Image Restoration in Portable Devices: Algorithms and Optimization
- 57 Downloads
Image and video data acquired by portable devices such as mobile phones are degraded by noise and blur due to the small size of optical sensors in these devices. A wide range of image restoration methods exists, yet feasibility of these methods in portable platforms is not guaranteed due to limited hardware resources on such platforms. The paper addresses this problem by focusing on denoising algorithms. We have chosen two representatives of denoising methods with state-of-the-art performance, and propose different parallel implementations and algorithmic simplifications suitable for mobile phones. In addition, an extension to resolution enhancement is presented including both visual and quantitative comparisons. Analysis of the algorithms is carried out with respect to the computation time, power consumption and output image quality.
KeywordsImage restoration Denoising Super-resolution Numerical optimization Portable devices
This work was supported by ARTEMIS JU project 621439 (ALMARVI) and partially also by the Czech Science Foundation project GA18-05360S.
- 1.Bordallo López, M., Nieto, A., Boutellier, J., Hannuksela, J., Silvén, O. (2014). Evaluation of real-time lbp computing in multiple architectures. Journal of Real-Time Image Processing, 1–22.Google Scholar
- 2.Buades, A., & Coll, B. (2005). A non-local algorithm for image denoising. In Computer vision and pattern recognition (CVPR) (pp. 60–65).Google Scholar
- 3.Buckler, M., Jayasuriya, S., Sampson, A. (2017). Reconfiguring the imaging pipeline for computer vision. In IEEE International conference on computer vision (ICCV) (pp. 975–984).Google Scholar
- 4.Burger, H.C., Schuler, C.J., Harmeling, S. (2012). Image denoising: can plain neural networks compete with BM3D? In Computer vision and pattern recognition (CVPR) (pp. 2392–2399).Google Scholar
- 10.Goossens, B., Luong, H., Aelterman, J., Pižurica, A., Philips, W. (2010). A GPU-accelerated real-time NLMeans algorithm for denoising color video sequences, (pp. 46–57). Berlin: Springer.Google Scholar
- 11.Grasso, I., Radojkovic, P., Rajovic, N., Gelado, I., Ramirez, A. (2014). Energy efficient hpc on embedded socs: optimization techniques for Mali gpu. In 2014 IEEE 28th International parallel and distributed processing symposium (pp. 123–132).Google Scholar
- 12.Hannuksela, J., Niskanen, M., Turtinen, M. (2015). Performance evaluation of image noise reduction computing on a mobile platform. In 2015 International conference on embedded computer systems: architectures, modeling, and simulation (SAMOS) (pp. 332–337).Google Scholar
- 14.Levin, A., & Nadler, B. (2011). Natural image denoising: optimality and inherent bounds. In Computer vision and pattern recognition (CVPR) (pp. 2833–2840).Google Scholar
- 15.Liu, C. (2009). Beyond pixels: exploring new representations and applications for motion analysis. Ph.D. thesis, Massachusetts Institute of Technology.Google Scholar
- 16.Márques, A., & Pardo, A. (2013). Implementation of non local means filter in GPUs, (pp. 407–414). Berlin: Springer.Google Scholar
- 17.Palma, G., Comerci, M., Alfano, B., Cuomo, S., Michele, P.D., Piccialli, F., Borrelli, P. (2013). 3d non-local means denoising via multi-gpu. In 2013 Federated conference on computer science and information systems (pp. 495–498).Google Scholar