Journal of Textile Research ›› 2019, Vol. 40 ›› Issue (06): 125-132.doi: 10.13475/j.fzxb.20180505008

• Management & Information • Previous Articles     Next Articles

Nonwovens multi-focus fusion based on GHM multi-wavelet transform

CHEN Yang1, XIN Binjie2(), DENG Na1   

  1. 1. College of Electrical Electronic Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
    2. College of Fashion, Shanghai University of Engineering Science, Shanghai 201620, China
  • Received:2018-05-21 Revised:2019-02-21 Online:2019-06-15 Published:2019-06-25
  • Contact: XIN Binjie E-mail:xinbj@sues.edu.cn

Abstract:

Aiming at the problem that the fibers in some areas of the fabric image captured by the optical microscope under a single focal plane will be blurred, a multi-focus image fusion algorithm based on multi-wavelet transform was proposed. Using the self-built nonwoven fabric microscopic imaging system to acquire the fabric image sequences under different focal planes, the initial image sequence was subjected to critical sampling pre-filtering, and the two fusion methods were used to process the high and low frequencies of the images one by one. The original fabric fusion image was after wavelet fusion and inverse transformation, the original fusion image and the subsequent single-focus surface image were merged according to the above method. After the integration cycle was completed, all the fiber regions could be clearly displayed until the convergence was completed. Experiments show that the fusion method can digitally image the image sequence taken under different focus planes, achieve the effect of clear focusing and fusion of the fiber mesh in the full field of view within a single image, and provide the foundation for the computer image processing and measurement laying algorithm.

Key words: critical sampling prefiltering, GHM multi-wavelet, multi-focus image fusion, nonwoven image, microscopic imaging

CLC Number: 

  • TP311.1

Fig.1

Image acquisition device"

Fig.2

Nonwoven fabric sample images captured at different focal planes. (a)Image 1; (b) Image 2; (c) Image 3; (d) Image 4; (e) Image 5; (f) Image 6; (g) Image 7; (h) Image 8; (i) Image 9"

Fig.3

Multi-focus image fusion algorithm flow chart"

Fig.4

Multi-focus image fusion effect of each method. (a)Multi-wavelet;(b)Single wavelet;(c)Double wavelet;(d)Partial enlargement of multi-wavelet;(e)Partial enlargement of single wavelet;(f)Partial enlargement of double wavelet;(g)Contrast pyramid;(h)Laplacian pyramid;(i)Gradient pyramid;(j)Partial enlargement of contranst pyramid;(k)Partical enlargement of laplacian pyramid;(l)Partical enlargement of gradient pyramid"

Fig.5

Comparison of original and fusion effect diagrams of 6 kinds of samples. (a) 1#; (b) 2#; (c) 3#; (d) 1# after fusion; (e) 2# after fusion;(f) 3# after fusion; (g) 4#; (h) 5#; (i) 6#; (j) 4# after fusion; (k) 5# after fusion; (l) 6# after fusion"

Tab.1

Fusion image quality assessment form"

类型 H- g? MI MMSE PSNR
多小波变换 6.618 6 8.011 7 0.532 2 44.755 0 31.876 0
加权平均 6.458 5 1.783 4 0.861 5 48.865 3 31.843 8
单小波变换 6.367 7 4.751 7 0.787 8 52.281 5 31.198 0
双小波变换 6.336 3 7.954 3 0.681 5 55.529 7 30.771 0
拉普拉斯金字塔融合 5.632 1 7.926 5 0.543 8 58.908 4 30.757 1
对比度金字塔融合 4.409 8 7.944 3 0.564 5 79.210 3 29.284 4
梯度金字塔融合 6.862 6 3.778 2 0.629 4 57.966 0 30.511 0
[1] WANG R W, XU B. Multi-focus image fusion for accurate measurement of nonwoven structures[J]. Journal of Industrial Textiles, 2016,46(3):968-985.
[2] LI X, WANG M. Research of multi-focus image fusion algorithm based on Gabor filter bank[C]//2014 12th International Conference on Signal Processing (ICSP). Hangzhou: IEEE, 2014: 693-697.
[3] BENES R, DVORAK P, FAUNDEZ-ZANUY M, et al. Multi-focus thermal image fusion[J]. Pattern Recognition Letters, 2013,34(5):536-544.
[4] POHL C, GENDEREN J L V. Review article multisensor image fusion in remote sensing: concepts, methods and applications[J]. International Journal of Remote Sensing, 1998,19(5):823-854.
[5] TIAN J, CHEN L, MA L, et al. Multi-focus image fusion using a bilateral gradient-based sharpness criterion[J]. Optics Communications, 2011,284(1):80-87.
[6] LI H, MANJUNATH B S, MITRA S K. Multisensor image fusion using the wavelet transform[J]. Graphical Models and Image Processing, 1995,57(3):235-245.
[7] TESCHER A G. Applications of digital image processing XII[J]. Journal of Modern Optics, 1989,26(8):160.
[8] GOUTSIAS J, HEIJMANS H J A M. Nonlinear multiresolution signal decomposition schemes: I: Morphological pyramids[J]. IEEE Transactions on Image Processing, 2000,9(11):1862-1876.
pmid: 18262923
[9] 苗启广, 王宝树. 基于改进的拉普拉斯金字塔变换的图像融合方法[J]. 光学学报, 2007,27(9):1605-1610.
MIAO Qiguang, WANG Baoshu. Multi-sensor image fusion based on improved laplacian pyramid tran-sform[J]. Acta Optica Sinica, 2007,27(9):1605-1610.
[10] AKERMAN A. Pyramidal techniques for multi-sensor fusion[J]. Proceedings of SPIE, DOI: 10.1117/12.131644.
doi: 10.1117/12.2547015 pmid: 32665745
[11] ROCKINGER O. Image sequence fusion using a shift-invariant wavelet transform [C]//Proceedings of International Conference on Image Processing. California: IEEE Computer Society, 1997: 288-291.
[12] MA X, PENG L, XU H. Block-based assimilation of spatial frequency multi-focus image fusion algorithm[J]. Science Technology and Engineering, 2012,12(1):64-67.
[13] CAO L, JIN L, TAO H, et al. Multi-focus image fusion based on spatial frequency in discrete cosine transform domain[J]. IEEE Signal Processing Letters, 2015,22(2):220-224.
[14] HAGHIGHAT M B A, AGHAGOLZADEH A, SEYEDARABI H. Multi-focus image fusion for visual sensor networks in DCT domain[J]. Computers & Electrical Engineering, 2011,37(5):789-797.
[15] 楼建强, 李俊峰, 戴文战. 非下采样剪切波变换的医学图像融合[J]. 中国图象图形学报, 2017,22(11):1574-1583.
LOU Jianqiang, LI Junfeng, DAI Wenzhan. Medical image fusion using nonsubsampled shearlet trans-form[J]. Jouanal of Image and Oraphics, 2017,22(11):1574-1583.
[16] WANG R W, XU B, ZENG P, et al. Multi-focus image fusion for enhancing fiber microscopic images[J]. Textile Research Journal, 2012,82(4):352-361.
doi: 10.1177/0040517511407377
[17] WANG R, XU B, LI C. Accurate fiber orientation measurements in nonwovens using a multi-focus image fusion technique[J]. Textile Research Journal, 2014,84(2):115-124.
[18] XU X, WANG R W. A Study on Multi-focus images fusion technology based on fiber boundaries[J]. Advannaturalced Materials Research, 2014,900:547-553.
[19] 杨晓蕊, 葛广英, 朱荣华, 等. 基于小波变换的卫星遥感图像融合与分割[J]. 聊城大学学报(自然科学版), 2018,31(4):18-26.
YANG Xiaorui, GE Guangying, ZHU Ronghua, et al. Remote sensing image processing of meteorological satellite[J]. Journal of Liaocheng Univesity(Natural Science Edition), 2018,31(4):18-26.
[20] WANG H H. A new multiwavelet-based approach to image fusion[J]. Journal of Mathematical Imaging & Vision, 2004,21(2):177-192.
[21] 宁梓淯, 李红岩, 李萌. 基于GHM多小波的多模态医学图像融合算法研究[J]. 电子测试, 2013(15):49-50.
NING Ziyu, LI Hongyan, LI Meng. The study of multi-modality medical image fusion algorithm based on GHM multiwavelet[J]. Electronic Test, 2013(15):49-50.
[22] HELLER P, STRANG G, TOPIWALA P, et al. The application of multiwavelet filter banks to signal and image processing[J]. IEEE Trans Image Process, 1999,8:548-563.
doi: 10.1109/83.753742 pmid: 18262898
[1] . Detection of fabric defects based on Gabor filters and Isomap [J]. JOURNAL OF TEXTILE RESEARCH, 2017, 38(03): 162-167.
[2] . Study on simulation of flexible fabric bend surface based on four-point interpolation method [J]. Journal of Textile Research, 2015, 36(06): 50-54.
[3] . Fabric defect detection of statistic aberration feature based on GMRF model [J]. JOURNAL OF TEXTILE RESEARCH, 2013, 34(4): 137-142.
[4] . Research of mixture feature aberrance fabric defect recognition based on self-adaptive disperse wavelet transform [J]. JOURNAL OF TEXTILE RESEARCH, 2013, 34(1): 133-137.
[5] . Fabric Defect Clustering Analysis based on Artificial Neural Network [J]. JOURNAL OF TEXTILE RESEARCH, 2011, 32(9): 29-33.
[6] YANG Xiaobo. Detection of fabric defects based on Gabor filter [J]. JOURNAL OF TEXTILE RESEARCH, 2010, 31(4): 55-59.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!