Nombre: THAÍS PEDRUZZI DO NASCIMENTO
Tipo: PhD thesis
Fecha de publicación: 17/05/2021
Supervisor:
Nombre |
Papel |
|---|---|
| EVANDRO OTTONI TEATINI SALLES | Advisor * |
Junta de examinadores:
| Nombre |
Papel |
|---|---|
| EVANDRO OTTONI TEATINI SALLES | Advisor * |
| HÉLIO PEDRINI | External Examiner * |
| JUGURTA ROSA MONTALVÃO FILHO | External Examiner * |
| PATRICK MARQUES CIARELLI | Internal Examiner * |
| RODRIGO VAREJÃO ANDREÃO | Internal Examiner * |
Sumario: The aim of multi-frame super-resolution is to generated a high resolution image from several low resolution imagens, from the alignment of them and the use regularization, which weighs noise suppression and edge information restoration. In this context, three approaches are purposed in this thesis, using local information and Demons registration: the hybrid approach, Demons super-resolution and the patch-based approach. Regarding the hybrid approach, multiple single layer neural networks were trained by the Regularized Extreme Learning Machine algorithm and implemented jointly with the multi-frame super-resolution methods Bilateral Total Variation (BTV) and Iterative Re-Weighted Super-Resolution (IRWSR), resulting in HyBTV and HyIRWSR, respectively. For Demons super-resolution two methods were proposed: D-BTVIR and D-IRWISR, which combine Demons registration with BTV-based an IRWSR-reconstruction, respectively. And for the patch-based approach (PB), which consists of aligning the patches, scan and super-resolve
them individually, three methods were proposed: PB - no classification, PB - smoothness and PB - variance. For PB - no classification all patches are super-resolved by IRW, which is based on IRWSR. For PB - smoothness, the patches are classified as homogeneous or not, by using smoothness as metrics, and super-resolved via bicubic interpolation, if homogeneous or via IRW, otherwise. The same procedure is done for PB - variance, but considering variance as metrics. Experiments were conducted using simulated deformation in 119
images, from Set5, Se14 and B100. PSNR, SSIM and the execution time were analyzed by the use of Friedman, Nemenyi and Wilcoxon hypothesis tests, besides visual analysis. The Wilcoxon tests suggested a better performance of HyBTV over BTV with 99% reliability (p-value = 1.26 × 10−11), and of HyIRWSR over IRWSR (p−value = 3.17 × 10−6), besides better time-quality trade-off of HyBTV over IRWSR, which is, on average, 3.6 times slower
than the first one. For the Demons-based approach, the Wilcoxon test suggested better performance of D-BTVIR over BTV with p-value = 3.52 × 10−7, and the same thing was noted considering D-IRWIR over IRWSR, with p-value 2.95 × 10−8. The Nemenyi test suggested statistical equivalence between D-BTVIR and IRWSIR, however, D-BTVIR was 7.2 times faster. Nemenyi test also suggested better performance of the three variations of
PB, when compared to BTV and IRWSR, besides statistical equivalence with each other, with PB - variance being the fastest one of them. Finally, the visual analysis supported the results from the hypothesis tests.
