Super-resolution reconstruction of fiber optic coil image based on lightweight network

ZHANG Qianchuang; GUO Chenxia; YANG Ruifeng; CHEN Xiaole

doi:10.5768/JAO202243.0502005

Journal of Applied Optics > 2022 > 43(5): 913-920. > DOI: 10.5768/JAO202243.0502005

ZHANG Qianchuang, GUO Chenxia, YANG Ruifeng, CHEN Xiaole. Super-resolution reconstruction of fiber optic coil image based on lightweight network[J]. Journal of Applied Optics, 2022, 43(5): 913-920. DOI: 10.5768/JAO202243.0502005

Citation:

PDF (3485 KB)

Super-resolution reconstruction of fiber optic coil image based on lightweight network

1.
School of Instrument and Electronics, North University of China, Taiyuan 030051, China
2.
Automated Test Equipment and System Engineering Technology Research Center of Shanxi Province, Taiyuan 030051, China

More Information

Received Date: January 17, 2022
Revised Date: May 04, 2022
Available Online: August 15, 2022

Graphical Abstract

Abstract

Abstract

In order to improve the winding image resolution of the optical fiber coils and reduce the memory and computational overhead caused by the deep learning model, a dual-branch network that can simultaneously extract the gradient information and image information was proposed. The image features in the network path were extracted by using the advantages of speediness and light weight of lightweight residual blocks, and the multi-stage residual feature transfer mechanism was also introduced. Under the combined action of gradient information and feature transfer, the network could retain the rich geometric structure information, which made the edge details of the reconstructed image clearer. The experimental results show that, the proposed model achieves superior performance with fewer parameters and a running time of 0.018 s. Under the double, triple and quadruple scale factors, the peak signal-to-noise ratio is 44.08 dB, 41.35 dB and 38.97 dB, respectively and the structural similarity index is 0.985 8, 0.979 3 and 0.976 9, respectively, which are both superior to other existing methods and provide a strong guarantee for subsequent quality detection of optical fiber coils.
- optical fiber coil,
- deep learning,
- super-resolution,
- gradient information extraction,
- feature transfer

FullText(HTML)

References (20)

References

[1]	龚智炳. 面向21世纪的新型陀螺仪——光纤陀螺[J]. 应用光学,1997,18(3):37-41. GONG Zhibing. A new type of gyroscope for the 21st century-fiber optic gyroscope[J]. Journal of Applied Optics,1997,18(3):37-41.
[2]	陶洪久, 柳健, 田金文. 基于小波变换和插值的超分辨率图像处理算法[J]. 武汉理工大学报,2002(8):63-66. TAO Hong, LIU Jian, TIAN Jinwen. A super-resolution image processing algorithm based on wavelet transform and interpolation[J]. Journal of Wuhan University of Technology,2002(8):63-66.
[3]	YANG J C, WRIGHT J, HUANG T S. Image super-resolution via sparse representation[J]. IEEE Transactions on Image Processing,2010,19(11):2861-2873. doi: 10.1109/TIP.2010.2050625
[4]	HUANG J B, SINGH A, AHUJA N. Single image super-resolution from transformed self-exemplars [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA. June 7-12, 2015, New York: IEEE, 2015: 5197-5206.
[5]	杨书广. 基于深度反向投影的感知增强超分辨率重建模型[J]. 应用光学,2021,42(4):691-697. YANG Shuguang. A perceptually enhanced super-resolution reconstruction model based on depth back projection[J]. Journal of Applied Optics,2021,42(4):691-697.
[6]	DONG C, LOY C C, HE K, et al. Image super-resolution using deep convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(2):295-307. doi: 10.1109/TPAMI.2015.2439281
[7]	KIM J, LEE J K, LEE K M. Accurate image super-resolution using very deep convolutional networks [C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, , Las Vegas, NV, USA, June 27-30, 2016. New York: IEEE, 2016: 1646-1654.
[8]	LIM B, SON S, KIM H. Enhanced deep residual networks for single image super-resolution [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, July 21-26, 2017. New York: IEEE, 2017: 1132-1140.
[9]	高青青, 赵建伟, 周正华. 基于递归多尺度卷积网络的图像超分辨率重建[J]. 模式识别与人工智能,2020,33(11):972-980. doi: 10.16451/j.cnki.issn1003-6059.202011002 GAO Qingqing, ZHAO Jianwei, ZHOU Zhenghua. Image super-resolution reconstruction based on recurrent multiscale convolutional networks[J]. Pattern Recognition and Artificial Intelligence,2020,33(11):972-980. doi: 10.16451/j.cnki.issn1003-6059.202011002
[10]	郑景阳. 基于密集残差网络的图像超分辨率算法的研究与应用[D]. 重庆: 重庆师范大学, 2020. ZHENG Jingyang. Research and application of image super-resolution algorithms based on dense residual networks [D]. Chongqing: Chongqing Normal University, 2020.
[11]	郭琳, 李晨, 陈晨, 等. 基于通道注意递归残差网络的图像超分辨率重建[J]. 计算机科学,2021,48(8):139-144. doi: 10.11896/jsjkx.200500150 GUO Lin, LI Chen, CHEN Chen, et al. Image super-resolution reconstruction based on channel attention recurrent residual network[J]. Computer Science,2021,48(8):139-144. doi: 10.11896/jsjkx.200500150
[12]	TAI Y S, YANG J X, LIU X. Image super-resolution via deep recursive residual network[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, July 21-26, 2017. New York: IEEE, 2017: 3147-3155.
[13]	HOWARD A, ZHU M, CHEN B, et al. Mobilenets: efficient convolutional neural networks for mobile vision applications. (2017-04-17)[2022-01-18]. https://arxiv.org/abs/1704.04861
[14]	ZHANG X, ZHOU X, LIN M. Shufflenet: an extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA , June 18-22, 2018. New York: IEEE, 2018: 6848-6856.
[15]	YANG W, ZHANG X, TIAN Y, et al. Lcscnet: linear compressing-based skip-connecting network for image super-resolution[J]. IEEE Transactions on Image Processing,2020,29:1450-1464. doi: 10.1109/TIP.2019.2940679
[16]	赵小强, 宋昭漾. Adam优化的CNN超分辨率重建[J]. 计算机科学与探索,2019,13(5):858-865. doi: 10.3778/j.issn.1673-9418.1809020 ZHAO Xiaoqiang, SONG Zhaoyang. Adam-optimized CNN super-resolution reconstruction[J]. Journal of Frontiers of Computer Science and Technology,2019,13(5):858-865. doi: 10.3778/j.issn.1673-9418.1809020
[17]	WANG Z, BOVIK C A, SHEIKH R H, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing,2004,13:600-612. doi: 10.1109/TIP.2003.819861
[18]	LAI W S, HUANG J B, AHUJA N, et al. Deep laplacian pyramid networks for fast and accurate super-resolution[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, July 21-26, 2017. New York: IEEE, 2017: 624-632.
[19]	ZHANG K. ZUO W M, ZHANG L. Deep plug-and-play super-resolution for arbitrary blur kernels [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, June16-20, 2019. New York: IEEE, 2019: 1671-1681.
[20]	SHEIKH H R, BOVIK A C, VECIANA G. An information fidelity criterion for image quality assessment using natural scene statistics[J]. IEEE Transactions on Image Processing,2005,14(11):2117-2128.

[1]	LI Yan, FAN Jihong, YU Bing, YUAN Lin'guang, SUN Yu'nan, QIN Yan, MA Li. Spectral responsivity measurement technology for UV detector based on cryogenic radiometer[J]. Journal of Applied Optics, 2022, 43(2): 311-316. DOI: 10.5768/JAO202243.0204001
[2]	LIN Yongjie, XU Nan, HE Yingwei, LIU Wende, GAN Haiyong, GONG Huaping. Relative spectral responsivity calibration technology of InGaAs photodetector based on super-continuum light source[J]. Journal of Applied Optics, 2021, 42(4): 709-716. DOI: 10.5768/JAO202142.0403003
[3]	DENG Yuqiang. Progress of terahertz metrology research and standard construction[J]. Journal of Applied Optics, 2020, 41(4): 651-661. DOI: 10.5768/JAO202041.0409002
[4]	LI Yongliang, YU Jianhui, ZHANG Jun. Detection of performances and noise of APD detector module[J]. Journal of Applied Optics, 2019, 40(6): 1115-1119. DOI: 10.5768/JAO201940.0603006
[5]	Ding Lei, Yuan Yinlin, Zheng Xiaobing, Zhang Yanna, Qi Tao, Wu Haoyu. Verification method of spectral calibration accuracy for hyperspectral remote sensors[J]. Journal of Applied Optics, 2017, 38(3): 463-468. DOI: 10.5768/JAO201738.0303006
[6]	XU Tao, YU Jing, DENG Yu-qiang, SUN Qing, ZHANG Yun-peng. Excimer laser power standard detector[J]. Journal of Applied Optics, 2012, 33(4): 793-798.
[7]	XU Li-jun, CAI Hong-xing, LI Chang-li, BI Juan, JI Guang-yong, ZHANG Xi-he. Responsivity of photoelectric detector irradiated by intense laser[J]. Journal of Applied Optics, 2010, 31(6): 1018-1022.
[8]	WANG Ji, ZHENG Xiao-bing, ZHANG Lei, LIN Zhi-qiang. Measurement of spectral responsivity of an infrared detector[J]. Journal of Applied Optics, 2007, 28(3): 313-316.
[9]	FAN Ji-hong, HOU Xi-qi, YANG Zhao-jin, YIN Tao, QIN Yan, LIU Jian-ping. Measurement technology for spectral responsivity of infrared detector[J]. Journal of Applied Optics, 2006, 27(5): 460-462.
[10]	FAN Ji-hong, YANG Zhao-jin, QIN Yan. Research of test technology for absolute spectral responsivity of HgCdTe detector[J]. Journal of Applied Optics, 2006, 27(supp): 79-82.

Cited By

Cited by

Periodical cited type(1)

杜国军，欧宗耀，张晨阳，王春辉，李旭，李重阳. 真空环境下激光测距仪收发光轴测试方法研究. 激光技术. 2021(05): 561-565 .

Other cited types(0)

Get Citation

PDF

XML

Article views (273) PDF downloads (30) Cited by(1)

Turn off MathJax

Article Contents

Abstract

References

Super-resolution reconstruction of fiber optic coil image based on lightweight network