Krystian Radlak

A novel approach to the eye movement analysis using a high speed camera

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.

Trimmed Non-local Means Technique for Mixed Noise Removal in Color Images

In this paper a novel approach to the mixed noise removal in color images is proposed. The described method is a generalization of the Non-Local Means algorithm, where the pixels in the filtering window are ordered and only the most centrally located pixels in the filtering window are considered and used to calculate the weights needed for the averaging operation. The comparison with the existing state-of-the-art denoising schemes in terms of image restoration quality measures shows, that the new approach yields significantly better results in suppressing mixed noise in color digital images.

Gaze direction estimation from static images

This study presents a novel multilevel algorithm for gaze direction recognition from static images. Proposed solution consists of three stages: (i) eye pupil localization using a multistage ellipse detector combined with a support vector machines verifier, (ii) eye bounding box localization calculated using a hybrid projection function and (iii) gaze direction classification using support vector machines and random forests. The proposed method has been tested on Eye-Chimera database with very promising results. Extensive tests show that eye bounding box localization allows us to achieve highly accurate results both in terms of eye location and gaze direction classification.

Comparison of Hand Feature Points Detection Methods

This paper presents the research and comparison of four methods of hand characteristic points detection. Each method was implemented and modified in order to test their capabilities on database for hand gesture recognition. All methods are explained, tested and compared to others with other leading to final remarks. The main purpose of the research is to choose the best algorithm giving the most information about human hand that would lead to create a human – computer interaction program.

Blink Detection Based on the Weighted Gradient Descriptor

In this paper some modifications of the eye blink detection method based on the weighted gradients are presented. We propose some novel techniques of denoising of the obtained waveforms and fully automated zero-crossing detection capable to detect eye blinks. These modifications were tested on two different databases. The evaluation of results show that the introduced modifications improve performance of the proposed detection framework, in which the pixels of each video frame are divided into two groups according to the direction and magnitude of the hybrid gradient vectors. The distance between their centers of gravity is used for the determination of the eye movement characteristics. 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.

Review of Image Quality Measures for Solar Imaging

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/r0

Silesian Deception Database: Presentation and Analysis

D/r_{0}

Adaptive Non-local Means Filtering for Speckle Noise Reduction

. 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/r0<4

High dimensional local binary patterns for facial expression recognition in the wild

D/r_{0}<4

Escaping path approach for speckle noise reduction

). The third method should mainly be considered for the post-processing of strongly blurred images.