Multi-modality Image Fusion Algorithm Based on NSST-DWT-ICSAPCNN
-
摘要: 为了增加融合图像的信息量,结合非下采样剪切波变换(Non-Subsampled Shearlet Transform, NSST)和离散小波变换(Discrete Wavelet Transform, DWT)的互补优势,提出了改进的多模态图像融合方法。采用NSST对两幅源图像进行多尺度、多方向的分解,得到相应的高频子带和低频子带;利用DWT将低频子带进一步分解为低频能量子带和低频细节子带,并利用最大值选择规则融合能量子带;采用改进连接强度的自适应脉冲耦合神经网络(Improved Connection Strength Adaptive Pulse Coupled Neural Network, ICSAPCNN)分别融合细节子带和高频子带,并对能量子带和细节子带进行DWT逆变换,得到融合的低频子带;采用NSST逆变换重构出细节信息丰富的融合图像。实验证明,提出的算法在主观视觉和客观评价方面均优于其他几种算法,且能同时适用于红外与可见光源图像、医学源图像的融合。
-
关键词:
- 多模态图像 /
- 图像融合 /
- 离散小波变换 /
- 自适应脉冲耦合神经网络 /
- 非下采样剪切波变换
Abstract: To increase the information of the fused image, this paper proposes an improved multi-modality image fusion algorithm that combines the complementary advantages of the non-subsampled shearlet transform (NSST) and discrete wavelet transform (DWT). NSST was used to decompose the two source images in multiscale and multi-direction to obtain the corresponding high-frequency and low-frequency sub-bands. The low-frequency sub-bands were further decomposed into low-frequency energy sub-bands and low-frequency detail sub-bands by the DWT, and the low-frequency energy sub-bands were fused by the maximum selection rules. An adaptive pulse-coupled neural network with improved connection strength (ICSAPCNN) was used to fuse the detailed sub-bands and high-frequency sub-bands, and the energy sub-bands and detailed sub-bands were fused by inverse DWT to obtain the fused low-frequency sub-bands. The NSST inverse transform was used to reconstruct the fusion image with rich details. The experimental results verified that the proposed algorithm is superior to the other algorithms in both subjective vision and objective evaluation and can be applied to the fusion of both infrared and visible source images and medical source images. -
表 1 两组红外与可见光图像客观评估指标值
Table 1. Values of objective evaluation index for 2 groups of infrared and visible images
Images Metrics ASR[7] CNN[8] NSCT-APCNN[9] NSST-APCNN[10] NSST-DWT-ICSAPCNN Road QEN 7.1339 7.4964 7.3703 7.331 7.4247 QMI 3.0046 3.2051 3.0786 3.2336 3.0167 QSD 38.3922 48.4964 45.5887 44.5039 51.7009 QVIFF 0.4469 0.5842 0.5206 0.5078 0.6275 QIE 0.8055 0.8054 0.8052 0.8053 0.8062 QTE 0.5749 0.5207 0.5401 0.5454 0.5886 Tree QEN 6.3464 7.1022 6.9596 6.9152 7.1043 QMI 1.2234 1.1755 1.3188 1.7535 2.1287 QSD 24.3398 37.2648 32.8565 31.4357 34.8227 QVIFF 0.3177 0.4706 0.3822 0.3798 0.4261 QIE 0.8033 0.8043 0.8035 0.8035 0.8040 QTE 0.4090 0.2861 0.2981 0.3279 0.3282 表 2 六组红外与可见光图像客观评估指标平均值
Table 2. Average values of objective evaluation index for 6 groups of infrared and visible images
Metrics ASR[7] CNN[8] NSCT-APCNN[9] NSST-APCNN[10] NSST-DWT-ICSAPCNN QEN 6.2345 6.8978 6.9633 6.9094 7.0247 QMI 2.8656 3.2917 3.6756 4.1826 4.3438 QSD 24.7236 38.7514 37.0670 35.4332 38.6467 QVIFF 0.3761 0.5399 0.5445 0.5032 0.5514 QIE 0.8063 0.8076 0.8086 0.8090 0.8097 QTE 0.7311 0.6582 0.6534 0.6971 0.6841 表 3 两组医学图像客观评估指标值
Table 3. Values of objective evaluation index for 2 groups of medical images
Images Metrics ASR[7] CNN[8] NSCT-APCNN[9] NSST-APCNN[10] NSST-DWT-ICSAPCNN fatal stroke QEN 4.5440 4.8244 5.0632 4.8747 5.1693 QMI 2.5170 2.8593 2.7118 2.8665 2.7618 QSD 72.3351 90.2448 90.0339 84.2365 88.4652 QVIFF 0.2691 0.3333 0.3259 0.3100 0.3131 QIE 0.8051 0.8055 0.8054 0.8051 0.8054 QTE 0.6663 0.7252 0.7277 0.7102 0.7896 meningoma QEN 4.1794 4.2013 4.3485 4.6852 4.6013 QMI 2.5408 2.9163 2.9516 3.0001 3.0665 QSD 72.0789 88.7470 92.8914 90.2904 91.3901 QVIFF 0.4940 0.6192 0.6279 0.5624 0.6292 QIE 0.8056 0.8059 0.8062 0.8064 0.8064 QTE 0.7907 0.7923 0.8445 0.8733 0.8804 表 4 八组医学图像客观评估指标平均值
Table 4. Average values of objective evaluation index for 8 groups of medical images
Metrics ASR[7] CNN[8] NSCT-APCNN[9] NSST-APCNN[10] NSST-DWT-ICSAPCNN QEN 4.3242 4.6515 4.7943 4.7715 4.8254 QMI 2.6843 2.9002 2.8697 2.8998 2.9848 QSD 66.6290 83.3568 85.9244 85.7634 85.7755 QVIFF 0.3561 0.4417 0.4562 0.4491 0.4647 QIE 0.8057 0.8061 0.8061 0.8062 0.8062 QTE 0.7033 0.7494 0.7608 0.7593 0.7818 -
[1] YANG Y, QUE Y, HUANG S, et al. Multimodal sensor medical image fusion based on type-2 fuzzy logic in NSCT domain[J]. IEEE Sensors Journal, 2016, 16(10): 3735-3745. doi: 10.1109/JSEN.2016.2533864 [2] LI G, LIN Y, QU X. An infrared and visible image fusion method based on multi-scale transformation and norm optimization[J]. Information Fusion, 2021, 71: 109-129. doi: 10.1016/j.inffus.2021.02.008 [3] LI X, ZHOU F, TAN H. Joint image fusion and denoising via three-layer decomposition and sparse representation[J]. Knowledge-Based Systems, 2021, 224: 107087. doi: 10.1016/j.knosys.2021.107087 [4] XU H, MA J. EMFusion: An unsupervised enhanced medical image fusion network[J]. Information Fusion, 2021, 76: 177-186. . doi: 10.1016/j.inffus.2021.06.001 [5] Bulanon D M, Burks T F, Alchanatis V. Image fusion of visible and thermal images for fruit detection[J]. Biosystems Engineering, 2009, 103(1): 12-22. doi: 10.1016/j.biosystemseng.2009.02.009 [6] ZHAN L, ZHUANG Y, HUANG L. Infrared and visible images fusion method based on discrete wavelet transform[J]. J. Comput. , 2017, 28(2): 57-71. [7] LIU Y, WANG Z. Simultaneous image fusion and denoising with adaptive sparse representation[J]. IET Image Processing, 2015, 9(5): 347-357. doi: 10.1049/iet-ipr.2014.0311 [8] LIU Y, CHEN X, CHENG J, et al. Infrared and visible image fusion with convolutional neural networks[J]. International Journal of Wavelets, Multiresolution and Information Processing, 2018, 16(3): 1850018. doi: 10.1142/S0219691318500182 [9] ZHU Z, ZHENG M, QI G, et al. A phase congruency and local Laplacian energy based multi-modality medical image fusion method in NSCT domain[J]. IEEE Access, 2019, 7: 20811-20824. doi: 10.1109/ACCESS.2019.2898111 [10] ZHANG L, ZENG G, WEI J, et al. Multi-modality image fusion in adaptive-parameters SPCNN based on inherent characteristics of image[J]. IEEE Sensors Journal, 2019, 20(20): 11820-11827. [11] 张蕾. 采用改进平均梯度与自适应PCNN的图像融合[J]. 计算机应用与软件, 2021, 38(3): 218-223. doi: 10.3969/j.issn.1000-386x.2021.03.033ZHANG Lei. Image fusion using improved average gradient and adaptive PCNN[J]. Computer Application and Software, 2021, 38(3): 218-223. doi: 10.3969/j.issn.1000-386x.2021.03.033 [12] YIN M, LIU X, LIU Y, et al. Medical image fusion with parameter- adaptive pulse coupled neural network in nonsubsampled shearlet transform domain[J]. IEEE Transactions on Instrumentation and Measurement, 2018, 68(1): 49-64. [13] Diwakar M, Singh P, Shankar A. Multi-modal medical image fusion framework using co-occurrence filter and local extrema in NSST domain[J]. Biomedical Signal Processing and Control, 2021, 68: 102788. doi: 10.1016/j.bspc.2021.102788 [14] 邓辉, 王长龙, 胡永江, 等. 脉冲耦合神经网络在图像融合中的应用研究[J]. 电光与控制, 2019, 26(11): 19-24. https://www.cnki.com.cn/Article/CJFDTOTAL-DGKQ201911006.htmDENG Hui, WANG Changlong, HU Yongjiang, et al. Application of pulse coupled neural network in image fusion[J]. Electronics Options & Contral, 2019, 26(11): 19-24. https://www.cnki.com.cn/Article/CJFDTOTAL-DGKQ201911006.htm [15] 杨风暴, 董安冉, 张雷, 等. DWT、NSCT和改进PCA协同组合红外偏振图像融合[J]. 红外技术, 2017, 39(3): 201-208. http://hwjs.nvir.cn/article/id/hwjs201703001YANG Fengbao, DONG Aran, ZHANG Lei, et al. Infrared Polarization Image fusion using the synergistic combination of DWT, NSCT and improved PCA[J]. Infrared Technology, 2017, 39(3): 201-208. http://hwjs.nvir.cn/article/id/hwjs201703001 [16] TAN W, Tiwari P, Pandey H M, et al. Multimodal medical image fusion algorithm in the era of big data[J]. Neural Computing and Applications, 2020: 1-21. [17] JIANG L, ZHANG D, CHE L. Texture analysis-based multi-focus image fusion using a modified Pulse-Coupled Neural Network (PCNN)[J]. Signal Processing: Image Communication, 2021, 91: 116068. doi: 10.1016/j.image.2020.116068 [18] LIU Z, Blasch E, XUE Z, et al. Objective assessment of multiresolution image fusion algorithms for context enhancement in night vision: a comparative study[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 34(1): 94-109.