Wyniki wyszukiwania - BazTech

1

Interpolation merge as augmentation technique in the problem of ship classification

Połap Dawid, Włodarczyk-Sielicka Marta

Annals of Computer Science and Information Systems

|

2020

|

Vol. 21

443--446

EN

Quite a common problem during training the classifier is a small number of samples in the training database, which can significantly affect the obtained results. To increase them, data augmentation can be used, which generates new samples based on existing ones, most often using simple transformations. In this paper, we propose a new approach to generate such samples using image processing techniques and discrete interpolation method. The described technique creates a new image sample using at least two others in the same class. To verify the proposed approach, we performed tests using different architectures of convolution neural networks for the ship classification problem.

2

Monte Carlo based reduction of image resolution in view of no-reference image quality assessment

Okarma K., Lech P., Polakowski A., Gajda S.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 2

68-70

EN

In the paper a fast algorithm of image downsampling is presented which is based on the estimation of mean local luminance using the Monte Carlo method assuming the division of an image into smaller non-overlapping blocks. Due to modifications proposed in the paper, one can obtain similar results than for classical methods compared using recently proposed no-reference image quality metrics. Nevertheless, further optimization requires the development of no-reference image quality metrics with higher accordance to human perception of typical distortions.

PL

W artykule zaprezentowano szybki algorytm redukcji rozdzielczości obrazu oparty na estymacji średniej jasności w bloku z użyciem metody Monte Carlo. Dzięki zaproponowanym modyfikacjom możliwe jest uzyskanie rezultatów podobnych do klasycznych metod, porównywanych z wykorzystaniem metod “ślepej” oceny jakości obrazów opracowanych w ostatnich latach. Dalsza optymalizacja wymaga jednakże opracowania “ślepych” wskaźników jakości obrazu charakteryzujących się wyższą korelacją z percepcją typowych zniekształceń obrazu przez człowieka.

3

Optimal polar image sampling

Dinčić M. R., Perić Z. H., Jovanović A. Ž.

Opto-Electronics Review

|

2011

|

Vol. 19, No. 2

249-255

EN

In this paper, a problem of efficient image sampling (deployment of image sensors) is considered. This problem is solved using techniques of two-dimensional quantization in polar coordinates, taking into account human visual system (HVS) and eye sensitivity function. The optimal radial compression function for polar quantization is derived. Optimization of the number of the phase levels for each amplitude level is done. Using optimal radial compression function and optimal number of phase levels for each amplitude level, optimal polar quantization is defined. Using deployment of quantization cells for the optimal polar quantization, deployment of image sensors is done, and therefore optimal polar image sampling is obtained. It is shown that our solution (the optimal polar sampling) has many advantages compared to presently used solutions, based on the log-polar sampling. The optimal polar sampling gives higher SNR (signal-to-noise ratio), compared to the log-polar sampling, for the same number of sensors. Also, the optimal polar sampling needs smaller number of sensors, to achieve the same SNR, compared to the log-polar sampling. Furthermore, with the optimal polar sampling, points in the image middle can be sampled, which is not valid for the log-polar sampling. This is very important since human eye is the most sensitive to these points, and therefore the optimal polar sampling gives better subjective quality.