帶圖像,;然后,,通過(guò)各種融合規(guī)則對(duì)子帶圖像進(jìn)行融合;再通過(guò)反變換得到最終融合圖像,。非下采樣輪廓波變換(Non-Subsampled Contourlet Transform,,NSCT)[1]的提出主要解決了融合圖像的邊緣及輪廓表現(xiàn)得不是很明顯的問(wèn)題。但是此變換忽視了空間一致性,。通過(guò)NSCT[2-3]和脈沖耦合神經(jīng)網(wǎng)絡(luò)(Pulse Coupled Neural Network,,PCNN)的有效結(jié)合,不僅解決了空間一致性問(wèn)題,,同時(shí)也實(shí)現(xiàn)了更好的視覺(jué)效果,。由于非下采樣剪切波變換(Non-Subsampled Shearlet Transform,NSST)[4]具有多方向,、多尺度變換,,平移不變等良好特性,也被用于圖像融合,。稀疏表示(Sparse Representations,,SR)[5],、低秩表示(Low-Rank Representation,LRR)[6]最近幾年也相繼出現(xiàn)在圖像融合領(lǐng)域,,LRR在帶有噪聲的圖像融合中表現(xiàn)較為突出,。基于卷積神經(jīng)網(wǎng)絡(luò)(Convolutional Neural Networks,,CNN)的圖像融合技術(shù)[7]等也被提出,,并且達(dá)到了很好的視覺(jué)效果。

BUDADES A等提出的非局部均值濾波(Non-Local Mean Filter,,NLMF)算法[8]不僅能達(dá)到去除噪聲的目的,,還能在很大程度上保留圖像的結(jié)構(gòu)信息。



本文詳細(xì)內(nèi)容請(qǐng)下載:http://forexkbc.com/resource/share/2000003549




作者信息:

吳  劍1,,吳曉紅1,,何小海1,李林怡2,,卿粼波1

(1.四川大學(xué) 電子信息學(xué)院 圖像信息研究所,,四川 成都610065;

2.中國(guó)民航局第二研究所,,四川 成都610041)


此內(nèi)容為AET網(wǎng)站原創(chuàng),,未經(jīng)授權(quán)禁止轉(zhuǎn)載。