基于颜色复杂度和结构张量的恰可察觉失真模型

doi:10.12066/j.issn.1007-2861.2276

上海大学学报(自然科学版) ›› 2022, Vol. 28 ›› Issue (2): 250-260.doi: 10.12066/j.issn.1007-2861.2276

基于颜色复杂度和结构张量的恰可察觉失真模型

王闯, 王永芳(), 练俊杰

上海大学通信与信息工程学院, 上海 200444

收稿日期:2020-05-21 出版日期:2022-04-30 发布日期:2022-04-28
通讯作者: 王永芳 E-mail:yfw@shu.edu.cn
作者简介:王永芳(1973--), 女, 教授, 博士,研究方向为智能多媒体处理与分析、图像视频质编码与评估等. E-mail: yfw@shu.edu.cn
基金资助:
国家自然科学基金资助项目(61671283)

Just-noticeable distortion model based on colour complexity and structure tensor

WANG Chuang, WANG Yongfang(), LIAN Junjie

School of Communication and Information Engineering, Shanghai University, Shanghai 200444, China

Received:2020-05-21 Online:2022-04-30 Published:2022-04-28
Contact: WANG Yongfang E-mail:yfw@shu.edu.cn

摘要/Abstract

摘要：

图像的恰可察觉失真(just noticeable distortion, JND)阈值是指人眼能够察觉的最小失真, 通常被用于去除图像/视频压缩中的视觉冗余. 针对 JND 模型对颜色和结构特征利用不充分的问题, 提出了一种基于颜色复杂度和结构张量的 JND 模型. 首先, 计算图像的颜色复杂度, 将其转换为与视觉敏感度相关的权值, 和对比掩蔽模型结合以提升模型的准确性; 然后, 利用结构张量对局部特征进行表示, 建立基于局部结构特征的调制因子, 估计结构不规则区域的视觉冗余程度; 最后, 将基于颜色复杂度的 JND 模型和基于结构张量的调制因子结合, 建立基于颜色复杂度和结构张量的 JND(complexity structure tensor based JND, CSJND)模型. 实验结果表明, 相比于已有的模型, 该模型在主观感知质量相同的前提下, 能使 PSNR 值明显降低; 该模型更加符合人眼的视觉特性, 能更准确地估计出 JND 阈值.

关键词: 恰可察觉失真模型, 颜色复杂度, 结构张量

Abstract:

The just noticeable distortion (JND) threshold refers to the minimum distortion at which eyes can perceive. JND can be used to remove visual redundancy derived from image or video compression. Considering that JND models do not make full use of colour features and structural information, this study proposes a JND model based on colour complexity and structure tensor. First, the colour complexity is estimated and it is used to calculate the visual weight values related to the sensitivity of human eyes. Then the estimated colour complexity is combined with the contrasting masking effect to improve the accuracy of the model. Next, utilising the local structure tensor to represent local features, the modulation factor is established to calculate the visual redundancy of irregular regions. Finally, the colour complexity structure tensor based JND (CSJND) model is estimated by combining the colour-complexity-based JND model and structure tensor modulation factor. Experimental results show that the proposed CSJND model can acquire a noticeably lower peak-signal-to-noise ratio as compared with some existing JND models while also achieving the same subjective perceptual quality. This is more consistent with human visual perception. The proposed CSJND model can also calculate the JND thresholds more accurately.

Key words: just noticeable distortion (JND) model, colour complexity, structure tensor

中图分类号:

TP37

王闯, 王永芳, 练俊杰. 基于颜色复杂度和结构张量的恰可察觉失真模型[J]. 上海大学学报(自然科学版), 2022, 28(2): 250-260.

WANG Chuang, WANG Yongfang, LIAN Junjie. Just-noticeable distortion model based on colour complexity and structure tensor[J]. Journal of Shanghai University（Natural Science Edition）, 2022, 28(2): 250-260.

图/表 8

图1

图2

图3

图4

图5

图6

图7

表1

参考文献 25

[1]	Yuan D, Zhao T, Xu Y, et al. Visual JND: a perceptual measurement in video coding[J]. IEEE Access, 2019, 7: 29014-29022. doi: 10.1109/ACCESS.2019.2901342
[2]	Li J, Zhang H, Wang J, et al. Orientation-aware saliency guided JND model for robust image watermarking[J]. IEEE Access, 2019, 7: 41261-41272. doi: 10.1109/ACCESS.2019.2904272
[3]	Su H, Jung C. Perceptual enhancement of low light images based on two-step noise suppression[J]. IEEE Access, 2018, 6: 7005-7018. doi: 10.1109/ACCESS.2018.2790433
[4]	Qi F, Zhao D, Fan X, et al. Stereoscopic video quality assessment based on visual attention and just-noticeable difference models[J]. Signal Image & Video Processing, 2016, 10(4): 737-744.
[5]	Yang X K, Ling W S, Lu Z K, et al. Just noticeable distortion model and its applications in video coding[J]. Signal Processing Image Communication, 2005, 20(7): 662-680. doi: 10.1016/j.image.2005.04.001
[6]	Liu A, Lin W, Paul M, et al. Just noticeable difference for images with decomposition model for separating edge and textured regions[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2010, 20(11): 1648-1652.
[7]	Wu J, Shi G, Lin W, et al. Just noticeable difference estimation for images with free-energy principle[J]. IEEE Transactions on Multimedia, 2013, 15(7): 1705-1710. doi: 10.1109/TMM.2013.2268053
[8]	Wu J, Li L, Dong W, et al. Enhanced just noticeable difference model for images with pattern complexity[J]. IEEE Transactions on Image Processing, 2017, 26: 2682-2693. doi: 10.1109/TIP.2017.2685682
[9]	Zeng Z, Zenga H, Chen J, et al. Visual attention guided pixel-wise just noticeable difference model[J]. IEEE Access, 2019, 7: 132111-132119. doi: 10.1109/ACCESS.2019.2939569
[10]	Wei Z, Ngan K. Spatio-temporal just noticeable distortion profile for grey scale image/video in DCT domain[J]. IEEE Transactions on Circuits & Systems for Video Technology, 2009, 19(3): 337-346.
[11]	Wan W, Wu J, Xie X, et al. A novel just noticeable difference model via orientation regularity in DCT domain[J]. IEEE Access, 2017, 5: 22953-22964. doi: 10.1109/ACCESS.2017.2699858
[12]	Wang H K, Yu L, Li T S, et al. A DCT-JND profile for disorderly concealment effect[C]// Advances in Multimedia Information Processing. 2018: 188-199.
[13]	Wang H K, Li Y, Wang S, et al. A novel foveated-jnd profile based on an adaptive foveated weighting model[C]// 2018 IEEE Visual Communications and Image Processing (VCIP). 2018: 1-4.
[14]	Ki S, Bae S H, Kim M, et al. Learning-based just-noticeable-quantization- distortion modeling for perceptual video coding[J]. IEEE Transactions on Image Processing, 2018, 27: 3178-3193. doi: 10.1109/TIP.2018.2818439
[15]	Liu H, Zhang Y, Zhang H, et al. Deep learning based picture-wise just noticeable distortion prediction model for image compression[J]. IEEE Transactions on Image Processing, 2019, 29: 641-656. doi: 10.1109/TIP.2019.2933743
[16]	Pian Z, Lu P P, Wu L X, et al. A new image segmentation approach with structure tensor and random walk[C]// 2008 Second International Symposium on Intelligent Information Technology Application. 2008: 432-436.
[17]	Landstrom A, Thurley M J. Adaptive morphology using tensor-based elliptical structuring elements[J]. Pattern Recognition Letters, 2013, 34(12): 1416-1422. doi: 10.1016/j.patrec.2013.05.003
[18]	Anders L. An approach to adaptive quadratic structuring functions based on the local structure tensor[C]// International Symposium on Mathematical Morphology and Its Applications to Signal and Image Processing. 2015.
[19]	许爽. 基于颜色特征的图像复杂度研究[D]. 开封: 河南大学, 2016.
[20]	Wang J, Wan W B, Li X X, et al. Color image watermarking based on orientation diversity and color complexity[J]. Expert Systems with Application, 2020, 140: 112868. doi: 10.1016/j.eswa.2019.112868
[21]	Chen H, Hu R, Hu J, et al. Temporal color just noticeable distortion model and its application for video coding[C]// Proceedings of the 2010 IEEE International Conference on Multimedia and Expo. 2010.
[22]	于永健, 王向阳, 吴俊峰. 基于颜色复杂度的加权颜色直方图图像检索算法[J]. 小型微型计算机系统, 2009, 30(3): 507-511.
[23]	Wu J, Lin W, Shi G, et al. Pattern masking estimation in image with structural uncertainty[J]. IEEE Transactions on Image Processing, 2013, 22(12): 4892-4904. doi: 10.1109/TIP.2013.2279934
[24]	赵高鹏, 李磊, 王建宇. 基于结构张量分析的弱小目标单帧检测[J]. 光子学报, 2019, 48(1): 135-145.
[25]	Ma C, Lü X, Ao J. Difference based median filter for removal of random value impulse noise in images[J]. Multimedia Tools and Applications, 2019, 78(1): 1131-1148. doi: 10.1007/s11042-018-6442-2

基于颜色复杂度和结构张量的恰可察觉失真模型

Just-noticeable distortion model based on colour complexity and structure tensor

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 25

相关文章 3

编辑推荐

Metrics

本文评价

[1]	徐正则, 张文俊. 一种基于深度图像的左右手同步分割改进方法[J]. 上海大学学报(自然科学版), 2021, 27(3): 454-465.
[2]	XU Zhengze, ZHANG Wenjun. Hand segmentation from a single depth image based on histogram threshold selection and shallow CNN[J]. 上海大学学报(自然科学版), 2018, 24(5): 675-685.
[3]	李智华张青春刘振. 蓄电池剩余电量的模糊预测[J]. 上海大学学报(自然科学版), 2009, 15(4): 364-368.