王琦 謝淑翠 王至琪
關(guān)鍵詞: 超分辨率重建; 稀疏表示; [L1]范數(shù)優(yōu)化; 字典學(xué)習(xí); 粒子群優(yōu)化算法; 特征提取算子
中圖分類號: TN911.73?34 ? ? ? ? ? ? ? ? ? ? ? 文獻(xiàn)標(biāo)識碼: A ? ? ? ? ? ? ? ? ? ? ? ? 文章編號: 1004?373X(2019)03?0045?04
Abstract: A single image super?resolution reconstruction method based on sparse representation of image blocks is proposed. The proposed reconstruction process provides a better sparse solution, and is used for [L1] norm optimization process. The efficient feature extraction operator is used in optimization process to ensure the accuracy of high?resolution image blocks. The particle swarm optimization (PSO) algorithm is used to select the best adaptive sparse regularization parameters, which makes the global reconstruction process robust. The dictionary?coupled training mode is used to learn the dictionaries. Various image quality evaluation criteria prove this method has better advantage than the existing super?resolution reconstruction methods.
Keywords: super resolution reconstruction; sparse representation; [L1] norm optimization; dictionary learning; PSO algorithm; feature extraction operator
超分辨率重建(SRR)的過程克服了低成本成像傳感器固有分辨率的問題,可以更好地利用低分辨率(LR)成像系統(tǒng)提供高分辨率(HR)解決方案。該技術(shù)的實(shí)現(xiàn)主要有兩類方法:基于重建的插值;基于學(xué)習(xí)的方法。重建主要是對多幀低分辨率圖像進(jìn)行融合,但是低分辨率圖像較少的情況下重建效果不佳。近年來,基于學(xué)習(xí)的方法吸引了很多人的關(guān)注[1?4],它以待重建圖像為依據(jù),用學(xué)習(xí)過程中獲得的知識對重建圖像中的信息進(jìn)行補(bǔ)充,充分利用圖像的先驗(yàn)知識恢復(fù)圖像,且克服了重建插值過程中提高重建倍數(shù)困難的局限[5?6]。
隨著壓縮感知和機(jī)器學(xué)習(xí)研究的深入,基于學(xué)習(xí)的超分辨率方法已取得了一系列成果。文獻(xiàn)[3]將壓縮感知理論與稀疏編碼相結(jié)合,提出基于稀疏表示的圖像超分辨率算法,它的主要工作集中在利用外部訓(xùn)練圖像集學(xué)習(xí)得到一對LR/HR字典,求解出低分辨率圖像塊在LR字典中的稀疏系數(shù),再利用稀疏系數(shù)與HR字典結(jié)合重建高分辨率圖像。但自適應(yīng)能力差,重構(gòu)的圖像偽影嚴(yán)重。本文采用粒子群優(yōu)化算法優(yōu)化自適應(yīng)稀疏正則化參數(shù)。在凸優(yōu)化過程中,還引入了有效的特征提取算子,以獲得更好的稀疏解,準(zhǔn)確預(yù)測HR圖像。
當(dāng)輸入低分辨率圖像塊時(shí),首先計(jì)算在低分辨率字典下的稀疏表示系數(shù)[α],接著利用此稀疏系數(shù)[α]和高分辨率字典進(jìn)行重建。高分辨率圖像塊[iH]由稀疏系數(shù)[α]進(jìn)行稀疏表示,即:
從視覺感知來看,雙三次插值處理效果較差,因?yàn)檫@種插值技術(shù)缺乏高頻細(xì)節(jié),因而產(chǎn)生過平滑的HR圖像,來自NE的結(jié)果產(chǎn)生更銳利的邊緣。而文獻(xiàn)[3]的重建方法是一種被廣泛使用的改造技術(shù)。但隨著放大倍數(shù)的增加,輸出質(zhì)量下降。這是由于稀疏正則參數(shù)和一般匹配約束的固定選擇造成的。而本文提出的SRR方法具有較好的特征提取和最優(yōu)懲罰參數(shù),提高了解的稀疏性,同時(shí)減少了振鈴偽影的數(shù)量。
為了驗(yàn)證算法的有效性,采用峰值信噪比(PSNR)[15]和結(jié)構(gòu)相似性(SSIM)[16]作為評價(jià)指標(biāo),比較結(jié)果見表1。
從表1中可以看出,所提出方法的峰值信噪比更高,且結(jié)構(gòu)相似度也高于對比方法。
本文提出一種基于稀疏表示的高效單幅圖像超分辨率重建的方法。結(jié)合字典訓(xùn)練來學(xué)習(xí)低分辨率字典和高分辨率字典。在優(yōu)化過程中,采用Gabor濾波器對不同頻率和方向的特征進(jìn)行跟蹤。實(shí)驗(yàn)結(jié)果表明,與傳統(tǒng)的超分辨率重建算法相比,該算法具有簡單實(shí)用的優(yōu)點(diǎn),且具有很好的準(zhǔn)確性、魯棒性,能較好地保留圖像的更多細(xì)節(jié)信息,改善圖像信噪比,具有更好的視覺效果。
參考文獻(xiàn)
[1] TANG Y, YAN P, YUAN Y, et al. Single?image super?resolution via local learning [J]. International journal of machine learning cybernetics, 2011, 2(1): 15?23.
[2] HE C, LIU L, XU L, et al. Learning based compressed sen?sing for SAR image super?resolution [J]. IEEE journal of selec?ted topics in applied earth observations and remote sensing, 2012, 5(4): 1272?1281.
[3] YANG J, MEMBER S, WRIGHT J, et al. Image super?resolution via sparse representation [J]. IEEE transactions on image processing, 2010, 19(11): 2861?2873.
[4] PELEG T, MEMBER S, FELLOW M E. A statistical prediction model based on sparse representations for single image super?resolution [J]. IEEE transactions on image processing, 2014, 23(6): 2569?2582.
[5] WEI C P, CHAO Y W, YEH Y R, et al. Locality sensitive dictionary learning for sparse representation based classification [J]. Pattern recognition, 2013, 46(5): 1277?1287.
[6] YANG J, WANG Z, LIN Z, et al. Couple dictionary training for image super?resolution [J]. IEEE transactions on image processing, 2012, 21(8): 3467?3478.
[7] 首照宇,吳廣祥,陳利霞.基于字典學(xué)習(xí)和非局部相似的超分辨率重建[J].計(jì)算機(jī)應(yīng)用,2014,34(11):3300?3303.
SHOU Zhaoyu, WU Guangxiang, CHEN Lixia. Super?resolution reconstruction based on dictionaries learning and non?local similarity [J]. Computer applications, 2014, 34(11): 3300?3303.
[8] DONOHO D L. For most large underdetermined systems of equations the minimal L1?norm near?solution approximates the sparsest near?solution [J]. Communication pure, 2006, 59(6): 907?934.
[9] FREEMAN W T, JONES T R, PASZTOR E C. Example?based super?resolution [J]. IEEE computer graphics and applications, 2002, 22(2): 56?65.
[10] ZHANG A, GUAN C, JIANG H, et al. An image super?resolution scheme based on compressive sensing with PCA sparse representation [C]// 2012 International Workshop on Digital Forensics and Watermarking. Berlin: Springer, 2012: 495?506.
[11] ROSLAN R, JAMIL N. Texture feature extraction using 2?D Gabor filters [C]// 2012 International Symposium on Computer Applications and Industrial Electronics. [S.l.]: Mendeley: 2012: 173?178.
[12] CAND?S E J, WAKIN M B, BOYD S P. Enhancing sparsity by reweighted ?1 minimization [J]. Journal of Fourier analysis and applications, 2008, 14(5): 877?905.
[13] BAHY R M, SALAMA G I, MAHMOUD T A. A no?reference blur metric guided fusion technique for multi?focus images [C]// 2011 National Radio Science Conference. Cairo: IEEE, 2011: 1?9.
[14] CHANG H, YEUNG D, XIONG Y, et al. Super?resolution through neighbor embedding [C]// Proceedings of 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE, 2004: 275?282.
[15] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity [J]. IEEE transactions on image processing, 2004, 13(4): 600?612.
[16] ZHANG L, ZHANG L, MOU X, et al. Correspondence FSIM: a feature similarity index for image [J]. IEEE transactions on image processing, 2011, 20(8): 2378?2386.