No abstract

In this article, the authors introduce a new algorithm to identify adult images that can effectively filter out images of naked human bodies in the internet. The algorithm detects eyes, which are known as the most salient component of a human face, and makes a statistical skin color distribution model directly from each input image by choosing reliable skin samples in facial areas near the detected eyes. Skin areas over the entire image are segmented robustly with the online constructed skin color model. The authors then extract a set of representative features characterizing naked bodies from the segmented skin areas and verify if the skin regions contain naked bodies through multilayer perceptron neural networked-based learning and inference of the representative features. Experimental results are given to demonstrate that the proposed adult image detection method can identify various types of nude images effectively compared to other conventional methods.

No abstract

No abstract

In recent years, the casualties of traffic accidents caused by driving cars have been gradually increasing. In particular, there are more serious injuries and deaths than minor injuries, and the damage due to major accidents is increasing. In particular, heavy cargo trucks and high-speed bus accidents that occur during driving in the middle of the night have emerged as serious social problems. Therefore, in this study, a drowsiness prevention system was developed to prevent large-scale disasters caused by traffic accidents. In this study, machine learning was applied to predict drowsiness and improve drowsiness prediction using facial recognition technology and eye-blink recognition technology. Additionally, a CO2 sensor chip was used to detect additional drowsiness. Speech recognition technology can also be used to apply Speech to Text (STT), allowing a driver to request their desired music or make a call to avoid drowsiness while driving.

Indium sulfide nanoparticle (NP)-embedded microporous carbons co-doped with S- and N-dopants are easily prepared by a direct carbonization of the as-prepared In(iii)-based metal-organic framework (In-MOF), [EtNH][In(tdc)]·DEF, containing ditopic S-containing 2,5-thiophenedicarboxylate (tdc) bridging linkers as a potential source of S-dopant. The charge on the anionic framework of [In(tdc)] is balanced by EtNH, which is also a potential N-dopant. Simultaneous embedding of In-based NPs, S-, and N-co-doping is achieved in a simple single step carbonization of In-MOF. Three porous carbon materials (PCMs), PCM-700, PCM-800, and PCM-900, are obtained from the carbonization of In-MOF at 700, 800, and 900 °C, respectively. The gas sorption analysis indicates them as good CO sorbents. The photocatalytic degradation of methyl orange by PCMs under visible light irradiation is also effectively operable owing to the photocatalytically active semiconducting indium sulfide NP with a small bandgap. The main component of indium sulfide NPs is revealed as InS based on the powder X-ray diffraction pattern. Small amounts of metallic In and InS are also observed. The specific capacitances of PCMs are also estimated from the galvanostatic charge/discharge curves. PCM-900 exhibits the highest gravimetric specific capacitance of 99.0 F g at a current density of 0.05 A g.

In this paper, we propose an affine parameter estimation algorithm from block motion vectors for extracting accurate motion information with the assumption that the undergoing motion can be characterized by an affine model. The motion may be caused either by a moving camera or a moving object. The proposed method first extracts motion vectors from a sequence of images by using size-variable block matching and then processes them by adaptive robust estimation to estimate affine parameters. Typically, a robust estimation filters out outliers (velocity vectors that do not fit into the model) by fitting velocity vectors to a predefined model. To filter out potential outliers, our adaptive robust estimation defines a continuous weight function based on a Sigmoid function. During the estimation process, we tune the Sigmoid function gradually to its hard-limit as the errors between the model and input data are decreased, so that we can effectively separate non-outliers from outliers with the help of the finally tuned hard-limit form of the weight function. Experimental results show that the suggested approach is very effective in estimating affine parameters reliably. q

In this study, techniques were proposed for the detection of epileptic seizures from electroencephalogram (EEG) signals using the wavelet transform (WT), peak extraction and phase–space reconstruction (PSR) based Euclidean distances. In the first step, the wavelet coefficients were extracted after eliminating the noise from the EEG signals using a WT, which is a widely used signal processing technique. In the second step, the peaks were extracted from the wavelet coefficients. In the third step, the continuous peaks that were extracted were mapped to 3D coordinates using PSR. In the fourth step, the Euclidean distances between the mapped 3D coordinates and the origin were obtained. The features of the Euclidean distances obtained were extracted using statistical techniques. The final features extracted were used as inputs to the neural network with weighted fuzzy membership (NEWFM). NEWFM contains the bounded sum of weighted fuzzy memberships (BSWFMs) that can reveal the differences in the graphic characteristics between normal EEG signals and epileptic-seizure EEG signals. The BSWFMs can easily be embedded in a portable device to detect epileptic seizures from EEG signals in real life.