Ground truth based comparison of saliency maps algorithms.

Deep neural networks (DNNs) have achieved outstanding results in domains such as image processing, computer vision, natural language processing and bioinformatics. In recent years, many methods have been proposed that can provide a visual explanation of decision made by such classifiers. Saliency maps are probably the most popular.

Comparison of Training Strategies for Autoencoder-Based Monochromatic Image Denoising.

Monochromatic images are used mainly in cases where the intensity of the received signal is examined. The identification of the observed objects as well as the estimation of intensity emitted by them depends largely on the precision of light measurement in image pixels. Unfortunately, this type of imaging is often affected by noise, which significantly degrades the quality of the results.

Multi-Wavelength Biometric Acquisition System Utilizing Finger Vasculature NIR Imaging.

Personal identification using analysis of the internal and external characteristics of the human finger is currently an intensively developed topic. The work in this field concerns new methods of feature extraction and image analysis, mainly using modern artificial intelligence algorithms. However, the quality of the data and the way in which it is obtained determines equally the effectiveness of identification.

SUTO-Solar Through-Turbulence Open Image Dataset.

Imaging through turbulence has been the subject of many research papers in a variety of fields, including defence, astronomy, earth observations, and medicine. The main goal of such research is usually to recover the original, undisturbed image, in which the impact of spatially dependent blurring induced by the phase modulation of the light wavefront is removed. The number of turbulence-disturbed image databases available online is small, and the datasets usually contain repeating types of ground objects (cars, buildings, ships, chessboard patterns).

Modified Distance Transformation for ImageEnhancement in NIR Imaging of Finger Vein System.

Most of the current image processing methods used in the near-infrared imaging of fingervascular system concentrate on the extraction of internal structures (veins). In this paper, we proposea novel approach which allows to enhance both internal and external features of a finger. The methodis based on the Distance Transformation and allows for selective extraction of physiological structuresfrom an observed finger.

Improving sub-pixel shifts estimation in a Shack-Hartmann wavefront sensor.

In the paper, we propose a simple algorithm that improves the quality with which the displacements between images registered in the sub-apertures of a a Shack-Hartmann (SH) wavefront sensor can be determined. Instead of measuring shifts between a given sub-aperture and a reference image, the method transforms a matrix of all relative displacements between sub-apertures into a vector of final shifts estimated with significantly increased accuracy. The method can be applied to any observations employing an SH wavefront sensor, especially if a scene evolves rapidly and a reference, high-fidelity image cannot be obtained.

Analysis of Dark Current in BRITE Nanostellite CCD Sensors.

The BRightest Target Explorer (BRITE) is the pioneering nanosatellite mission dedicated for photometric observations of the brightest stars in the sky. The BRITE charge coupled device (CCD) sensors are poorly shielded against extensive flux of energetic particles which constantly induce defects in the silicon lattice. In this paper we investigate the temporal evolution of the generation of the dark current in the BRITE CCDs over almost four years after launch.

Beyond the current noise limit in imaging through turbulent medium.

Shift-and-add is an approach employed to mitigate the phenomenon of resolution degradation in images acquired through a turbulent medium. Using this technique, a large number of consecutive short exposures is registered below the coherence time of the atmosphere or other blurring medium. The acquired images are shifted to the position of the brightest speckle and stacked together to obtain high resolution and high signal-to-noise frame.