White-Light Interference Microscopy Image Super-Resolution Using Generative Adversarial Networks

To reduce external disturbances and achieve high vertical resolution, the scanning time for white-light interference microscopy is very short. Because capturing high-resolution (HR) images is time consuming, low-resolution (LR) images are acquired instead. However, HR images are more desirable because they contain more details. To ensure high vertical resolution and high image resolution, one feasible solution is to process the scanned LR images to HR images by single image super-resolution (SISR). In this paper, an interference image super-resolution (IISR) model based on a generative adversarial network (GAN) is proposed. The generator is based on the enhanced super-resolution generative adversarial network (ESRGAN) architecture. With the aim of acquiring more realistic images, the discriminator network is designed using a modified DenseNet architecture, in which the pooling layers are replaced with dilated convolutional layers. The perceptual loss is optimized, and the content loss is upgraded to a continuously differentiable piecewise function. Various microscopy images are tested, including images with and without interference fringes. The IISR model has been proven to restore LR images to HR images. The comparative experiments prove that the proposed model achieves better visual quality than other models, preserving more realistic details.

[1]  Mirabela Rusu,et al.  An Application of Generative Adversarial Networks for Super Resolution Medical Imaging , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[2]  Pourya Shamsolmoali,et al.  G-GANISR: Gradual generative adversarial network for image super resolution , 2019, Neurocomputing.

[3]  Zhihui Lai,et al.  Structured optimal graph based sparse feature extraction for semi-supervised learning , 2020, Signal Process..

[4]  Jin Wang,et al.  Complexity and Algorithms for Superposed Data Uploading Problem in Networks With Smart Devices , 2020, IEEE Internet of Things Journal.

[5]  Xi Chen,et al.  Single-Image Super-Resolution Algorithm Based on Structural Self-Similarity and Deformation Block Features , 2019, IEEE Access.

[6]  Kenli Li,et al.  A robust and fixed-time zeroing neural dynamics for computing time-variant nonlinear equation using a novel nonlinear activation function , 2019, Neurocomputing.

[7]  Jianming Zhang,et al.  Remote Sensing Image Sharpening by Integrating Multispectral Image Super-Resolution and Convolutional Sparse Representation Fusion , 2019, IEEE Access.

[8]  Hyuk-Jae Lee,et al.  Resolution-Preserving Generative Adversarial Networks for Image Enhancement , 2019, IEEE Access.

[9]  Shenglong Li,et al.  Deep adversarial model for musculoskeletal quality evaluation , 2020, Inf. Process. Manag..

[10]  Samarth Tripathi,et al.  Towards Deeper Generative Architectures for GANs using Dense connections , 2018, ArXiv.

[11]  Xi Chen,et al.  Multiscale fast correlation filtering tracking algorithm based on a feature fusion model , 2019, Concurr. Comput. Pract. Exp..

[12]  Ke Gu,et al.  Secure Data Sequence Query Framework Based on Multiple Fogs , 2019 .

[13]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Yuantao Chen,et al.  The fire recognition algorithm using dynamic feature fusion and IV-SVM classifier , 2019, Cluster Computing.

[15]  Ankur Datta,et al.  Dense Bynet: Residual Dense Network for Image Super Resolution , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[16]  Pourya Shamsolmoali,et al.  Image super resolution by dilated dense progressive network , 2019, Image Vis. Comput..

[17]  Xilin Chen,et al.  FCSR-GAN: Joint Face Completion and Super-Resolution via Multi-Task Learning , 2019, IEEE Transactions on Biometrics, Behavior, and Identity Science.

[18]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Yuechao Wang,et al.  Three-Dimensional Super-Resolution Morphology by Near-Field Assisted White-Light Interferometry , 2016, Scientific Reports.

[20]  Fei Cheng,et al.  FRD-CNN: Object detection based on small-scale convolutional neural networks and feature reuse , 2019, Scientific Reports.

[21]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[22]  Junchao Li,et al.  Super Resolution Image Reconstruction of Textile Based on SRGAN , 2019, 2019 IEEE International Conference on Smart Internet of Things (SmartIoT).

[23]  Feng Zhou,et al.  Automatic Target Recognition for Synthetic Aperture Radar Images Based on Super-Resolution Generative Adversarial Network and Deep Convolutional Neural Network , 2019, Remote. Sens..

[24]  Zengbo Wang,et al.  Optical virtual imaging at 50 nm lateral resolution with a white-light nanoscope. , 2011, Nature communications.

[25]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Jong Hyuk Park,et al.  Waiting Time Minimized Charging and Discharging Strategy Based on Mobile Edge Computing Supported by Software-Defined Network , 2020, IEEE Internet of Things Journal.

[27]  Lianlin Li,et al.  Super-resolution SAR Image Reconstruction via Generative Adversarial Network , 2018, 2018 12th International Symposium on Antennas, Propagation and EM Theory (ISAPE).

[28]  Jie Xiong,et al.  A novel online incremental and decremental learning algorithm based on variable support vector machine , 2019, Cluster Computing.

[29]  Victor S. Sheng,et al.  A convolutional neural network-based linguistic steganalysis for synonym substitution steganography. , 2019, Mathematical biosciences and engineering : MBE.

[30]  Edward Hæggström,et al.  3D Super-Resolution Optical Profiling Using Microsphere Enhanced Mirau Interferometry , 2017, Scientific Reports.

[31]  Lixin Zheng,et al.  A Fast Medical Image Super Resolution Method Based on Deep Learning Network , 2019, IEEE Access.