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. However, it is still unclear how to properly interpret saliency maps for a given image and which techniques perform most accurately. This paper presents a methodology to practically evaluate the real effectiveness of saliency map generation methods. We used three state-of-the-art network architectures along with specially prepared benchmark datasets, and we proposed a novel metric to provide a quantitative comparison of the methods. The comparison identified the most reliable techniques and the solutions which usually failed in our tests.

Noise reduction is one of the most important and still active research topics in low-level image processing due to its high impact on object detection and scene understanding for computer vision systems. Recently, we observed a substantially increased interest in the application of deep learning algorithms. Many computer vision systems use them, due to their impressive capability of feature extraction and classification. While these methods have also been successfully applied in image denoising, significantly improving its performance, most of the proposed approaches were designed for Gaussian noise suppression. In this paper, we present a switching filtering technique intended for impulsive noise removal using deep learning. In the proposed method, the distorted pixels are detected using a deep neural network architecture and restored with the fast adaptive mean filter. The performed experiments show that the proposed approach is superior to the state-of-the-art filters designed for impulsive noise removal in color digital images.

Numerous studies have examined behavioral cues to deception with low temporal video resolution, which does not enable to track the facial movements dynamics. Another problem is the lack of publicly available video databases that allow to develop computer vision algorithms dedicated to the automatic deception recognition. In this paper, we describe a novel publicly available database that consists of 101 video recordings acquired with the use of a high speed camera at 100 fps in a well-controlled laboratory environment and proper illumination. Within this database, over 1.1 million frames were coded providing the ground truth for the potential cues of deception displayed on the subject's face during telling the truth and lying. Some preliminary psychological implications are also presented.

Observations of the solar photosphere from the ground encounter significant problems caused by Earth’s turbulent atmosphere. Before image reconstruction techniques can be applied, the frames obtained in the most favorable atmospheric conditions (the so-called lucky frames) have to be carefully selected. However, estimating the quality of images containing complex photospheric structures is not a trivial task, and the standard routines applied in nighttime lucky imaging observations are not applicable. In this paper we evaluate 36 methods dedicated to the assessment of image quality, which were presented in the literature over the past 40 years. We compare their effectiveness on simulated solar observations of both active regions and granulation patches, using reference data obtained by the Solar Optical Telescope on the Hinode satellite. To create images that are affected by a known degree of atmospheric degradation, we employed the random wave vector method, which faithfully models all the seeing characteristics. The results provide useful information about the method performances, depending on the average seeing conditions expressed by the ratio of the telescope’s aperture to the Fried parameter, \(D/r_{0}\). The comparison identifies three methods for consideration by observers: Helmli and Scherer’s mean, the median filter gradient similarity, and the discrete cosine transform energy ratio. While the first method requires less computational effort and can be used effectively in virtually any atmospheric conditions, the second method shows its superiority at good seeing (\(D/r_{0}<4\)). The third method should mainly be considered for the post-processing of strongly blurred images.

In this paper a new method of eye blink detection and analysis is proposed. The described technique is based on a combination of spatial and temporal derivatives calculated in video sequences acquired with a high speed camera. The pixels of each frame are divided into two groups according to the direction and magnitude of the hybrid gradient vectors and the distance between their centers of gravity is used for the determination of the eye movement characteristics. Preliminary experiments revealed a high detection rate of eye blinks, which is not dependent on the change of head position. The proposed technique can also be used for the analysis of eye movements and can be utilized in systems which are monitoring human fatigue, drowsiness and emotional states.

Deep learning has been widely applied in many computer vision tasks due to its impressive capability of automatic feature extraction and classification. Recently, deep neural networks have been used in image denosing, but most of the proposed approaches were designed for Gaussian noise suppression. Therefore, in this paper, we address the problem of impulsive noise reduction in color images using Denoising Convolutional Neural Networks (DnCNN). This network architecture utilizes the concept of deep residual learning and is trained to learn the residual image instead of the directly denoised one. Our preliminary results show that direct application of DnCNN allows to achieve significantly better results than the state-of-the-art filters designed for impulsive noise in color images.