帮助 关于我们

返回检索结果

Bayer阵列图像去马赛克算法综述
The review of demosaicing methods for Bayer color filter array image

查看参考文献70篇

魏凌云 1   孙帮勇 1,2 *  
文摘 Bayer阵列图像去马赛克技术是对稀疏采样的Bayer阵列图像进行RGB信息重建,图像重建质量是成像设备评价的重要因素之一,同时也对其他计算机视觉任务(如图像分割、人脸识别)产生影响。随着深度学习方法的快速发展,图像去马赛克领域提出了多种高性能算法。为了便于研究者更全面了解图像去马赛克算法的原理和研究进展,本文对该领域的经典算法和深度学习算法进行综述。首先对Bayer采样阵列原理和图像去马赛克技术进行概述。然后将现有方法分为传统方法和基于深度学习方法两类进行总结,同时根据去马赛克任务是否具有独立性,将深度学习方法分为独立去马赛克任务和联合去马赛克任务两类,分析不同方法的原理和优缺点,重点阐述基于深度学习的去马赛克方法的网络结构和重建机理,介绍去马赛克领域常用的公共数据集和性能评价指标,并对图像去马赛克相关实验进行分析对比。最后,围绕网络深度、运算效率和实用性等方面分析了现阶段图像去马赛克技术面临的挑战及未来发展方向。目前,基于深度学习的图像去马赛克方法已成为主流发展方向,但仍然存在计算成本较高、实际应用性不强等问题。因此,如何开发出重建精度高、处理时间短以及实用性强的图像去马赛克方法,是该领域未来重要的研究方向。
其他语种文摘 The Bayer array image demosaicing technology is one of the essential parts in the digital image signal processing process mechanism,which reconstructs the sparsely sampled Bayer array image into a completed RGB image. In terms of a single-sensor image acquisition of Bayer color filter array,single color channel value is just recorded by the position of each pixel. The other two color channels information needs to be reconstructed by the Bayer color filter array demosaicking technology. The reconstruction effect of qualified RGB information determines the accuracy of computer vision analysis like image segmentation and face recognition. Deep learning based Bayer array image demosaicing technology has promoted more high-performance algorithms nowadays. To recognize the principle and development of image demosaicing algorithms,we review some classic algorithms and analyze the key concepts. First,an overview is illustrated for the Bayer sampling array and image demosaicing technology. Next,we divide the existing methods into two categories in accordance with traditional methods and deep learning methods. The pros and cons of different methods are analyzed and the information transmission issue of the learning-based demosaicing network is focused on. We introduce traditional demosaicing methods in brief based on the basic principle,growth path and applications of the residual interpolation algorithms. Specifically,we divide the learning-based methods into single demosaic algorithms and joint multi-task demosaic algorithms derived of the independence of the demosaicing task. Single demosaicing algorithms can be divided into three categories of those are two-stage demosaicing network,three-stage demosaicing network,and end-to-end demosaicing network. Joint multi-task demosaic algorithms are mostly based on end-to-end multiple networks structure like full convolution,residual,densely connected, U-Net,feature pyramid,and generative adversarial network (GAN). At the same time,we compare seven representative methods to the two benched datasets of Kodak and McMaster,including three traditional methods and four deep learning methods. In addition,we introduce common public datasets and performance evaluation metrics peak signal-to-noise ratio (PSNR) and structural similarity in the field of demosaicing. Finally,we analyze the technical problems faced by the current image demosaicing technology and the future development direction from the perspectives of its network depth,computing efficiency,and feasibility. Our experimental results show that the deep learning based method surpasses the traditional methods in terms of objective quality evaluation indicators and subjective vision. We clarified that the highest PSNR value of the learning-based methods on the Kodak dataset surpassed the traditional methods by 12.73 dB,and the highest PSNR value of the learning-based methods on the McMaster dataset surpassed the traditional methods by 5.10 dB. The traditional method obtains the estimated value of the color image via the degradation model of the Bayer array image and some prior information. However,some distortion issues appear in the clear edges and multi-textured areas of the reconstructed image, such as color artifacts and checkerboard effects. Current deep learning methods have become the main development prospects in the field of demosaicing. Although the reconstructed image of learning-based methods is more similar to the original image than the traditional method on the visual effect and accuracy,it also has the problem of high computational cost and poor practical applicability. It is challenged to guarantee the accuracy of network algorithms and reduce the computational cost of the network both. Therefore,a high-performance and effective image demosaicing method has to be developed further in terms of datasets option,network structure optimization,and improvement of computing efficiency.
来源 中国图象图形学报 ,2022,27(9):2683-2696 【核心库】
DOI 10.11834/jig.211059
关键词 图像去马赛克 ; Bayer阵列图像 ; 图像处理 ; 深度学习 ; 卷积神经网络(CNN) ; 综述
地址

1. 西安理工大学印刷包装与数字媒体学院, 西安, 710048  

2. 中国科学院西安光学精密机械研究所, 中国科学院光谱成像技术重点实验室, 西安, 710119

语种 中文
文献类型 综述型
ISSN 1006-8961
学科 自动化技术、计算机技术
基金 国家自然科学基金 ;  陕西省重点研发计划资助 ;  中国科学院光谱成像技术重点实验室基金项目
文献收藏号 CSCD:7315612

参考文献 共 70 共4页

1.  Adams J E Jr. Interactions between color plane interpolation and other image processing functions in electronic photography. Proceedings Cameras and Systems for Electronic Photography and Scientific Imaging,1995:144-151 CSCD被引 1 次    
2.  Bayer B E. Color imaging array. U. S., No. 3 971 065,1976 CSCD被引 1 次    
3.  Cui K. Color image demosaicking using a 3-stage convolutional neural network structure. Proceedings of the 25th IEEE International Conference on Image Processing,2018:2177-2181 CSCD被引 2 次    
4.  Din S. Lightweight deep dense demosaicking and denoising using convolutional neural networks. Multimedia Tools and Applications,2020,79(45):34385-34405 CSCD被引 1 次    
5.  Dong C. Learning a deep convolutional network for image super-resolution. Proceedings of the 13th European Conference on Computer Vision,2014:184-199 CSCD被引 38 次    
6.  Dong W S. Joint demosaicing and denoising with perceptual optimization on a generative adversarial network,2018 CSCD被引 1 次    
7.  Gharbi M. Deep joint demosaicking and denoising. ACM Transactions on Graphics,2016,35(6):191 CSCD被引 9 次    
8.  Goodfellow I J. Generative adversarial nets,2014 CSCD被引 26 次    
9.  Guo Y. Residual learning for effective joint demosaicing-denoising,2020 CSCD被引 1 次    
10.  He K M. Guided image filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(6):1397-1409 CSCD被引 785 次    
11.  He K M. Deep residual learning for image recognition. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition,2016:770-778 CSCD被引 577 次    
12.  Hou H. Cubic splines for image interpolation and digital filtering. IEEE Transactions on Acoustics,Speech,and Signal Processing,1978,26(6):508-517 CSCD被引 76 次    
13.  Huang G. Densely connected convolutional networks. Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition,2017:2261-2269 CSCD被引 111 次    
14.  Huang T. Lightweight deep residue learning for joint color image demosaicking and denoising. Proceedings of the 24th International Conference on Pattern Recognition,2018:127-132 CSCD被引 1 次    
15.  Ioffe S. Batch normalization: accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on Machine Learning,2015:448-456 CSCD被引 261 次    
16.  Iriyama T. Deep demosaicking considering inter-channel correlation and self-similarity. Nonlinear Theory and Its Applications,2021,12(3):453-463 CSCD被引 1 次    
17.  Jia F. Pixel-Attention CNN with color correlation loss for color image denoising. IEEE Signal Processing Letters,2021,28:1600-1604 CSCD被引 2 次    
18.  Kang M. Low-dimensional manifold model for demosaicking from a RGBW color filter array. Signal,Image and Video Processing,2020,14(1):143-150 CSCD被引 2 次    
19.  Kang Q. Deep color image demosaicking with feature pyramid channel attention. Proceedings of 2019 IEEE International Conference on Multimedia and Expo Workshops,2019:246-251 CSCD被引 1 次    
20.  Kiku D. Residual interpolation for color image demosaicking. Proceedings of 2013 IEEE International Conference on Image Processing,2013:2304-2308 CSCD被引 1 次    
引证文献 2 篇

1 岳焕景 像感域(Raw域)底层视觉重建技术进展 中国图象图形学报,2024,29(6):1646-1666
CSCD被引 0 次

2 潘俊 融合色差梯度和颜色相关性的Bayer成像插值方法 武汉大学学报. 信息科学版,2024,49(6):888-898
CSCD被引 0 次

显示所有2篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号