• Journal of Korea Multimedia Society
• /
• v.8 no.11
• /
• pp.1496-1509
• /
• 2005

In this paper, an adaptive license plate recognition system which detects and recognizes license plate at real-time by using projected plane convolution and Decision Tree Classifier is proposed. And it was tested in circumstances which presence of complex background. Generally, in expressway tollgate or gateway of parking lots, it is very difficult to detect and segment license plate because of size, entry angle and noisy problem of vehicles due to CCD camera and road environment. In the proposed algorithm, we suggested to extract license plate candidate region after going through image acquisition process with inputted real-time image, and then to compensate license size as well as gradient of vehicle with change of vehicle entry position. The proposed algorithm can exactly detect license plate using accumulated edge, projected convolution and chain code labeling method. And it also segments letter of license plate using adaptive binary method. And then, it recognizes license plate letter by applying hybrid pattern vector method. Experimental results show that the proposed algorithm can recognize the front and rear direction license plate at real-time in the presence of complex background environments. Accordingly license plate detection rate displayed $98.8\%$ and $96.5\%$ successive rate respectively. And also, from the segmented letters, it shows $97.3\%$ and $96\%$ successive recognition rate respectively.

• Journal of applied mathematics & informatics
• /
• v.30 no.3_4
• /
• pp.365-380
• /
• 2012

Non-negative matrix factorization (NMF) is a very efficient method to explain the relationship between functions for finding basis information of multivariate nonnegative data. The multiplicative update (MU) algorithm is a popular approach to solve the NMF problem, but it fails to approach a stationary point and has inner iteration and zero divisor. So the elementwisely alternating projected gradient (eAPG) algorithm was proposed to overcome the defects. In this paper, we use the fact that the equilibrium point is stable to prove the convergence of the eAPG algorithm. By using a classic model, the equilibrium point is obtained and the invariant sets are constructed to guarantee the integrity of the stability. Finally, the convergence conditions of the eAPG algorithm are obtained, which can accelerate the convergence. In addition, the conditions, which satisfy that the non-zero equilibrium point exists and is stable, can cause that the algorithm converges to different values. Both of them are confirmed in the experiments. And we give the mathematical proof that the eAPG algorithm can reach the appointed precision at the least iterations compared to the MU algorithm. Thus, we theoretically illustrate the advantages of the eAPG algorithm.

• The Journal of the Korea Contents Association
• /
• v.3 no.4
• /
• pp.17-22
• /
• 2003

In this paper, we propose the new side-view face detection method in color images which contain faces over one. It uses color and the geometrical distance between nose and chin. We convert RGB to YCbCr color space. We extract candidate regions of face using skin color information from image. And then, the extracted regions are processed by morphological filter, and the processed regions are labeled. Also, we correct the gradient of inclined face image using projected character of nose. And we detect the inclined side-view faces that have right and left 45 tips by within via ordinate. And we get 92% detection rate in 100 test images.

• Journal of Integrative Natural Science
• /
• v.3 no.4
• /
• pp.226-230
• /
• 2010

Calculation of partial charge is important in chemistry. However, because there are many methods developed, it is of considerable interest to know how to calculate and apply properly to address various chemical problems. For basis set, usually double zeta quality is acceptable, and double zeta polarization function would be enough for most cases. To describe electronic state more accurately, Many electron configurations would be necessary to describe highly strained or anionic species. The NPA population introduced new concept about amide bonds, i.e., the planar geometry of nitrogen atom may not come from resonance, but from the lowering of p-orbital energy by electronegative carbonyl carbon atom. The issues for hypervalent atomic charges was also addressed by various charge derivation scheme. When the charge schemes were applied to organolithium compounds, the ionic nature of boding was revealed. This comes from the fact that previous Mulliken partial atomic charges overemphasized the covalent character, wihout much justification. The other partial charge derivation schemes such as NPA(natural population analysis), IPP (Integrated Projected Population) showed that much more ionic picture. ESP potential derived charges are generally believed to be suitable to describe intermolecular interactions, therefore they are used for molecular dynamics simulations and CoMFA (comparative molecular field analysis). The charge derivation schemes using multipole polarization was mainly applied to reproduce experimental infrared spectroscopy. In some reports these schemes are also suitable for intermecular electrostatic interactions. Charges derived from electron density gradient have shown the some bonds are not straight, but actually bent. The proper choice of charge-calculation method along with suitable level of theory and basis set are briefly discussed.

• Journal of Magnetics
• /
• v.12 no.3
• /
• pp.97-102
• /
• 2007

We have investigated the electronic structures and magnetism of a full Heusler alloy $Co_2CrGa(001)$ surface by using the all-electron full-potential linearized augmented plane wave (FLAPW) method within the generalized gradient approximation (GGA). We considered two types of different terminations: the Co-terminated (Co-Term) and the CrGa-terminated (CrGa-Term) surfaces. From the calculated layer-projected density of states (LDOS), we found that the surface of the CrGa-Term shows nearly half-metallic character while that of the Co-Term is far from the half-metallic. For the Co-Term, the surface Co atom moves down to the bulk region by $0.05{\AA}A$, while the subsurface Cr and Ga atoms move up to the surface layer by 0.05 and $0.01{\AA}$, respectively. For the CrGa-Term, there is a large inward relaxation of the surface Ga atom $(0.07{\AA})$, but the relaxation of the surface Cr atom is very small $(0.01{\AA})$. The relaxations affect not much to the overall shapes of DOS for both terminations, but make the surface states of the surface Cr and Ga atoms for the CrGa-Term shift to higher energy that enhances the nearly half-metallic character of the CrGa-Term. The magnetic moments of the surface $Cr(2.98{\mu}_B)$ in the CrGa-Term and the surface $Co(1.17{\mu}_B)$ in the Co-Term were much increased compared to those of the inner-layers $(1.79\;and\;0.77{\mu}_B)$, respectively, while that of the subsurface Cr atom in the Co-Term was decreased to $1.19{\mu}_B$.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.31-41
• /
• 2024

Deep learning models show excellent performance in tasks such as image classification and object detection in the field of computer vision, and are used in various ways in actual industrial sites. Recently, research on improving robustness has been actively conducted, along with pointing out that this deep learning model is vulnerable to hostile examples. A hostile example is an image in which small noise is added to induce misclassification, and can pose a significant threat when applying a deep learning model to a real environment. In this paper, we tried to confirm the robustness of the edge-learning classification model and the performance of the adversarial example detection model using it for adversarial examples of various algorithms. As a result of robustness experiments, the basic classification model showed about 17% accuracy for the FGSM algorithm, while the edge-learning models maintained accuracy in the 60-70% range, and the basic classification model showed accuracy in the 0-1% range for the PGD/DeepFool/CW algorithm, while the edge-learning models maintained accuracy in 80-90%. As a result of the adversarial example detection experiment, a high detection rate of 91-95% was confirmed for all algorithms of FGSM/PGD/DeepFool/CW. By presenting the possibility of defending against various hostile algorithms through this study, it is expected to improve the safety and reliability of deep learning models in various industries using computer vision.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.88-95
• /
• 2011

An embedded mobile device mostly has lower computation power than a general purpose computer because of its relatively lower system specifications. Consequently, conventional face tracking and face detection methods, requiring complex algorithms for higher recognition rates, are unsuitable in a mobile environment aiming for real time detection. On the other hand, by applying a real-time tracking and detecting algorithm, we would be able to provide a two-way interactive multimedia service between an user and a mobile device thus providing a far better quality of service in comparison to a one-way service. Therefore it is necessary to develop a real-time face and eye tracking technique optimized to a mobile environment. For this reason, in this paper, we proposes a method of tracking horizontal face position of a user on a T-DMB device for enhancing the quality of 3D DMB content. The proposed method uses the orientation of edges to estimate the left and right boundary of the face, and by the color edge information, the horizontal position and size of face is determined finally to decide the horizontal face. The sobel gradient vector is projected vertically and candidates of face boundaries are selected, and we proposed a smoothing method and a peak-detection method for the precise decision. Because general face detection algorithms use multi-scale feature vectors, the detection time is too long on a mobile environment. However the proposed algorithm which uses the single-scale detection method can detect the face more faster than conventional face detection methods.