Jan-Ray Liao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jan-Ray Liao has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Li-Wen Chang
General Education Center, Chaoyang University of Technology, Taichung 413310, Taiwan
3 shared publications Chun-Chieh Chen
Department of Electrical Engineering National Chung Hsing University Taichung Taiwan
2 shared publicationsChun-Ming Chen
Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan
2 shared publications- Jeng-Ren Duann
Institute of Cognitive Neuroscience, National Central University, Zhongli, Taoyuan District, Taiwan
2 shared publications Shun-Zhi Lee
Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan
2 shared publicationsShye-Chorng Kuo
2 shared publications
Latest Publications
- Open Access
Adjustable Complexity Transformer Architecture for Image Denoising
In recent years, image denoising has seen a shift from traditional non-local self-similarity methods like BM3D to deep-learning based approaches that use learnable convolutions and attention mechanisms. While pixel-level attention is effective at capturing long-range relationships similar to non-local self-similarity based methods, it incurs extremely high computational costs that scale quadratically with image resolution. As an alternative, channel-wise attention is resolution-independent and computationally efficient but may miss crucial spatial details. In this paper, an adjustable attention mechanism is introduced that bridges the gap between pixel and channel attentions. In the proposed model, average pooling and variable-size convolutions are added before attention calculation to adjust spatial resolution and, thus, allow dynamical adjustment of computational complexity. This adjustable attention is applied in a transformer-based U-Net architecture and achieves performance comparable to state-of-the-art methods in both real and Gaussian blind denoising tasks. To be more concrete, the proposed method achieves a Peak Signal-to-Noise Ratio of 39.65 dB and a Structural Similarity Index Measure of 0.913 on the Smartphone Image Denoising Dataset. Therefore, the proposed method demonstrates a balance between efficiency and denoising quality.
Open AccessAdjustable Complexity Transformer Architecture for Image Denoising
In recent years, image denoising has seen a shift from traditional non-local self-similarity methods like BM3D to deep-learning based approaches that use learnable convolutions and attention mechanisms. While pixel-level attention is effective at capturing long-range relationships similar to non-local self-similarity based methods, it incurs extremely high computational costs that scale quadratically with image resolution. As an alternative, channel-wise attention is resolution-independent and computationally efficient but may miss crucial spatial details. In this paper, an adjustable attention mechanism is introduced that bridges the gap between pixel and channel attentions. In the proposed model, average pooling and variable-size convolutions are added before attention calculation to adjust spatial resolution and, thus, allow dynamical adjustment of computational complexity. This adjustable attention is applied in a transformer-based U-Net architecture and achieves performance comparable to state-of-the-art methods in both real and Gaussian blind denoising tasks. To be more concrete, the proposed method achieves a Peak Signal-to-Noise Ratio of 39.65 dB and a Structural Similarity Index Measure of 0.913 on the Smartphone Image Denoising Dataset. Therefore, the proposed method demonstrates a balance between efficiency and denoising quality.
- 1 October 2025
- Published by Springer Nature
- p. 3-10
Fusion of Region-Constraint Attention and Convolution Neural Network for Blind Image Denoising
- 1 October 2025
- Published by Springer Nature
- p. 3-10
Fusion of Region-Constraint Attention and Convolution Neural Network for Blind Image Denoising
- Open Access
- 15 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 247-253
Image Inpainting Using Lightweight Transformer Neural Network Based on Channel Attention
- 15 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 247-253
Open AccessImage Inpainting Using Lightweight Transformer Neural Network Based on Channel Attention
- 14 April 2023
- Published by Elsevier in Digital Signal Processing
- Vol. 137
Residual dense network with non-residual guidance for blind image denoising
- 14 April 2023
- Published by Elsevier in Digital Signal Processing
- Vol. 137
Residual dense network with non-residual guidance for blind image denoising
- 29 October 2022
- Published by Springer Nature in Multidimensional Systems and Signal Processing
- Vol. 34 (1) , 147-162
Improving non-local means image denoising by correlation correction
- 29 October 2022
- Published by Springer Nature in Multidimensional Systems and Signal Processing
- Vol. 34 (1) , 147-162
Improving non-local means image denoising by correlation correction
- Open Access
- 13 June 2020
- Published by Wiley in Discrete Dynamics in Nature and Society
- Vol. 2020, 1-16
A Robust Two-Machine Flow-Shop Scheduling Model with Scenario-Dependent Processing Times
In many scheduling studies, researchers consider the processing times of jobs as constant numbers. This assumption sometimes is at odds with practical manufacturing process due to several sources of uncertainties arising from real-life situations. Examples are the changing working environments, machine breakdowns, tool quality variations and unavailability, and so on. In light of the phenomenon of scenario-dependent processing times existing in many applications, this paper proposes to incorporate scenario-dependent processing times into a two-machine flow-shop environment with the objective of minimizing the total completion time. The problem under consideration is never explored. To solve it, we first derive a lower bound and two optimality properties to enhance the searching efficiency of a branch-and-bound method. Then, we propose 12 simple heuristics and their corresponding counterparts improved by a pairwise interchange method. Furthermore, we set proposed 12 simple heuristics as the 12 initial seeds to design 12 variants of a cloud theory-based simulated annealing (CSA) algorithm. Finally, we conduct simulations and report the performances of the proposed branch-and-bound method, the 12 heuristics, and the 12 variants of CSA algorithm.
- 13 June 2020
- Published by Wiley in Discrete Dynamics in Nature and Society
- Vol. 2020, 1-16
Open AccessA Robust Two-Machine Flow-Shop Scheduling Model with Scenario-Dependent Processing Times
In many scheduling studies, researchers consider the processing times of jobs as constant numbers. This assumption sometimes is at odds with practical manufacturing process due to several sources of uncertainties arising from real-life situations. Examples are the changing working environments, machine breakdowns, tool quality variations and unavailability, and so on. In light of the phenomenon of scenario-dependent processing times existing in many applications, this paper proposes to incorporate scenario-dependent processing times into a two-machine flow-shop environment with the objective of minimizing the total completion time. The problem under consideration is never explored. To solve it, we first derive a lower bound and two optimality properties to enhance the searching efficiency of a branch-and-bound method. Then, we propose 12 simple heuristics and their corresponding counterparts improved by a pairwise interchange method. Furthermore, we set proposed 12 simple heuristics as the 12 initial seeds to design 12 variants of a cloud theory-based simulated annealing (CSA) algorithm. Finally, we conduct simulations and report the performances of the proposed branch-and-bound method, the 12 heuristics, and the 12 variants of CSA algorithm.
- 1 May 2020
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 29 (03) , 033003-11
Noise shaping for direct binary search image halftoning
Among image halftoning algorithms, direct binary search (DBS) minimizes the total squared perceived error instead of using heuristic approaches. Therefore, it can generate halftone output with the best quality. The limitation of DBS is that its halftone pattern is controlled by the autocorrelation filter, which corresponds to both the human visual system and the printer model. Because of the low-pass characteristics of the filter, DBS can only generate blue-noise-like halftone pattern and the only variation is the clustered-dot algorithm proposed in 2013. We use the results of theoretical bounds to show that halftone patterns in DBS can be controlled in both frequency and spatial domains through an approach called “noise shaping.” This approach is achieved through an added term to the filtered error in DBS. We also show that DBS clustered-dot halftoning is a special case of this noise-shaping approach. Experimental results show that both the spatial-domain and frequency-domain characteristics of the generated halftone pattern can be manipulated freely using this approach.
- 1 May 2020
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 29 (03) , 033003-11
Noise shaping for direct binary search image halftoning
Among image halftoning algorithms, direct binary search (DBS) minimizes the total squared perceived error instead of using heuristic approaches. Therefore, it can generate halftone output with the best quality. The limitation of DBS is that its halftone pattern is controlled by the autocorrelation filter, which corresponds to both the human visual system and the printer model. Because of the low-pass characteristics of the filter, DBS can only generate blue-noise-like halftone pattern and the only variation is the clustered-dot algorithm proposed in 2013. We use the results of theoretical bounds to show that halftone patterns in DBS can be controlled in both frequency and spatial domains through an approach called “noise shaping.” This approach is achieved through an added term to the filtered error in DBS. We also show that DBS clustered-dot halftoning is a special case of this noise-shaping approach. Experimental results show that both the spatial-domain and frequency-domain characteristics of the generated halftone pattern can be manipulated freely using this approach.
- Open Access
- 27 March 2018
- Published by Institute of Industrial Applications Engineers
Efficient Non-Local Means Image Denoising Using Halftone Image for Pre-Classification
Efficient Non-Local Means Image Denoising Using Halftone Image for Pre-Classification
- 27 March 2018
- Published by Institute of Industrial Applications Engineers
Open AccessEfficient Non-Local Means Image Denoising Using Halftone Image for Pre-Classification
Efficient Non-Local Means Image Denoising Using Halftone Image for Pre-Classification
- Open Access
- 8 September 2016
- Published by Institute of Industrial Applications Engineers
- p. 519-526
Optimal Binary Descriptor for Pre-Classification in Efficient Non-Local Mean Image Denoising
Optimal Binary Descriptor for Pre-Classification in Efficient Non-Local Mean Image Denoising
- 8 September 2016
- Published by Institute of Industrial Applications Engineers
- p. 519-526
Open AccessOptimal Binary Descriptor for Pre-Classification in Efficient Non-Local Mean Image Denoising
Optimal Binary Descriptor for Pre-Classification in Efficient Non-Local Mean Image Denoising
- Open Access
- 26 March 2016
- Published by Institute of Industrial Applications Engineers
Efficient Non-Local Image Denoising Using Binary Descriptor Classification
Efficient Non-Local Image Denoising Using Binary Descriptor Classification
- 26 March 2016
- Published by Institute of Industrial Applications Engineers
Open AccessEfficient Non-Local Image Denoising Using Binary Descriptor Classification
Efficient Non-Local Image Denoising Using Binary Descriptor Classification