Sparse representation based facial image compression via multiple dictionaries and separated ROI

Taheri, Amir Masoud; Mahdavi-Nasab, Homayoun

doi:10.1007/s11042-018-6197-9

Cited by 10 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This would enhance the coding efficiency for the similar video classes, as observed in e.g. [9–11] for still images of special classes. Moreover, to extend this scheme to VC, it is of crucial importance to keep the bitrate and computational burden as low as possible, the latter being a significant issue in SR applications for both the DL and sparse coding procedures [9, 15].…”

Section: The Proposed Coding Algorithmsmentioning

confidence: 99%

“…This makes an overall O(mnkT) per frame complexity for the schemes that apply multiple dictionaries (e.g. [10,15]) to enhance the coding quality to bear higher complexities, as it is O(nkTL) per patch for [15], where L is the number of dictionaries involved. Thus, keeping the offline DL and the basic sparse coding of Figure 1, in the proposed semi-intraframe SISC2 scheme, we have also reduced the number of image patches to be sparse coded to achieve the lowest computation complexities among the relevant VC methods.…”

Section: Computational Complexity and Comparisonmentioning

confidence: 99%

“…Despite authentic works on SR-based compression dealing with special classes of image and video e.g. [9][10][11][12], there are not many general-purpose VC counterparts in the literature. Additionally, different settings of the DL, dissimilar train and test The method of [16] shares the goals of the current research.…”

Section: Computational Complexity and Comparisonmentioning

confidence: 99%

“…As stated above, sparse representation (SR) based on overcomplete dictionaries has shown promising results in image compression, especially for special classes of image contents e.g. facial images [9,10], urban surveillance images [11], and Synthetic Aperture Radar (SAR) images [12,13]. These have achieved performances near the advanced DWT based JPEG2000 standard for natural images [13], and even surpassing that for specific classes [9,10], or natural images using boosted learning by an ensemble of trained dictionaries [15].…”

Section: Introductionmentioning

confidence: 99%

“…facial images [9,10], urban surveillance images [11], and Synthetic Aperture Radar (SAR) images [12,13]. These have achieved performances near the advanced DWT based JPEG2000 standard for natural images [13], and even surpassing that for specific classes [9,10], or natural images using boosted learning by an ensemble of trained dictionaries [15].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Sparse representation based intraframe and semi‐intraframe video coding schemes for low bitrates

Irannejad

Mahdavi-Nasab

2020

IET Image Processing

Self Cite

View full text Add to dashboard Cite

This paper proposes some extensions of the successful sparse coding of still images to intraframe and semi-intraframe video coding. The presented frameworks apply the efficient K-singular value decomposition and recursive least squares dictionary learning methods for sparse representation of videos to study their coding performances. In the proposed semi-intraframe schemes, namely, SISC1 and SISC2, only frame-blocks with more than a threshold deviation from the blocks of the previous frame are transmitted/coded. This reduces the required bitrate and prevents the sparse coding of similar blocks, leading to more efficient video coding methods. The results show that the dictionary learning-based intraframe coding improves the rate-distortion performance of the conventional Motion-JPEG and Motion-JPEG2000 at low bitrates for more than about 3 and 0.5 dB of PSNR on average (for 0.2-1 bpp compression), respectively. The proposed methods outperform the basic dictionary learning-based coding, especially for slower changing videos, generally, with more than 3 dB superiority on average over the tested bitrates. These schemes even present superior performance than the HEVC in the intramode for the complex textured or cluttered scenes. The proposed SISC2 method also saves up to about 50% of the sparse coding computational cost by preventing the coding of more similar frame-blocks. 1 This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: The Proposed Coding Algorithmsmentioning

confidence: 99%