Efficient halftone algorithm based on lightweight residual networks

doi:10.3785/j.issn.1008-973X.2025.01.006

Journal of ZheJiang University (Engineering Science)

2025, Vol. 59

Issue (1): 62-69 DOI: 10.3785/j.issn.1008-973X.2025.01.006

Efficient halftone algorithm based on lightweight residual networks

Dengfeng LIU1,2(

),Shihai CHEN1,2,Wenjing GUO1,2,Zhilei CHAI1,2

1. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China
2. Engineering Research Center of Intelligent Technology for Healthcare, Ministry of Education, Wuxi 214122, China

Download:

HTML

PDF(1232KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

To address the issues of sluggish processing speed and substandard quality of the halftone effect in image halftoning, an efficient halftone algorithm was proposed, which relies on a lightweight residual convolutional neural network(CNN). A noise compensation block was introduced to provide the model with jitter dependencies, to address the issue of flatness degradation in the original CNN. The inclusion of blue noise loss in the loss function was implemented to further optimize the model’s performance. The low-frequency components were suppressed and the anisotropy of the high-frequency region was optimized when halftoning a constant-value grayscale image. Experimental results showed that, compared with the available deep halftone methods, the proposed algorithm exhibited a significant reduction of 96.77% in the number of parameters, the structural similarity (SSIM) improved by 8.17% and the peak signal-to-noise ratio (PSNR) improved by 0.133 3 dB in the VOC test set, the halftone images had blue noise characteristics, and the processing speed was increased by 57.28%.

Key words： residual network halftone blue noise characteristic deep learning model lightweight

Received: 18 August 2023 Published: 18 January 2025

CLC:

TP 391

Fund: 国家重点研发专项计划资助项目（2022YFE0112400）；国家自然科学基金青年项目（21706096）；第62批中国博士后科学基金资助项目（2017M621627）；江苏省博士后科研项目（1601009A）；江苏省自然科学基金青年项目（BK20160162）.

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Dengfeng LIU
	Shihai CHEN
	Wenjing GUO
	Zhilei CHAI

Cite this article:

Dengfeng LIU,Shihai CHEN,Wenjing GUO,Zhilei CHAI. Efficient halftone algorithm based on lightweight residual networks. Journal of ZheJiang University (Engineering Science), 2025, 59(1): 62-69.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2025.01.006 OR https://www.zjujournals.com/eng/Y2025/V59/I1/62

基于轻量残差网络的高效半色调算法

为了解决图像半色调中处理速度慢以及半色调效果不佳的问题，提出基于轻量型残差卷积神经网络（CNN）的高效半色调算法. 为了解决原始CNN平坦性退化问题，引入噪声补偿块，为模型提供抖动依赖. 为了进一步提升模型性能，在损失函数中引入蓝噪声损失；在半色调常值灰度图像时，抑制低频分量，优化高频区域的各向异性. 实验结果表明，对比现有深度半色调方法，所提算法的参数量下降96.77%，在VOC测试集中结构相似性(SSIM)提升8.17%，峰值信噪比(PSNR)提升0.1333 dB，半色调图像具有蓝噪声特性，处理速度提升57.28%.

关键词： 残差网络, 半色调, 蓝噪声特性, 深度学习, 模型轻量化

Fig.1 Power spectrum of ideal blue noise halftone

Fig.2 Model structure of halftone algorithm based on residual networks

Fig.3 Building blocks comparison of different residual networks

Fig.4 Structure of noise compensation block

Tab.1 Quantitative evaluation of halftone algorithms

Fig.5 Comparison of halftone effects for different algorithms

Tab.2 Test results of five algorithms in public datasets

Fig.6 Halftone spectral analysis for constant-value grayscale (grayscale of 15/255)

Tab.3 Effect of noise intensity on model performance

Tab.4 Ablation experimental results of proposed algorithm’s module

Fig.7 Half-tone images generated by different models

Tab.5 Runtime and parameter number comparison for different algorithms


[1]	FRANK T, LIU J, GAT S, et al A machine learning approach to design of aperiodic, clustered-dot halftone screens via direct binary search[J]. IEEE Transactions on Image Processing, 2022, 31: 5498- 5512 doi: 10.1109/TIP.2022.3196821

[2]	LAU D L, ARCE G R. Modern digital halftoning [M]. 2nd ed. Boca Raton: CRC Press, 2018.

[3]	ULICHNEY R A Dithering with blue noise[J]. Proceedings of the IEEE, 1988, 76 (1): 56- 79 doi: 10.1109/5.3288

[4]	KOPF J, COHEN-OR D, DEUSSEN O, et al Recursive Wang tiles for real-time blue noise[J]. ACM Transactions on Graphics, 2006, 25 (3): 509- 518 doi: 10.1145/1141911.1141916

[5]	BAYER B E An optimum method for two level rendition of continuous tone pictures[J]. IEEE International Conference on Communications, 1973, 9 (1): 26.11- 26.15

[6]	YI Y, LI R, YU C, et al Quality evaluation metric for greyscale error diffusion halftone images based on texture and visual characteristics[J]. Imaging Science Journal, 2017, 65 (5/6): 315- 326

[7]	YANG G, JIAO S, LIU J P, et al Error diffusion method with optimized weighting coefficients for binary hologram generation[J]. Applied Optics, 2019, 58 (20): 5547- 5555 doi: 10.1364/AO.58.005547

[8]	FUNG Y H, CHAN Y H Tone-dependent error diffusion based on an updated blue-noise model[J]. Journal of Electronic Imaging, 2016, 25 (1): 013013 doi: 10.1117/1.JEI.25.1.013013

[9]	CHIZHOV V, GEORGIEV I, MYSZKOWSKI K, et al Perceptual error optimization for Monte Carlo rendering[J]. ACM Transactions on Graphics, 2022, 41 (3): 1- 17

[10]	MAO Y, SARKAR U, BORRELL I, et al Ink drop displacement model-based direct binary search[J]. IEEE Transactions on Image Processing, 2023, 32: 3897- 3911 doi: 10.1109/TIP.2023.3283924

[11]	XIA M, WONG T T. Deep inverse halftoning via progressively residual learning [C]// Computer Vision–ACCV 2018 . Perth: Springer, 2019: 523–539.

[12]	SHAO L, ZHANG E, LI M An efficient convolutional neural network model combined with attention mechanism for inverse halftoning[J]. Electronics, 2021, 10 (13): 1574 doi: 10.3390/electronics10131574

[13]	JIANG H, MU Y Conditional diffusion process for inverse halftoning[J]. Advances in Neural Information Processing Systems, 2022, 35: 5498- 5509

[14]	XIA M, HU W, LIU X, et al. Deep halftoning with reversible binary pattern [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision . Montreal: IEEE, 2021: 14000–14009.

[15]	SHAO S, LI Z, ZHANG T, et al. Objects365: a large-scale, high-quality dataset for object detection [C]// Proceedings of the IEEE/CVF International Conference on Computer Vision . Seoul: IEEE, 2019: 8430–8439.

[16]	CHOI B, ALLEBACH J P Mimicking DBS halftoning via a deep learning approach[J]. Electronic Imaging, 2022, 34 (15): 158

[17]	AGUSTSSON E, TIMOFTE R. NTIRE 2017 challenge on single image super-resolution: dataset and study [C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops . Honolulu: IEEE, 2017: 126–135.

[18]	HUI Z, WANG X, GAO X. Fast and accurate single image super-resolution via information distillation network [C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City: IEEE, 2018: 723–731.

[19]	ZHANG H, WANG P, ZHANG C, et al A comparable study of CNN-based single image super-resolution for space-based imaging sensors[J]. Sensors, 2019, 19 (14): 3234 doi: 10.3390/s19143234

[20]	JIU M, PUSTELNIK N A deep primal-dual proximal network for image restoration[J]. IEEE Journal of Selected Topics in Signal Processing, 2021, 15 (2): 190- 203 doi: 10.1109/JSTSP.2021.3054506

[21]	DONG C, LOY C C, TANG X. Accelerating the super-resolution convolutional neural network [C]// Computer Vision–ECCV 2016 . Amsterdam: Springer, 2016: 391–407.

[22]	MATSUI Y, ITO K, ARAMAKI Y, et al Sketch-based Manga retrieval using Manga109 dataset[J]. Multimedia Tools and Applications, 2017, 76: 21811- 21838 doi: 10.1007/s11042-016-4020-z

[23]	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: IEEE, 2015: 5197–5206.

[24]	OSTROMOUKHOV V. A simple and efficient error-diffusion algorithm [C]// Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques . [S.l.]: ACM, 2001: 567–572.

[1]	Zhichao CHEN,Jie YANG,Fan LI,Zhicheng FENG. Review on deep learning-based key algorithm for train running environment perception[J]. Journal of ZheJiang University (Engineering Science), 2025, 59(1): 1-17.

[2]	Fan LI,Jie YANG,Zhicheng FENG,Zhichao CHEN,Yunxiao FU. Pantograph-catenary contact point detection method based on image recognition[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(9): 1801-1810.

[3]	Li XIAO,Zhigang CAO,Haoran LU,Zhijian HUANG,Yuanqiang CAI. Elastic metamaterial design based on deep learning and gradient optimization[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(9): 1892-1901.

[4]	Shuhan WU,Dan WANG,Yuanfang CHEN,Ziyu JIA,Yueqi ZHANG,Meng XU. Attention-fused filter bank dual-view graph convolution motor imagery EEG classification[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(7): 1326-1335.

[5]	Linrui LI,Dongsheng WANG,Hongjie FAN. Fact-based similar case retrieval methods based on statutory knowledge[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(7): 1357-1365.

[6]	Xianwei MA,Chaohui FAN,Weizhi NIE,Dong LI,Yiqun ZHU. Robust fault diagnosis method for failure sensors[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(7): 1488-1497.

[7]	Juan SONG,Longxi HE,Huiping LONG. Deep learning-based algorithm for multi defect detection in tunnel lining[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(6): 1161-1173.

[8]	Bo ZHONG,Pengfei WANG,Yiqiao WANG,Xiaoling WANG. Survey of deep learning based EEG data analysis technology[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(5): 879-890.

[9]	Cuiting WEI,Weijian ZHAO,Bochao SUN,Yunyi LIU. Intelligent rebar inspection based on improved Mask R-CNN and stereo vision[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(5): 1009-1019.

[10]	Xianglong LUO,Yafei WANG,Yanbo WANG,Lixin WANG. Structural deformation prediction of monitoring data based on bi-directional gate board learning system[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(4): 729-736.

[11]	Hai HUAN,Yu SHENG,Chenxi GU. Global guidance multi-feature fusion network based on remote sensing image road extraction[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(4): 696-707.

[12]	Qingjie QIAN,Junhe YU,Hongfei ZHAN,Rui WANG,Jian HU. Dimension prediction method of injection molded parts based on multi-feature fusion of DL-BiGRU[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(3): 646-654.

[13]	Mingjun SONG,Wen YAN,Yizhao DENG,Junran ZHANG,Haiyan TU. Light-weight algorithm for real-time robotic grasp detection[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(3): 599-610.

[14]	Xinhua YAO,Tao YU,Senwen FENG,Zijian MA,Congcong LUAN,Hongyao SHEN. Recognition method of parts machining features based on graph neural network[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(2): 349-359.

[15]	Yuebo MENG,Bo WANG,Guanghui LIU. Multi-scale context-guided feature elimination for ancient tower image classification[J]. Journal of ZheJiang University (Engineering Science), 2024, 58(12): 2489-2499.

Viewed

Full text

Abstract

Cited

Shared

Discussed