ABSTRACT
Image compression is a core task for mobile devices, social media and cloud storage backend services. Key evaluation criteria for compression are: the quality of the output, the compression ratio achieved and the computational time (and energy) expended. Predicting the effectiveness of standard compression implementations like libjpeg and WebP on a novel image is challenging, and often leads to non-optimal compression. This paper presents a machine learning-based technique to accurately model the outcome of image compression for arbitrary new images in terms of quality and compression ratio, without requiring significant additional computational time and energy. Using this model, we can actively adapt the aggressiveness of compression on a per image basis to accurately fit user requirements, leading to a more optimal compression.
- WebP manual, Google Developers. https://developers.google.com/speed/webp/docs/cwebp, December 2015.Google Scholar
- Independent JPEG group. http://www.ijg.org/, January 2016.Google Scholar
- C. M. Bishop. Neural Networks for Pattern Recognition. Oxford University Press, Inc., New York, NY, USA, 1995. Google ScholarCross Ref
- S. Chandra and C. S. Ellis. JPEG compression metric as a quality aware image transcoding. In 2nd USENIX Symposium on Internet Technologies & Systems (USITS'99), 1999. Google ScholarDigital Library
- S. Coulombe and S. Pigeon. Low-complexity transcoding of JPEG images with near-optimal quality using a predictive quality factor and scaling parameters. Image Processing, IEEE Transactions on, 19(3):712--721, 2010. Google ScholarDigital Library
- K. Fant. A nonaliasing, real-time spatial transform technique. Computer Graphics and Applications, IEEE, 6(1):71--80, January 1986. Google ScholarDigital Library
- ITU. Recommendation ITU-R BT.601--7. https://www.itu.int/dms_pubrec/itu-r/rec/bt/R-REC-BT.601--7--201103-I!!PDF-E.pdf, March 2011.Google Scholar
- U. Javaid. Find & remove similar photos instantly. http://www.addictivetips.com/windows-tips/find-remove-similar-photos-instantly, June 2010.Google Scholar
- A. Lewis, S. Ghosh, and N.-F. Tzeng. Run-time energy consumption estimation based on workload in server systems. In Proceedings of the 2008 Conference on Power Aware Computing and Systems, HotPower'08, pages 4--4, Berkeley, CA, USA, 2008. USENIX Association. Google ScholarDigital Library
- T. Little. The Oxford Handbook of Quantitative Methods, Vol. 2: Statistical Analysis. Oxford Library of Psychology. Oxford University Press, 2013.Google Scholar
- H. Louafi, S. Coulombe, and U. Chandra. Efficient near-optimal dynamic content adaptation applied to JPEG slides presentations in mobile web conferencing. In Advanced Information Networking and Applications (AINA), 2013 IEEE 27th International Conference on, pages 724--731, March 2013. Google ScholarDigital Library
- L. Marchesotti, F. Perronnin, D. Larlus, and G. Csurka. Assessing the aesthetic quality of photographs using generic image descriptors. In Computer Vision (ICCV), 2011 IEEE International Conference on, pages 1784--1791, Nov 2011. Google ScholarDigital Library
- M. Montgomery. Next generation video: Introducing daala part 3. https://people.xiph.org/xiphmont/demo/daala/demo3.shtml, August 2013.Google Scholar
- S. Pigeon and S. Coulombe. Computationally efficient algorithms for predicting the file size of JPEG images subject to changes of quality factor and scaling. In Communications, 2008 24th Biennial Symposium on, pages 378--382, June 2008.Google ScholarCross Ref
- S. Pigeon and S. Coulombe. Efficient clustering-based algorithm for predicting file size and structural similarity of transcoded JPEG images. In Multimedia (ISM), 2011 IEEE International Symposium on, pages 137--142, Dec 2011. Google ScholarDigital Library
- S. Pigeon and S. Coulombe. Optimal quality-aware predictor-based adaptation of multimedia messages. In Intelligent Data Acquisition and Advanced Computing Systems (IDAACS), 2011 IEEE 6th International Conference on, volume 1, pages 496--499, Sept 2011.Google ScholarCross Ref
- S. Pigeon and S. Coulombe. K-means based prediction of transcoded JPEG file size and structural similarity. International Journal of Multimedia Data Engineering and Management (IJMDEM), 3(2):41--57, 2012. Google ScholarDigital Library
- S. Pigeon and S. Coulombe. Quality-aware predictor-based adaptation of still images for the multimedia messaging service. Multimedia tools and applications, 72(2):1841--1865, 2014. Google ScholarDigital Library
- H. Tong, M. Li, H. Zhang, and C. Zhang. Blur detection for digital images using wavelet transform. In Multimedia and Expo, 2004. ICME '04. 2004 IEEE International Conference on, volume 1, pages 17--20 Vol.1, June 2004.Google Scholar
- P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features. In Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on, volume 1, pages I--511--I--518 vol.1, 2001.Google Scholar
- Z. Wang, A. Bovik, H. Sheikh, and E. Simoncelli. Image quality assessment: from error visibility to structural similarity. Image Processing, IEEE Transactions on, 13(4):600--612, April 2004. Google ScholarDigital Library
Index Terms
- Predicting and Optimizing Image Compression
Recommendations
On performance of lossless compression for HDR image quantized in color space
High dynamic range (HDR) image requires a higher number of bits per color channel than traditional images. This brings about problems to storage and transmission. Color space quantization has been extensively studied to achieve bit encodings for each ...
Conditional Entropy Coding of VQ Indexes for Image Compression
DCC '97: Proceedings of the Conference on Data CompressionVector quantization (VQ) is a source coding methodology with provable rate-distortion optimality. However, despite more than two decades of intensive research, VQ theoretical promise is yet to be fully realized in image compression practice. Restricted ...
Entropy-constrained predictive residual vector quantization of digital images
ICIP '95: Proceedings of the 1995 International Conference on Image Processing (Vol. 3)-Volume 3 - Volume 3A major problem with a VQ based image compression scheme is its codebook search complexity. Recently, a new VQ scheme called predictive residual vector quantizer (PRVQ) was proposed by Rizvi and Nasrabadi (see Proc. IEEE Int. Conf. Image Processing (...
Comments