液晶与显示
液晶與顯示
액정여현시
Chinese Journal of Liquid Crystals and Displays
2015年
6期
1024-1031
,共8页
图像融合%非下采样剪切波变换%压缩感知%局部区域能量%局部区域方差
圖像融閤%非下採樣剪切波變換%壓縮感知%跼部區域能量%跼部區域方差
도상융합%비하채양전절파변환%압축감지%국부구역능량%국부구역방차
image fusion%non-subsampled Shearlet transform%compressed sensing%local area vari-ance%local area energy
针对非下采样剪切波变换(NSST)分解后图像的高频系数数据量较大且具有较大稀疏性的问题,本文提出一种基于 NSST 和压缩感知(CS)的图像融合算法。算法首先采用 NSST 对源图像进行分解;其次利用 CS 算法将 NSST 分解后的图像的高频系数进行压缩、融合及重构;然后利用“局部区域能量和局部区域方差”联合指导待融合图像的低频系数的融合;最后利用 NSST 逆变换重构融合图像。由于只需要对高频系数的压缩值进行融合,因此算法可以在不影响图像融合效果的同时加快代码的运行速度。仿真实验表明,该算法不需要原图像的先验知识就可以完成图像的融合,当图像的尺寸较大时,该算法牺牲了微小的融合图像质量,但却可以显著提高算法的运行速度,减小代码的时间代价,降低对硬件系统的要求。该算法对于融合系统的实时性要求提供了一种思路,具有较大的应用价值。
針對非下採樣剪切波變換(NSST)分解後圖像的高頻繫數數據量較大且具有較大稀疏性的問題,本文提齣一種基于 NSST 和壓縮感知(CS)的圖像融閤算法。算法首先採用 NSST 對源圖像進行分解;其次利用 CS 算法將 NSST 分解後的圖像的高頻繫數進行壓縮、融閤及重構;然後利用“跼部區域能量和跼部區域方差”聯閤指導待融閤圖像的低頻繫數的融閤;最後利用 NSST 逆變換重構融閤圖像。由于隻需要對高頻繫數的壓縮值進行融閤,因此算法可以在不影響圖像融閤效果的同時加快代碼的運行速度。倣真實驗錶明,該算法不需要原圖像的先驗知識就可以完成圖像的融閤,噹圖像的呎吋較大時,該算法犧牲瞭微小的融閤圖像質量,但卻可以顯著提高算法的運行速度,減小代碼的時間代價,降低對硬件繫統的要求。該算法對于融閤繫統的實時性要求提供瞭一種思路,具有較大的應用價值。
침대비하채양전절파변환(NSST)분해후도상적고빈계수수거량교대차구유교대희소성적문제,본문제출일충기우 NSST 화압축감지(CS)적도상융합산법。산법수선채용 NSST 대원도상진행분해;기차이용 CS 산법장 NSST 분해후적도상적고빈계수진행압축、융합급중구;연후이용“국부구역능량화국부구역방차”연합지도대융합도상적저빈계수적융합;최후이용 NSST 역변환중구융합도상。유우지수요대고빈계수적압축치진행융합,인차산법가이재불영향도상융합효과적동시가쾌대마적운행속도。방진실험표명,해산법불수요원도상적선험지식취가이완성도상적융합,당도상적척촌교대시,해산법희생료미소적융합도상질량,단각가이현저제고산법적운행속도,감소대마적시간대개,강저대경건계통적요구。해산법대우융합계통적실시성요구제공료일충사로,구유교대적응용개치。
After the image decomposition with NSST,the high-frequency coefficients have a large amount of data and greater sparsity.In order to obtain fusion results rapidly,an image fusion algo-rithm based on Non-subsampled Shearlet Transform (NSST)combined with Compressed Sensing (CS) is presented.Firstly,the source images are decomposed with NSST;secondly,the high-frequency sub-band coefficients of the decomposed images are compressed,fused and reconstructed by CS;then, based on local area variance and local area energy,the low-frequency coefficients was fused;finally, the inverse NSST is used to get the final fused image.Because only the compressed values of the high frequency coefficients are fused,the image fusion effects can’t be affected,and the running time of the algorithm can be reduced.In this paper,the multi-focus image,medical image and infrared and visible images are used to verify the effectiveness of the algorithm.The simulation results indicate that this algorithm can achieve the fusion of the image without prior knowledge of the original image. When the image size is larger,although the fusion image quality is sacrificed,it can significantly im-prove the speed to reduce the time cost and hardware requirements.The algorithm provides an idea on how to satisfy the real time requirements in the fusion system,which has a great practical value.