A New Method for Face Recognition Using Convolutional Neural Network

In this paper, a 3D reconstruction algorithm using CT slices of human pelvis is presented. We propose the method for 3D image reconstruction that is based on a combination of the SURF (Speeded-Up Robust Features) descriptor and SSD (Sum of Squared Differences) matching algorithm using image segmentation with aim to obtain accurate 3D model of human pelvis. Firstly, we apply image filtering for noise removing and smoothing. Next, the filtered image is split into segments using Mean- Shift segmentation algorithm. Secondly, the edges using Canny edge detector are extracted. Then, for each segment we look at the associated corresponding points. The best corresponding points of all the segments using SURF-SSD method were obtained. The smaller is the value of SSD at a particular pixel, the more similarity exists between the first image and the second image in the neighborhood of that pixel. Finally, we have integrated the Mean-Shift segmentation algorithm with the SURF-SSD method. The obtained experimental results demonstrate that the SURF-SSD algorithm in combination with image segmentation provides accurate 3D model of human pelvis.

This paper proposes a 3D surface registration algorithm based on the iterated closest point algorithm (ICP). The proposed algorithm uses the Scale-Invariant Feature Transform (SIFT) functions for initial alignment in combination with the K-Nearst Neighbor (KNN) algorithm for function comparison and the Iterative Closest Point (ICP) algorithm weighted for performing accurate registration. First, the point area properties are used for corresponding cloud point areas. Second, files with associated regions are classified to calculate the initial registration transformation matrix. Based on this combination, the correct matching points were extracted between the input data. The proposed registration approach is able to perform automatic registration without any assumptions about their initial positions. Experimental results using biomedical data (CT data) indicate the effectiveness of the proposed approach. Experimental results show that the proposed algorithm increases the number of correct function correspondences while reducing significantly corresponding errors compared to the original ICP and RPM algorithms.

The advancement in science and technology has resulted in the invention and widespread usage of many electrical devices in the daily lives of humans. The exponential use of modern electronic facilities has increased electromagnetic field exposure in the current population. Therefore, the presented article deals with designing, constructing, and testing a new applicator system developed for cells electromagnetic biocompatibility studies. The applicator system is intended for studying the non-thermal impacts of low-frequency magnetic field on cell cultures growth. Main attention is focused on increasing the capacity of the applicator and effectivity of the experiments. The key idea is to reach high level of the magnetic field homogeneity in an area of interest and the temperature stability during the biocompatibility studies. The applicator system is designed based on numerical simulations and its construction, measurements, and properties evaluation are also reported for proving the applicator’s functionality. The new applicator allows performing five parallel experiments at the same time under the same conditions. The simulation together with the experimental results confirm that the magnetic field homogeneity reaches 99% in the area of interest and the maximum temperature instability is lower than 2% during the experiments. The effectiveness of new applicator is tested and proved during preliminary experiments with Saccharomyces Cerevisiae cells. The observed effects of MF exposure represent maximal stimulation of 74% and maximal inhibition of 49%. The reason why MF with the same parameters induces inhibition in one sample and stimulation in the other will be the subject of further research.

Normal or excessive oxidative metabolism in organisms is essential in physiological and pathophysiological processes, respectively. Therefore, monitoring of biological oxidative processes induced by the chemical or physical stimuli is nowadays of extreme importance due to the environment overloaded with various physicochemical factors. Current techniques typically require the addition of chemical labels or light illumination, which perturb the samples to be analyzed. Moreover, the current techniques are very demanding in terms of sample preparation and equipment. To alleviate these limitations, we propose a label-free monitoring tool of oxidation based on biological autoluminescence (BAL). We demonstrate this tool on Saccharomyces cerevisiae cell culture. We showed that BAL can be used to monitor chemical perturbation of yeast due to Fenton reagents initiated oxidation—the BAL intensity changes with hydrogen peroxide concentration in a dose-dependent manner. Furthermore, we also showed that BAL reflects the effects of low-frequency magnetic field on the yeast cell culture, where we observed a disturbance of the BAL kinetics in the exposed vs. control case. Our results contribute to the development of novel techniques for label-free, real-time, noninvasive monitoring of oxidative processes and approaches for their modulation.

This paper details our further experiments pertaining to the influence of low frequency electromagnetic fields (LF EMF) on the growth dynamics of two wild-type Saccharomyces cerevisiae strands. We opted to explore frequencies beyond the usual 5060Hz range, motivated by the ion parametric resonance theory and several studies which discovered and recorded endogenous biosignals in various Saccharomyces cerevisiae strands in the 0.42.0kHz frequency range, most probably stemming from microtubules. Both yeast strands used in our experiments have been subjected to continuous 66-hour session of LF EMF exposure (frequencies 1.2, 1.4, 1.6, 1.8, and 2.0kHz; average magnetic flux density 2.43mT) under identical ambient conditions. Experiment results indicate a frequency-dependent proliferative response of both yeast strands. This paper details our further experiments pertaining to the influence of low frequency electromagnetic fields (LF EMF) on the growth dynamics of two wild-type Saccharomyces cerevisiae strands. We opted to explore frequencies beyond the usual 5060Hz range, motivated by the ion parametric resonance theory and several studies which discovered and recorded endogenous biosignals in various Saccharomyces cerevisiae strands in the 0.42.0kHz frequency range, most probably stemming from microtubules. Both yeast strands used in our experiments have been subjected to continuous 66-hour session of LF EMF exposure (frequencies 1.2, 1.4, 1.6, 1.8, and 2.0kHz; average magnetic flux density 2.43mT) under identical ambient conditions. Experiment results indicate a frequency-dependent proliferative response of both yeast strands.