Name: DANIEL LUIS COSMO
Publication date: 04/10/2019
Advisor:
Name |
Role |
|---|---|
| EVANDRO OTTONI TEATINI SALLES | Advisor * |
Examining board:
| Name |
Role |
|---|---|
| EVANDRO OTTONI TEATINI SALLES | Advisor * |
| HILÁRIO SEIBEL JÚNIOR | External Examiner * |
| KARIN SATIE KOMATI | External Examiner * |
| THOMAS WALTER RAUBER | External Examiner * |
Summary: Super-resolution methods aim to increase the spatial resolution of an image while maintaining
the highest possible fidelity between the estimated image and the original source from
which that image was taken. The need to increase the resolution of an image arises due to
the process of image formation through image acquisition devices. These devices sample
an image at fixed rates, depending on their internal hardware, and add blurring and noise
effects to the sampled image. To circumvent the low sampling rate of the hardware of these
devices, it is more advantageous to develop software solutions capable of increasing the
resolution of the images after the capture, through super resolution algorithms. This work
proposes a single-image super-resolution algorithm based on machine learning techniques,
WHERE an external database is used to learn a model that relates low and high-resolution
images. The method is based on multiple regressors in the form of single-hidden-layer
feed-forward neural networks trained by extreme learning machine, applied in subspaces of
the training set generated by clustering techniques. Pre and post-processing reconstruction
techniques and the training of reshaping masks are used to refine the result of reconstruction.
The proposed method stands out for the low training time and the ability to be
used in an ordinary computer, without GPUs and large amounts of RAM, while delivering
results that compete with important works in the literature.
Keywords: Super resolution, machine learning, extreme learning machines, k-means
clustering, gradient orientation.
