An Advanced Noise Reduction and Edge Enhancement Algorithm
Abstract
:1. Introduction
- Noise removal and contrast enhancement are simultaneously learned for effective performance improvement without requiring large amounts of training data.
- The color distortion of denoised images is prevented by applying LP decomposition.
- Edge information is enhanced to achieve high-quality output images by taking advantage of spatially correlated information obtained from SATs.
2. Proposed Method
2.1. DIP-Based Module
2.2. Image Fusion Module
2.3. Progressive Refinement Module
3. Experimental Results
3.1. Ablation Study
3.2. Quantitative Results
3.3. Qualitative Results
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Anagnostis, A.; Tagarakis, A.C.; Kateris, D.; Moysiadis, V.; Sørensen, C.G.; Pearson, S.; Bochtis, D. Orchard Mapping with Deep Learning Semantic Segmentation. Sensors 2021, 21, 3813. [Google Scholar] [CrossRef]
- Shirokanev, A.; Ilyasova, N.; Andriyanov, N.; Zamytskiy, E.; Zolotarev, A.; Kirsh, D. Modeling of Fundus Laser Exposure for Estimating Safe Laser Coagulation Parameters in the Treatment of Diabetic Retinopathy. Mathematics 2021, 9, 967. [Google Scholar] [CrossRef]
- Lee, K.; Tang, W. A Fully Wireless Wearable Motion Tracking System with 3D Human Model for Gait Analysis. Sensors 2021, 21, 4051. [Google Scholar] [CrossRef] [PubMed]
- Liu, C.; Wang, A.; Bu, C.; Wang, W.; Sun, H. Human Motion Tracking with Less Constraint of Initial Posture from a Single RGB-D Sensor. Sensors 2021, 21, 3029. [Google Scholar] [CrossRef] [PubMed]
- Nan, M.; Trăscău, M.; Florea, A.M.; Iacob, C.C. Comparison between Recurrent Networks and Temporal Convolutional Networks Approaches for Skeleton-Based Action Recognition. Sensors 2021, 21, 2051. [Google Scholar] [CrossRef]
- Wu, N.; Kawamoto, K. Zero-Shot Action Recognition with Three-Stream Graph Convolutional Networks. Sensors 2021, 21, 3793. [Google Scholar] [CrossRef]
- Le, T.H.; Huang, S.C.; Jaw, D.W. Cross-Resolution Feature Fusion for Fast Hand Detection in Intelligent Homecare Systems. IEEE Sens. J. 2019, 19, 4696–4704. [Google Scholar] [CrossRef]
- Huang, S.C.; Le, T.H.; Jaw, D.W. DSNet: Joint Semantic Learning for Object Detection in Inclement Weather Conditions. IEEE Trans. Pattern Anal. Mach. Intell. 2021, 43, 2623–2633. [Google Scholar] [CrossRef]
- Le, T.H.; Jaw, D.W.; Lin, I.C.; Liu, H.B.; Huang, S.C. An efficient hand detection method based on convolutional neural network. In Proceedings of the 2018 7th International Symposium on Next Generation Electronics (ISNE), Taipei, Taiwan, 7–9 May 2018; pp. 1–2. [Google Scholar]
- Hoang, Q.V.; Le, T.H.; Huang, S.C. An Improvement of RetinaNet for Hand Detection in Intelligent Homecare Systems. In Proceedings of the 2020 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan), Taoyuan, Taiwan, 28–30 September 2020; pp. 1–2. [Google Scholar]
- Hoang, Q.V.; Le, T.H.; Huang, S.C. Data Augmentation for Improving SSD Performance in Rainy Weather Conditions. In Proceedings of the 2020 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan), Taoyuan, Taiwan, 28–30 September 2020; pp. 1–2. [Google Scholar]
- Huang, S.C.; Le, T.H. Principles and Labs for Deep Learning; Academic Press: London, UK, 2021. [Google Scholar]
- Wang, F.; Huang, H.; Liu, J. Variational-based mixed noise removal with CNN deep learning regularization. IEEE Trans. Image Process. 2019, 29, 1246–1258. [Google Scholar] [CrossRef] [Green Version]
- Lin, P.H.; Chen, B.H.; Cheng, F.C.; Huang, S.C. A morphological mean filter for impulse noise removal. J. Disp. Technol. 2016, 12, 344–350. [Google Scholar] [CrossRef]
- Zhang, P.; Li, F. A new adaptive weighted mean filter for removing salt-and-pepper noise. IEEE Signal Process. Lett. 2014, 21, 1280–1283. [Google Scholar] [CrossRef]
- Hsieh, M.H.; Cheng, F.C.; Shie, M.C.; Ruan, S.J. Fast and efficient median filter for removing 1–99% levels of salt-and-pepper noise in images. Eng. Appl. Artif. Intell. 2013, 26, 1333–1338. [Google Scholar] [CrossRef]
- Toh, K.K.V.; Isa, N.A.M. Noise adaptive fuzzy switching median filter for salt-and-pepper noise reduction. IEEE Signal Process. Lett. 2009, 17, 281–284. [Google Scholar] [CrossRef] [Green Version]
- Esakkirajan, S.; Veerakumar, T.; Subramanyam, A.N.; PremChand, C.H. Removal of High Density Salt and Pepper Noise Through Modified Decision Based Unsymmetric Trimmed Median Filter. IEEE Signal Process. Lett. 2011, 18, 287–290. [Google Scholar] [CrossRef]
- Xu, J.; Zhang, L.; Zhang, D. External prior guided internal prior learning for real-world noisy image denoising. IEEE Trans. Image Process. 2018, 27, 2996–3010. [Google Scholar] [CrossRef] [Green Version]
- Huang, S.C.; Peng, Y.T.; Chang, C.H.; Cheng, K.H.; Huang, S.W.; Chen, B.H. Restoration of Images with High-Density Impulsive Noise Based on Sparse Approximation and Ant-Colony Optimization. IEEE Access 2020, 8, 99180–99189. [Google Scholar] [CrossRef]
- Le, T.H.; Lin, P.H.; Huang, S.C. LD-Net: An Efficient Lightweight Denoising Model Based on Convolutional Neural Network. IEEE Open J. Comput. Soc. 2020, 1, 173–181. [Google Scholar] [CrossRef]
- Zhang, K.; Zuo, W.; Chen, Y.; Meng, D.; Zhang, L. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Trans. Image Process. 2017, 26, 3142–3155. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Vasil’ev, K.K.; Dement’ev, V.E.; Andriyanov, N.A. Doubly stochastic models of images. Pattern Recognit. Image Anal. 2015, 25, 105–110. [Google Scholar] [CrossRef]
- Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar]
- Ulyanov, D.; Vedaldi, A.; Lempitsky, V. Deep image prior. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 9446–9454. [Google Scholar]
- Cheng, K.H.; Huang, S.W.; Peng, Y.T. Image Denoising with Edge Enhancement based on Deep Image Prior and Image Fusion. In Proceedings of the 33rd IPPR Conference on Computer Vision, Graphics, and Image Processing (CVGIP), Hsinchu, Taiwan, 16–18 August 2020. [Google Scholar]
- Cheng, Z.; Gadelha, M.; Maji, S.; Sheldon, D. A bayesian perspective on the deep image prior. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 5443–5451. [Google Scholar]
- Gandelsman, Y.; Shocher, A.; Irani, M. “Double-DIP”: Unsupervised Image Decomposition via Coupled Deep-Image-Priors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, 15–20 June 2019; pp. 11026–11035. [Google Scholar]
- Agustsson, E.; Timofte, R. Ntire 2017 challenge on single image super-resolution: Dataset and study. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, 21–26 July 2017; pp. 126–135. [Google Scholar]
- Zhang, C.; Bengio, S.; Hardt, M.; Recht, B.; Vinyals, O. Understanding deep learning requires rethinking generalization. arXiv 2016, arXiv:1611.03530. [Google Scholar]
- Pizer, S.M.; Amburn, E.P.; Austin, J.D.; Cromartie, R.; Geselowitz, A.; Greer, T.; ter Haar Romeny, B.; Zimmerman, J.B.; Zuiderveld, K. Adaptive histogram equalization and its variations. Comput. Vis. Graph. Image Process. 1987, 39, 355–368. [Google Scholar] [CrossRef]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 7–13 December 2015; pp. 1026–1034. [Google Scholar]
- Burt, P.J.; Adelson, E.H. The Laplacian pyramid as a compact image code. In Readings in Computer Vision; Elsevier: Amsterdam, The Netherlands, 1987; pp. 671–679. [Google Scholar]
- Qin, H. Autonomous environment and target perception of underwater offshore vehicles. In Fundamental Design and Automation Technologies in Offshore Robotics; Elsevier: Amsterdam, The Netherlands, 2020; pp. 91–113. [Google Scholar]
- Crow, F.C. Summed-area tables for texture mapping. In Proceedings of the 11th Annual Conference on Computer Graphics and Interactive Techniques, Minneapolis, MN, USA, 23–27 July 1984; pp. 207–212. [Google Scholar]
- Russo, F. A method for estimation and filtering of Gaussian noise in images. IEEE Trans. Instrum. Meas. 2003, 52, 1148–1154. [Google Scholar] [CrossRef]
- Zhang, R.; Isola, P.; Efros, A.A.; Shechtman, E.; Wang, O. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 586–595. [Google Scholar]
Type | Filter Size | Number of Filters |
---|---|---|
Downsampling | [3 × 3, 3 × 3, 3 × 3, 3 × 3, 3 × 3] | [128, 128, 128, 128, 128] |
Upsampling | [3 × 3, 3 × 3, 3 × 3, 3 × 3, 3 × 3] | [128, 128, 128, 128, 128] |
skip-connections | [1 × 1, 1 × 1, 1 × 1, 1 × 1, 1 × 1] | [4, 4, 4, 4, 4] |
Method | Noise Level () | ||
---|---|---|---|
60 | 70 | 80 | |
DIP() [25] | 0.266 | 0.317 | 0.366 |
DIP() [25] | 0.303 | 0.373 | 0.425 |
CLAHE-DIP [25,31] | 0.332 | 0.424 | 0.493 |
DIPIF [26] | 0.259 | 0.298 | 0.349 |
Proposed Method | 0.248 | 0.283 | 0.326 |
Image | Chicken | Temple | Jellyfish | House 1 | Horse | House 2 | Cactus | Pyramid | Airplane | Statue |
---|---|---|---|---|---|---|---|---|---|---|
Noise Level | = 60 | |||||||||
DIP() [25] | 0.285 | 0.241 | 0.262 | 0.256 | 0.284 | 0.248 | 0.275 | 0.261 | 0.276 | 0.267 |
DIP() [25] | 0.339 | 0.269 | 0.305 | 0.278 | 0.327 | 0.275 | 0.313 | 0.296 | 0.319 | 0.310 |
CLAHE-DIP [25,31] | 0.381 | 0.295 | 0.321 | 0.308 | 0.360 | 0.301 | 0.347 | 0.315 | 0.352 | 0.336 |
DIPIF [26] | 0.273 | 0.238 | 0.259 | 0.251 | 0.271 | 0.246 | 0.267 | 0.256 | 0.269 | 0.262 |
Proposed Method | 0.265 | 0.225 | 0.247 | 0.237 | 0.259 | 0.236 | 0.256 | 0.245 | 0.251 | 0.254 |
Noise Level | = 70 | |||||||||
DIP() [25] | 0.353 | 0.282 | 0.311 | 0.299 | 0.351 | 0.294 | 0.326 | 0.306 | 0.331 | 0.315 |
DIP() [25] | 0.408 | 0.318 | 0.379 | 0.354 | 0.399 | 0.349 | 0.384 | 0.375 | 0.386 | 0.381 |
CLAHE-DIP [25,31] | 0.496 | 0.314 | 0.415 | 0.367 | 0.513 | 0.331 | 0.489 | 0.386 | 0.492 | 0.433 |
DIPIF [26] | 0.327 | 0.255 | 0.298 | 0.279 | 0.333 | 0.272 | 0.307 | 0.289 | 0.317 | 0.302 |
Proposed Method | 0.316 | 0.244 | 0.277 | 0.26 | 0.304 | 0.281 | 0.292 | 0.274 | 0.293 | 0.286 |
Noise Level | = 80 | |||||||||
DIP() [25] | 0.423 | 0.309 | 0.361 | 0.324 | 0.412 | 0.317 | 0.386 | 0.342 | 0.408 | 0.375 |
DIP() [25] | 0.496 | 0.347 | 0.412 | 0.388 | 0.485 | 0.363 | 0.455 | 0.398 | 0.478 | 0.425 |
CLAHE-DIP [25,31] | 0.559 | 0.414 | 0.484 | 0.465 | 0.543 | 0.437 | 0.512 | 0.472 | 0.539 | 0.506 |
DIPIF [26] | 0.404 | 0.288 | 0.345 | 0.303 | 0.391 | 0.294 | 0.382 | 0.325 | 0.393 | 0.364 |
Proposed Method | 0.374 | 0.270 | 0.323 | 0.298 | 0.362 | 0.283 | 0.348 | 0.312 | 0.355 | 0.330 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Huang, S.-C.; Hoang, Q.-V.; Le, T.-H.; Peng, Y.-T.; Huang, C.-C.; Zhang, C.; Fung, B.C.M.; Cheng, K.-H.; Huang, S.-W. An Advanced Noise Reduction and Edge Enhancement Algorithm. Sensors 2021, 21, 5391. https://doi.org/10.3390/s21165391
Huang S-C, Hoang Q-V, Le T-H, Peng Y-T, Huang C-C, Zhang C, Fung BCM, Cheng K-H, Huang S-W. An Advanced Noise Reduction and Edge Enhancement Algorithm. Sensors. 2021; 21(16):5391. https://doi.org/10.3390/s21165391
Chicago/Turabian StyleHuang, Shih-Chia, Quoc-Viet Hoang, Trung-Hieu Le, Yan-Tsung Peng, Ching-Chun Huang, Cheng Zhang, Benjamin C. M. Fung, Kai-Han Cheng, and Sha-Wo Huang. 2021. "An Advanced Noise Reduction and Edge Enhancement Algorithm" Sensors 21, no. 16: 5391. https://doi.org/10.3390/s21165391
APA StyleHuang, S.-C., Hoang, Q.-V., Le, T.-H., Peng, Y.-T., Huang, C.-C., Zhang, C., Fung, B. C. M., Cheng, K.-H., & Huang, S.-W. (2021). An Advanced Noise Reduction and Edge Enhancement Algorithm. Sensors, 21(16), 5391. https://doi.org/10.3390/s21165391