• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.457-461
• /
• 2010

Even though face recognition researches have been developed for a long ago, there is no practical face recognition system in real life. It is caused by several real situations where non-facial components such as glasses, scarf, and hair occlude facial components while facial images in a face database are well designed. This occlusion decreases recognition performance. Previous approaches in recent years have tried to solve non-facial components but have not resulted in enough performance. In this paper, we propose a method to handle this problem based on support vector data description, which trains the hyperball in feature space to find the minimum distance estimating the approximated face. In order to evaluate its performance and validate the effectiveness of the proposed method, we make several experiments and the results show that the proposed method has a considerable effectiveness.

• Journal of the Institute of Convergence Signal Processing
• /
• v.8 no.1
• /
• pp.15-21
• /
• 2007

We propose a 3D modeling method for surface inspection of non-constant velocity moving object. 1'lie laser lines reflect tile surface curvature. We can acquire 3D surface information by analyzing projected laser lines on object. In this paper, we use multi-line laser to improve the single stripe method and high speed of single frame. Binarization and edge extraction of frame image were proposed for robust laser each line extraction. A new labeling method was used for laser line labeling. We acquired some feature points for image matching from the frame data and juxtaposed the frames data to obtain a 3D shape image. We verified the superiority of proposed method by applying it to inspect container's damages.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.5
• /
• pp.653-659
• /
• 2011

In general, electrocardiogram(ECG) signals are sampled with a frequency over 200Hz and stored for a long time. It is required to compress data efficiently for storing and transmitting them. In this paper, a method for compression of ECG data is proposed, using by Non Uniform B-spline approximation, which has been widely used to approximation theory of applied mathematics and geometric modeling. ECG signals are compressed and reconstructed using B-spline basis function which curve has local controllability and control a shape and curve in part. The proposed method selected additional knot with each step for minimizing reconstruction error and reduced time complexity. It is established that the proposed method using B-spline approximation has good compression ratio and reconstruct besides preserving all feature point of ECG signals, through the experimental results from MIT-BIH Arrhythmia database.

• Journal of Digital Contents Society
• /
• v.11 no.4
• /
• pp.597-606
• /
• 2010

This paper describes a real-time camera tracking framework specifically designed to track a monocular camera in an AR workspace. Typically, the Kalman filter is often employed for the camera tracking. In general, however, tracking performances of conventional methods are seriously affected by unpredictable situations such as ambiguity in feature detection, occlusion of features and rapid camera shake. In this paper, a recursive Bayesian sampling framework which is also known as the particle filter is adopted for the camera pose estimation. In our system, the camera state is estimated on the basis of the Gaussian distribution without employing additional uncertainty model and sample weight computation. In addition, the camera state is directly computed based on new sample particles which are distributed according to the true posterior of system state. In order to verify the proposed system, we conduct several experiments for unstable situations in the desktop AR environments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11A
• /
• pp.1872-1879
• /
• 2001

As multiview video applications become more popular, correspondence problem for stereo image matching plays an important role in expanding view points. Thus, we propose an efficient dense disparity estimation algorithm considering features of each image pair of multiview image sets. Main concepts of the proposed algorithm are based on the region-dividing-bidirectional-pixel-matching method. This algorithm makes matching process efficient and keeps the reliability of the estimated disparities. Other improvement have obtained by proposed cost function, matching window expanding technique, disparity regularization, and disparity assignment in ambiguous region. These techniques make disparities more stable by removing false disparities and ambiguous regions. The estimated disparities are used to synthesize intermediate views of multiview images. Computer simulation demonstrates the excellence of the proposed algorithm in both subjective and objective evaluations. In addition, processing time is reduced as well.

• Journal of Climate Change Research
• /
• v.6 no.2
• /
• pp.95-104
• /
• 2015

To discuss whether we have credible estimations about historical surface temperature evolution since industrial revolution or not, present study investigates consistencies and differences of averaged surface air temperature since 1900 between the multiple data sources: Hadley Center Climate Research Unit (HadCRU4) surface air temperature data, ECMWF 20 Century Reanalysis data (ERA20CR), and NCEP 20 Century Reanalysis data (NCEP20CR). Averaged surface temperatures are obtained for the global, polar (90S~60S, 60N~0N), midlatitude (60S~30S, 30N~60N), tropical (30S~30N) region, separately. From the analysis, we show that: 1) spatio-temporal inhomogenity and scarcity of HadCRU4 data are not major obstacles in the reliable estimation of global surface air temperature. 2) Globally averaged temperature variability is largely contributed by those of tropical and midlatitude, which occupy more than 70% of earth surface in area. 3) Both data show consistent temperature variability in tropical region. 4) ERA20CR does not capture warm period over Arctic region in early 1900s, which is obvious feature in HadCRU4 data. Discrepancies among datasets suggest that high-level caution is needed especially in the interpretation of large Arctic warming in the early 1900s, which is often regarded as a natural variability in the Arctic region.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1814-1828
• /
• 2021

Low-light image enhancement is a key technique to overcome the quality degradation of photos taken under scotopic vision illumination conditions. The degradation includes low brightness, low contrast, and outstanding noise, which would seriously affect the vision of the human eye recognition ability and subsequent image processing. In this paper, we propose an approach based on deep learning and Retinex theory to enhance the low-light image, which includes image decomposition, illumination prediction, image reconstruction, and image optimization. The first three parts can reconstruct the enhanced image that suffers from low-resolution. To reduce the noise of the enhanced image and improve the image quality, a super-resolution algorithm based on the Laplacian pyramid network is introduced to optimize the image. The Laplacian pyramid network can improve the resolution of the enhanced image through multiple feature extraction and deconvolution operations. Furthermore, a combination loss function is explored in the network training stage to improve the efficiency of the algorithm. Extensive experiments and comprehensive evaluations demonstrate the strength of the proposed method, the result is closer to the real-world scene in lightness, color, and details. Besides, experiments also demonstrate that the proposed method with the single low-light image can achieve the same effect as multi-exposure image fusion algorithm and no ghost is introduced.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4065-4083
• /
• 2021

Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.105-111
• /
• 2023

Currently, most of content restoration using artificial intelligence learning is 2D learning. However, 3D form of artificial intelligence learning is in an incomplete state due to the disadvantage of requiring a lot of computation and learning speed from the existing 2 axes (X, Y) to 3 axes (X, Y, Z). The purpose of this paper is to secure a data-set for artificial intelligence learning by analyzing and 3D modeling the stone pagodas of ourinari by era based on the two-dimensional information (image) of cultural assets. In addition, we analyzed the differences and characteristics of towers in each era in Korea, and proposed a feature modeling method suitable for artificial intelligence learning. Restoration of cultural properties relies on a variety of materials, expert techniques and historical archives. By recording and managing the information necessary for the restoration of cultural properties through this study, it is expected that it will be used as an important documentary heritage for restoring and maintaining Korean traditional pagodas in the future.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.1
• /
• pp.31-43
• /
• 2015

This study had been aimed to conduct the camera calibration on VLBI antenna in the Space Geodetic Observation Center of Sejong City with a low-cost digital camera, which embedded in a mobile phone to determine the three-dimension position coordinates of the VLBI antenna, based on stereo images. The initial values for the camera calibration have been obtained by utilizing the Direct Linear Transformation algorithm and the commercial digital photogrammetry system, PhotoModeler $Scanner^{(R)}$ ver. 6.0, respectively. The accuracy of camera calibration results was compared with that the camera calibration results, acquired by a bundle adjustment with nonlinear collinearity condition equation. Although two methods showed significant differences in the initial value, the final calibration demonstrated the consistent results whichever methods had been performed for obtaining the initial value. Furthermore, those three-dimensional coordinates of feature points of the VLBI antenna were respectively calculated using the camera calibration by the two methods to be compared with the reference coordinates obtained from a total station. In fact, both methods have resulted out a same standard deviation of $X=0.004{\pm}0.010m$, $Y=0.001{\pm}0.015m$, $Z=0.009{\pm}0.017m$, that of showing a high degree of accuracy in centimeters. From the result, we can conclude that a mobile phone camera opens up the way for a variety of image processing studies, such as 3D reconstruction from images captured.