Abstract
A block-level perceptual image compression framework is proposed in this work, including a block-level just noticeable difference (JND) prediction model and a preprocessing scheme. Specifically speaking, block-level JND values are first deduced by utilizing the OTSU method based on the variation of block-level structural similarity values between two adjacent picture-level JND values in the MCL-JCI dataset. After the JND value for each image block is generated, a convolutional neural network–based prediction model is designed to forecast block-level JND values for a given target image. Then, a preprocessing scheme is devised to modify the discrete cosine transform coefficients during JPEG compression on the basis of the distribution of block-level JND values of the target test image. Finally, the test image is compressed by the max JND value across all of its image blocks in the light of the initial quality factor setting. The experimental results demonstrate that the proposed block-level perceptual image compression method is able to achieve 16.75% bit saving as compared to the state-of-the-art method with similar subjective quality. The project page can be found at https://mic.tongji.edu.cn/43/3f/c9778a148287/page.htm.
- Rich Franzen. 1999. Kodak Image Dataset. Retrieved September 24, 2020 from http://r0k.us/graphics/kodak/.Google Scholar
- Website Hosting Rating. 2020. 40+ Instagram Statistics 8 Facts for 2020. Retrieved September 24, 2020 from https://www.websitehostingrating.com/instagram-statistics/.Google Scholar
- S.-H. Bae, J. Kim, and M. Kim. 2016. HEVC-based perceptually adaptive video coding using a DCT-based local distortion detection probability model. IEEE Transactions on Image Processing 25, 7 (July 2016), 3343--3357.Google Scholar
Cross Ref
- M. Bouchakour, G. Jeannic, and F. Autrusseau. 2008. JND mask adaptation for wavelet domain watermarking. In Proceedings of the IEEE International Conference on Multimedia and Expo. 201--204.Google Scholar
- Y.-J. Chiu and T. Berger. 1999. A software-only videocodec using pixelwise conditional differential replenishment and perceptual enhancements. IEEE Transactions on Circuits and Systems for Video Technology 9, 3 (April 1999), 438--450.Google Scholar
- C. H. Chou and K. C. Liu. 2010. A perceptually tuned watermarking scheme for color images. IEEE Transactions on Image Processing 19, 11 (Nov. 2010), 2966--2982.Google Scholar
- J. D. Cock, Z. Li, M. Manohara, and A. Aaron. 2016. Complexity-based consistent-quality encoding in the cloud. In Proceedings of the IEEE International Conference on Image Processing. 179--183.Google Scholar
- ITU. 2002. Methodology for the Subjective Assessment of the Quality of Television Pictures. Rec. ITU-R BT.500-11. ITU, Geneva, Switzerland.Google Scholar
- F. Ernawan and S. H. Nugraini. 2014. The optimal quantization matrices for jpeg image compression from psychovisual threshold. Journal of Theoretical and Applied Information Technology 70, 3 (Dec. 2014), 566--572.Google Scholar
- S. Hu, H. Wang, and C.-C. J. Kuo. 2016. A GMM-based stair quality model for human perceived JPEG images. In Proceedings of the International Conference on Acoustics, Speech, and Signal Processing. 1070--1074.Google Scholar
Digital Library
- L. Jin, J. Y. Lin, S. Hu, H. Wang, P. Wang, L. Katsavounidis, A. Aaron, and C.-C. J. Kuo. 2016. Statistical study on perceived JPEG image quality via MCL-JCI dataset construction and analysis. Electronic Imaging 9 (Feb. 2016), 1--9.Google Scholar
- S. Ki, S.-H. Bae, M. Kim, and H. Ko. 2018. Learning-based just-noticeable-quantization-distortion modeling for perceptual video coding. IEEE Transactions on Image Processing 27, 7 (July 2018), 3178--3193.Google Scholar
Cross Ref
- A. Krizhevsky, I. Sutskever, and G. E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In Proceedings of the Neural Information Processing Systems Conference. 1097--1105.Google Scholar
- L. Li, W. Lin, and H. Zhu. 2014. Learning structural regularity for evaluating blocking artifacts in JPEG images. IEEE Signal Processing Letters 21, 8 (Aug. 2014), 918--922.Google Scholar
Cross Ref
- Y. Li, H. Liu, and Z. Chen. 2016. Perceptually-lossless image coding based on foveated-JND and H.265/HEVC. Journal of Visual Communication and Image Representation 40 (Aug. 2016), 600--610.Google Scholar
Digital Library
- J. Y. Lin, L. Jin, S. Hu, Z. Li, A. Aaron, and C.-C. J. Kuo. 2015. Experimental design and analysis of JND test on coded image/video. Applications of Digital Image Processing XXXVIII 9599 (Sept 2015), 1--11.Google Scholar
- W. Lin, L. Dong, and P. Xue. 2005. Visual distortion gauge based on discrimination of noticeable contrast changes. IEEE Transactions on Circuits and Systems for Video Technology 15, 7 (July 2005), 900--909.Google Scholar
Digital Library
- A. Liu, W. Lin, M. Paul, C. Deng, and F. Zhang. 2010. Just noticeable difference for images with decomposition model for separating edge and textured regions. IEEE Transactions on Circuits and Systems for Video Technology 20, 11 (Nov. 2010), 1648--1652.Google Scholar
Digital Library
- Z. Lu, W. Lin, X. Yang, E. Ong, and S. Yao. 2005. Modeling visual attention’s modulatory aftereffects on visual sensitivity and quality evaluation. IEEE Transactions on Image Processing 14, 11 (Nov. 2005), 1928--1942.Google Scholar
- Z. Pan, J. Lei, Y. Zhang, and F. L. Wang. 2018. Adaptive fractional-pixel motion estimation skipped algorithm for efficient HEVC motion estimation. ACM Transactions on Multimedia Computing, Communications, and Applications 14, 1 (Jan. 2018), 1--19.Google Scholar
Digital Library
- G. J. Sullivan, J. Ohm, W.-J. Han, and T. Wiegand. 2012. Overview of the high efficiency video coding (HEVC) standard. IEEE Transactions on Circuits and Systems for Video Technology 22, 12 (Sept. 2012), 1649--1668.Google Scholar
Digital Library
- M. Takeuchi, S. Saika, Y. Sakamoto, T. Nagashima, Z. Cheng, K. Kanai, J. Katto, K. Wei, Z. Ju, and W. Xu. 2018. Perceptual quality driven adaptive video coding using JND estimation. In Proceedings of the Picture Coding Symposium. 179--183.Google Scholar
- T. Tian and H. Wang. 2018. Large-scale video compression: Recent advances and challenges. Frontiers of Computer Science 12, 5 (Oct. 2018), 825--839.Google Scholar
Digital Library
- G. K. Wallace. 1992. The JPEG still picture compression standard. IEEE Transactions on Consumer Electronics 38, 1 (Feb. 1992), xviii–xxxiv.Google Scholar
Digital Library
- H. Wang, W. Gan, S. Hu, J. Y. Lin, L. Jin, L. Song, P. Wang, I. Katsavounidis, A. Aaron, and C.-C. J. Kuo. 2016. MCL-JCV: A JND-based H.264/AVC video quality assessment dataset. In Proceedings of the IEEE International Conference on Image Processing. 1509--1513.Google Scholar
Cross Ref
- Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. 2004. Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing 13, 4 (April 2004), 1--14.Google Scholar
Digital Library
- A. B. Watson. 1993. DCT quantization matrices visually optimized for individual images. Human Vision, Visual Processing, and Digital Display IV 1913 (Sept. 1993), 202--217.Google Scholar
- A. B. Watson, J. Hu, and J. F. McGowan. 2001. Digital video quality metric based on human vision. Journal of Electronic Imaging 10, 1 (Jan. 2001), 20--29.Google Scholar
Cross Ref
- Z. Wei and K. N. Ngan. 2009. Spatio-temporal just noticeable distortion profile for grey scale image/video in DCT domain. IEEE Transactions on Circuits and Systems for Video Technology 19, 3 (March 2009), 337--346.Google Scholar
- T. Wiegand, G. J. Sullivan, G. Bjøntegaard, and A. Luthra. 2003. Overview of the H.264/AVC video coding standard. IEEE Transactions on Circuits and Systems for Video Technology 13, 7 (Aug. 2003), 560--576.Google Scholar
Digital Library
- R. B. Wolfgang, C. I. Podilchuk, and E. J. Delp. 2013. Perceptual watermarks for digital images and video. Proceedings of the IEEE 87, 7 (July 2013), 1108--1126.Google Scholar
- J. Wu, L. Li, W. Dong, G. Shi, W. Lin, and C.-C. J. Kuo. 2017. Enhanced just noticeable difference model for images with pattern complexity. IEEE Transactions on Image Processing 26, 6 (March 2017), 2682--2693.Google Scholar
Digital Library
- J. Wu, G. Shi, W. Lin, A. Liu, and F. Qi. 2013. Just noticeable difference estimation for images with free-energy principle. IEEE Transactions on Multimedia 15, 7 (Nov. 2013), 1705--1710.Google Scholar
Digital Library
- X. Yang, W. Lin, Z. Lu, E. Ong, and S. Yao. 2005. Motion-compensated residue preprocessing in video coding based on just-noticeable-distortion profile. IEEE Transactions on Circuits and Systems for Video Technology 15, 6 (June 2005), 742--752.Google Scholar
- X. Zhang, W. Lin, and P. Xue. 2005. Improved estimation for just-noticeable visual distortion. Signal Processing 85, 4 (April 2005), 795--808.Google Scholar
Digital Library
- X. Zhang, S. Wang, K. Gu, W. Lin, S. Ma, and W. Gao. 2017. Just-noticeable difference-based perceptual optimization for JPEG compression. IEEE Signal Processing Letters 24, 1 (Jan. 2017), 96--100.Google Scholar
Cross Ref
Index Terms
Perceptual Image Compression with Block-Level Just Noticeable Difference Prediction
Recommendations
Locally Adaptive Perceptual Compression for Color Images
The main idea in perceptual image compression is to remove the perceptual redundancy for representing images at the lowest possible bit rate without introducing perceivable distortion. A certain amount of perceptual redundancy is inherent in the color ...
Perceptual watermarking using just noticeable difference model based on block classification
MobiMedia '06: Proceedings of the 2nd international conference on Mobile multimedia communicationsOne of the main goals of watermarking is to optimize capacity while preserving high video fidelity. The perceptual adjustment of the watermark is mainly based on Watson Just Noticeable Difference (JND) model. Recently, it was proposed to improve Watson ...
Perceptual watermarking using a new Just-Noticeable-Difference model
In this paper, a new watermarking scheme based on Human Visual System (HVS) modeling is proposed. The approach consists in building computational models which take into account the most common properties of the HVS that can be exploited for ...






Comments