TY - GEN
T1 - Image resolution enhancement using edge extraction and sparse representation in wavelet domain for real-time application
AU - Ponomaryov, Volodymyr I.
AU - Chavez-Roman, Herminio
AU - Gonzalez-Huitron, Victor
N1 - Funding Information:
This work was supported by: the Japan Agency for Medical Research and Development (AMED) under grant number JP17km0405108h0005 to KIi, KIs, KN, and KT, and JP17km0405205h0002 and 18km0405205h0003 to KT and MN; and by the Japan Society for the Promotion of Science (JSPS) under Grant-in-Aid for Scientific Research fostering Joint International Research (B) 18KK0244 to KIi, YH, TH, CN, and KN. Part of this study was funded by European Research Council grant ERC-2012-ADG_20120314 (grant agreement 322947) and Agence Nationale pour la Recherche “Genetransnephrose” grant ANR-16-CE17-004-01 to PR. RG is supported by National Institutes of Health / National Institutes of Diabetes and Digestive and Kidney Diseases (NIH/NIDDK) grants 5R01DK098135 and 5R01DK094987 , the Doris Duke Charitable Foundation Clinical Scientist Development Award 2009033, and a Duke Health Scholars award. MGS is supported by a National Institutes of Health grant ( R01-DK108805 ). The Nephrotic Syndrome Study Network Consortium (NEPTUNE; U54-DK-083912) is a part of the National Center for Advancing Translational Sciences (NCATS). The Rare Disease Clinical Research Network (RDCRN) was supported through a collaboration between the Office of Rare Diseases Research (ORDR), NCATS, and the National Institute of Diabetes, Digestive, and Kidney Diseases. The RDCRN is an initiative of the ORDR of NCATS. Additional funding and/or programmatic support for this project was provided by the University of Michigan, NephCure Kidney International, and the Halpin Foundation. The NEPHROVIR cohort was supported by 2 grants to Georges Deschênes from the Programme Hospitalier de Recherche Clinique: grants PHRC 2007-AOM07018 and PHRC 2011-AOM11002. The NEPHROVIR network is coordinated by the Pediatric Nephrology Unit of Robert Debré Hospital, the “Unité de Recherche Clinique de l’Est Parisien,” and the “Délégation de la Recherche Clinique de la Région Ile-de-France.” Marina Vivarelli was supported by the Associazione per la Cura del bambino Nefropatico ONLUS (Organizzazione Non Lucrativa di Utilità Sociale).
PY - 2014
Y1 - 2014
N2 - The paper presents the design and hardware implementation of novel framework for image resolution enhancement employing the wavelet domain. The principal idea of resolution enhancement consists of using edge preservation procedure and mutual interpolation between the input low-resolution (LR) image and the HF sub-band images performed via the Discrete Wavelet Transform (DWT). The LR image is used in the sparse representation for the resolution-enhancement process, employing a 1-D interpolation in set of angle directions; following, the computations of the new samples are found, estimating the missing samples. Finally, pixels are performed via the Lanczos interpolation. To preserve more edge information additional edge extraction in HF sub-bands is performed in the DWT decomposition of input image. The differences between the LL sub-band image and LR input image is used to correct the HF component, generating a significantly sharper reconstructed image. All sub-band images are used to generate the new HR image applying the inverse DWT (IDWT). Additionally, the novel framework employs a denoising procedure by using the Non-Local Means for the input LR image. An efficiency analysis of the designed and other state-of-the-art filters have been performed on the DSP TMS320DM648 by Texas Instruments through MATLAB's Simulink module and on the video card (NVIDIA® Quadro® K2000), showing that novel SR procedure can be used in real-time processing applications. Experimental results have confirmed that implemented framework outperforms existing SR algorithms in terms of objective criteria (PSNR, MAE and SSIM) as well as in subjective perception, justifying better image resolution.
AB - The paper presents the design and hardware implementation of novel framework for image resolution enhancement employing the wavelet domain. The principal idea of resolution enhancement consists of using edge preservation procedure and mutual interpolation between the input low-resolution (LR) image and the HF sub-band images performed via the Discrete Wavelet Transform (DWT). The LR image is used in the sparse representation for the resolution-enhancement process, employing a 1-D interpolation in set of angle directions; following, the computations of the new samples are found, estimating the missing samples. Finally, pixels are performed via the Lanczos interpolation. To preserve more edge information additional edge extraction in HF sub-bands is performed in the DWT decomposition of input image. The differences between the LL sub-band image and LR input image is used to correct the HF component, generating a significantly sharper reconstructed image. All sub-band images are used to generate the new HR image applying the inverse DWT (IDWT). Additionally, the novel framework employs a denoising procedure by using the Non-Local Means for the input LR image. An efficiency analysis of the designed and other state-of-the-art filters have been performed on the DSP TMS320DM648 by Texas Instruments through MATLAB's Simulink module and on the video card (NVIDIA® Quadro® K2000), showing that novel SR procedure can be used in real-time processing applications. Experimental results have confirmed that implemented framework outperforms existing SR algorithms in terms of objective criteria (PSNR, MAE and SSIM) as well as in subjective perception, justifying better image resolution.
KW - DSP
KW - Edge extraction
KW - GPU
KW - Interpolation
KW - Sparse mixing estimators
KW - Super resolution
KW - Wavelet domain
UR - http://www.scopus.com/inward/record.url?scp=84902491611&partnerID=8YFLogxK
U2 - 10.1117/12.2051552
DO - 10.1117/12.2051552
M3 - Contribución a la conferencia
AN - SCOPUS:84902491611
SN - 9781628410877
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Real-Time Image and Video Processing 2014
PB - SPIE
T2 - Real-Time Image and Video Processing 2014
Y2 - 16 April 2014 through 17 April 2014
ER -