基于经验小波的太阳能电池缺陷图像融合
|
摘要
为解决太阳能电池的弱缺陷检测问题,提出一种基于二维张量经验小波的多光谱图像融合算法。使用一组特定波长的光源采集太阳能电池片图像信息,对图像进行顶帽变换抑制背景噪声;使用经验小波变换对预处理图像进行分解,分别对获得的高低频子带图像采用基于极大值的显著性融合规则进行融合,将融合后的高低频子带图像进行小波反变换获得最终的融合图像。在相同的采集条件下获取五类色差电池片图像,进行算法测试试验,并从图像视觉效果和客观评价指标两方面与其他算法分析比较。试验结果表明,此算法不仅具有良好的适应性,而且在保持光谱信息和抑制噪声等方面均取得良好的效果。
To solve the problem of the weak defect detection of solar cells,a multispectral image fusion algorithm based on 2D tensor empirical wavelet transform was proposed. The image information of solar cells was collected by using a set of specific wavelengths' lights,and the noise was suppressed by using top-hat transformation. The preprocessed images were decomposed using empirical wavelet transform,and the obtained subband images of high and lowfrequency were fused using the saliency rules based on maximum value. The fused subband images of high and lowfrequency were transformed into the final image through inverse empirical wavelet transform. Cell images of five types of chromatic aberrations were acquired under the same acquisition conditions for testing algorithm,and were compared with other algorithms from two aspects of image visual effect and objective evaluation indexes.The experimental results showed that the proposed algorithm had good adaptability and good performance in the aspects of maintaining spectral information and suppressing noise.
To solve the problem of the weak defect detection of solar cells,a multispectral image fusion algorithm based on 2D tensor empirical wavelet transform was proposed. The image information of solar cells was collected by using a set of specific wavelengths' lights,and the noise was suppressed by using top-hat transformation. The preprocessed images were decomposed using empirical wavelet transform,and the obtained subband images of high and lowfrequency were fused using the saliency rules based on maximum value. The fused subband images of high and lowfrequency were transformed into the final image through inverse empirical wavelet transform. Cell images of five types of chromatic aberrations were acquired under the same acquisition conditions for testing algorithm,and were compared with other algorithms from two aspects of image visual effect and objective evaluation indexes.The experimental results showed that the proposed algorithm had good adaptability and good performance in the aspects of maintaining spectral information and suppressing noise.
引文
[1]周晓波,程海龙,贾琦.图像分块融合算法速度优化处理研究[J].北京交通大学学报,2014,38(5):33-36.ZHOU Xiaobo,CHENG Hailong,JIA Qi.Optimization of image block fusion algorithm in speed[J].Journal of Beijing Jiaotong University,2014,38(5):33-36.
[2]WANG W,CHANG F.A multi-focus image fusion method based on laplacian pyramid[J].Journal of Computers,2011,6(12):2559-2566.
[3]KAVITHA C T,CHELLAMUTHU C,RAJESH R.Medical image fusion using combined discrete w avelet and ripplet transforms[J].Procedia Engineering,2012,38(38):813-820.
[4]GILLES J.Empirical wavelet transform[J].IEEE Transactions on Signal Processing,2013,61(16):3999-4010.
[5]BORJI A,ITTI L.State-of-the-art in visual attention modeling[J].IEEE Transaction on Pattern Analysis and M achine Intelligence,2013,35(1):185-207.
[6]BORJI A,SIHITE D N,ITTI L.Quantitative analysis of human-model agreement in visual saliency modeling:a comparative study[J].IEEE Transaction on Image Processing,2013,22(1):55-69.
[7]GOFERMAN S,ZELNIK-MANOR L,TAL A.Contextaw are saliency detection[J].IEEE Trans Pattern Anal M ach Intell,2012,34(10):1915-1926.
[8]HOU Xiaodi,ZHANG Liqing.Saliency detection:a spectral residual approach[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataw ay,USA:IEEE Computer Society,2007:1-8.
[9]BAVIRISETTI D P,DHULI R.Multi-focus image fusion using maximum symmetric surround saliency detection[J].Elcvia Electronic Letters on Computer Vision&Image Analysis,2016,14(2):58-73.
[10]QI S,MA J,LI H,et al.Infrared small target enhancement via phase spectrum of quaternion fourier transform[J].Infrared Physics&Technology,2014,62(2):50-58.
[11]刘斌,祝青,胡福强,等.基于采样二通道不可分小波的多光谱图像融合[J].电子学报,2013,41(4):710-716.LIU Bin,ZHU Qing,HU Fuqiang,et al.M ulti-spectral image fusion method based on sampled tw o channel nonseparable w avelets[J].Acta Electronica Sinica,2013,41(4):710-716.
[12]段建民,战宇辰,刘冠宇.基于TopHat分割和曲线模型的三车道检测方法[J].北京工业大学学报,2016,42(8):1174-1181.DUAN Jianmin,ZHAN Yuchen,LIU Guanyu.Threelane detection method based on top-hat segmentation and curve models[J].Journal of Beijing University of Technology,2016,42(8):1174-1181.
[13]陈林.基于经验小波变换的多曝光图像融合方法的研究[D].长春:吉林大学,2017:30-40CHEN Lin.Research of multi-exposure image fusion based on empirical w avelet transform[D].Changchun:Jilin University,2017:30-40.
[14]王达,卞红雨.水下声图像多分辨率融合研究[J].武汉大学学报(信息科学版),2015,40(1):77-82.WANG Da,BIAN Hongyu.Underw ater acoustic image multiresolution fusion research[J].Geomatics and Information Science of Wuhan University,2015,40(1):77-82.
[15]邹勤,贾永红.一种基于形态金字塔的遥感影像融合方法及其性能评价[J].武汉大学学报(信息科学版),2006,30(11):971-974.ZOU Qin,JIA Yonghong.Fusion of remote sensing images based on morphological pyramid and its performance evaluation[J].Geomatics and Information Science of Wuhan University,2006,30(11):971-974.
[16]魏兴瑜,周涛,陆惠玲,等.基于双树复小波变换的PET/CT自适应融合算法[J].计算机科学与探索,2015,9(3):360-367.WEI Xingyu,ZHOU Tao,LU Huiling,et al.Selfadaption fusion algorithm of PET/CT based on dual-tree complex w avelet transform[J].Journal of Frontiers of Computer Science and Technology,2015,9(3):360-367.
[17]NAMRATHA H N,RAGHU M T.Remote sensing satellite image fusion using fast curvelet transforms[J].International Journal of Science and Research,2015:1537-1542.
[18]SHEN Y,REN E,DANG J W,et al.A nonsubsampled contourlet transform based medical image fusion method[J].Information Technology Journal,2013,12(4):749-755.(:)
[2]WANG W,CHANG F.A multi-focus image fusion method based on laplacian pyramid[J].Journal of Computers,2011,6(12):2559-2566.
[3]KAVITHA C T,CHELLAMUTHU C,RAJESH R.Medical image fusion using combined discrete w avelet and ripplet transforms[J].Procedia Engineering,2012,38(38):813-820.
[4]GILLES J.Empirical wavelet transform[J].IEEE Transactions on Signal Processing,2013,61(16):3999-4010.
[5]BORJI A,ITTI L.State-of-the-art in visual attention modeling[J].IEEE Transaction on Pattern Analysis and M achine Intelligence,2013,35(1):185-207.
[6]BORJI A,SIHITE D N,ITTI L.Quantitative analysis of human-model agreement in visual saliency modeling:a comparative study[J].IEEE Transaction on Image Processing,2013,22(1):55-69.
[7]GOFERMAN S,ZELNIK-MANOR L,TAL A.Contextaw are saliency detection[J].IEEE Trans Pattern Anal M ach Intell,2012,34(10):1915-1926.
[8]HOU Xiaodi,ZHANG Liqing.Saliency detection:a spectral residual approach[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataw ay,USA:IEEE Computer Society,2007:1-8.
[9]BAVIRISETTI D P,DHULI R.Multi-focus image fusion using maximum symmetric surround saliency detection[J].Elcvia Electronic Letters on Computer Vision&Image Analysis,2016,14(2):58-73.
[10]QI S,MA J,LI H,et al.Infrared small target enhancement via phase spectrum of quaternion fourier transform[J].Infrared Physics&Technology,2014,62(2):50-58.
[11]刘斌,祝青,胡福强,等.基于采样二通道不可分小波的多光谱图像融合[J].电子学报,2013,41(4):710-716.LIU Bin,ZHU Qing,HU Fuqiang,et al.M ulti-spectral image fusion method based on sampled tw o channel nonseparable w avelets[J].Acta Electronica Sinica,2013,41(4):710-716.
[12]段建民,战宇辰,刘冠宇.基于TopHat分割和曲线模型的三车道检测方法[J].北京工业大学学报,2016,42(8):1174-1181.DUAN Jianmin,ZHAN Yuchen,LIU Guanyu.Threelane detection method based on top-hat segmentation and curve models[J].Journal of Beijing University of Technology,2016,42(8):1174-1181.
[13]陈林.基于经验小波变换的多曝光图像融合方法的研究[D].长春:吉林大学,2017:30-40CHEN Lin.Research of multi-exposure image fusion based on empirical w avelet transform[D].Changchun:Jilin University,2017:30-40.
[14]王达,卞红雨.水下声图像多分辨率融合研究[J].武汉大学学报(信息科学版),2015,40(1):77-82.WANG Da,BIAN Hongyu.Underw ater acoustic image multiresolution fusion research[J].Geomatics and Information Science of Wuhan University,2015,40(1):77-82.
[15]邹勤,贾永红.一种基于形态金字塔的遥感影像融合方法及其性能评价[J].武汉大学学报(信息科学版),2006,30(11):971-974.ZOU Qin,JIA Yonghong.Fusion of remote sensing images based on morphological pyramid and its performance evaluation[J].Geomatics and Information Science of Wuhan University,2006,30(11):971-974.
[16]魏兴瑜,周涛,陆惠玲,等.基于双树复小波变换的PET/CT自适应融合算法[J].计算机科学与探索,2015,9(3):360-367.WEI Xingyu,ZHOU Tao,LU Huiling,et al.Selfadaption fusion algorithm of PET/CT based on dual-tree complex w avelet transform[J].Journal of Frontiers of Computer Science and Technology,2015,9(3):360-367.
[17]NAMRATHA H N,RAGHU M T.Remote sensing satellite image fusion using fast curvelet transforms[J].International Journal of Science and Research,2015:1537-1542.
[18]SHEN Y,REN E,DANG J W,et al.A nonsubsampled contourlet transform based medical image fusion method[J].Information Technology Journal,2013,12(4):749-755.(:)