• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.5
• /
• pp.415-419
• /
• 2008

Detecting and correcting defects on LCD glasses early in the manufacturing process becomes important for panel makers to reduce the manufacturing costs and to improve productivity. Many attempts have been made and were successfully applied to detect and identify simple defects such as scratches, dents, and foreign objects on glasses. However, it is still difficult to robustly detect low-contrast defect region, called Mura or blemish area on glasses. Typically, these defect areas are roughly defined as relatively large, several millimeters of diameter, and relatively dark and/or bright region of low Signal-to-Noise Ratio (SNR) against background of low-frequency signal. The aim of this article is to present a robust algorithm to segment these blemish defects. Early 90's, a highly robust estimator, known as the Model-Fitting (MF) estimator was developed by X. Zhuang et. al. and have been successfully used in many computer vision application. Compared to the conventional Least-Square (LS) estimator the MF estimator can successfully estimate model parameters from a dataset of contaminated Gaussian mixture. Such a noise model is defined as a regular white Gaussian noise model with probability $1-\varepsilon$ plus an outlier process with probability $varepsilon$. In the sense of robust estimation, the blemish defect in images can be considered as being a group of outliers in the process of estimating image background model parameters. The algorithm developed in this paper uses a modified MF estimator to robustly estimate the background model and as a by-product to segment the blemish defects, the outliers.

• Journal of information and communication convergence engineering
• /
• v.9 no.6
• /
• pp.666-670
• /
• 2011

In this paper, we propose a stable active contour based tracking method which utilizes the bimodal segmentation technique to obtain a background color diminished image frame. The proposed method overcomes the drawback of the Mansouri model which is liable to fall into a local minimum state when colors appear in the background that are similar to the target colors. The Mansouri model has been a foundation for active contour based tracking methods, since it is derived from a probability based interpretation. By stabilizing the model with the proposed speed function, the proposed model opens the way to extend probability based active contour tracking for practical applications.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.1
• /
• pp.123-130
• /
• 2000

In this paper, we propose an extracting method of moving object contour using active contour model from image sequences acquired by fixed camera. We use an adaptive background model for robust processing in surrounding conditions. Object segmentation model detects pixels thresholded from local difference image between background and current image and extracts connected regions. Noises in boundary area of moving object we eliminated by morphological filter. The contour of segmented object is corrected by using active contour model for extracting accurate boundary of moving object. We apply the proposed method to highway image sequences and show the results of simulation.

• Speech Sciences
• /
• v.12 no.3
• /
• pp.105-114
• /
• 2005

It was verified that a speaker verification system improved its performances of EER by regularizing log likelihood ratio, using background speaker models. Recently the wireless mobile phones are becoming more dominant communication terminals than wired phones. So the need for building a speaker verification system on mobile phone is increasing abruptly. Therefore in this paper, we had some experiments to examine the performance of speaker verification based on mobile phone's voices. Especially we are focused on the performance variations in EER(Equal Error Rate) according to several background speaker's characteristics, such as selecting methods(MSC, MIX), number of background speakers, aging factor of speech database. For this, we constructed a speaker verification system that uses GMM(Gaussin Mixture Model) and found that the MIX method is generally superior to another method by about 1.0% EER. In aspect of number of background speakers, EER is decreasing in proportion to the background speakers populations. As the number is increasing as 6, 10 and 16, the EERs are recorded as 13.0%, 12.2%, and 11.6%. An unexpected results are happened in aging effects of the speech database on the performance. EERs are measured as 4%, 12% and 19% for each seasonally recorded databases from session 1 to session 3, respectively, where duration gap between sessions is set by 3 months. Although seasons speech database has 10 speakers and 10 sentences per each, which gives less statistical confidence to results, we confirmed that enrolled speaker models in speaker verification system should be regularly updated using the ongoing claimant's utterances.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.157-165
• /
• 2011

It is challenging to detect foreground objects when background includes an illumination variation, shadow or structural variation due to its motion. Basically pixel-based background models including codebook-based modeling suffer from statistical randomness of each pixel. This paper proposes an algorithm that incorporates Markov random field model into pixel-based background modeling to achieve more accurate foreground detection. Under the assumptions the distance between the pixel on the input imaging and the corresponding background model and the difference between the scene estimates of the spatio-temporally neighboring pixels are exponentially distributed, a recursive approach for estimating the MRF regularizing parameters is proposed. The proposed method alternates between estimating the parameters with the intermediate foreground detection and estimating the foreground detection with the estimated parameters, after computing it with random initial parameters. Extensive experiment is conducted with several videos recorded both indoors and outdoors to compare the proposed method with the standard codebook-based algorithm.

• Proceedings of the IEEK Conference
• /
• 2003.11b
• /
• pp.111-114
• /
• 2003

In this paper, we propose a depth-based mesh modeling method to generate virtual environment. The proposed algorithm constructs mesh model from unorganized point cloud obtained from a multi-view camera. We separate the point cloud consisting objects from the background. Then, we apply triangulation to each object and background. Since the objects and the background are modeled independently, it is possible to construct effective virtual environment. The application of proposed modeling method is applicable to entertainment, such as movie and video game and effective virtual environment generation.

• Communications for Statistical Applications and Methods
• /
• v.8 no.1
• /
• pp.299-309
• /
• 2001

In PET(Positron Emission Tomography), it is necessary to use transmission scan data in order to estimate the attenuation map. Recently, there are several empirical studies in which one might be able to estimate attenuation map and activity distribution simultaneously with emissive sinogram alone without transmission scan. However, their algorithms are based on the model in which does not include the background counts term, and so is unrealistic. If the background counts component has been included in the model, their algorithm would introduce non-monotonic reconstruction algorithm which results in vain in practice. in this paper, we develop a monotonic and parallelizable algorithm for simultaneous reconstruction of both characteristics and present the validity through some simulations.

• Journal of Biomedical Engineering Research
• /
• v.8 no.2
• /
• pp.223-230
• /
• 1987

In this paper the harmonic degrees between $\alpha$ wave and $\beta$ wave in visual evoked potential are analyzed by the bicoherence. The bicoherence analysis is based on an AR model which provides significantly better resolution than that of Fourier transform. The analysis results of visual evoked pope ntial are compared with the analysis results of background EEC. From the comparison results it is found that the harmonic degree of visual evoked potential is less than she harmonic degree of background EEG and the $\beta$ wave of visual evoke potential unlike the background EEC contains the non harmonic property of a wave more than the harmonic properity

• 한국지구물리탐사학회:학술대회논문집
• /
• 2007.06a
• /
• pp.197-202
• /
• 2007

Most of seismic reflection prospecting assumes subsurface formation to be homogeneous media. These models are not capable of estimating small scale heterogeneity which is verified by well log data or drilling core. And those synthetic seismograms by homogeneous media are limited to explain various changes at field data. So we developed a inhomogeneous velocity model which can estimate inhomogeneity of background medium to implement numerical modeling from homogeneous medium and inhomogeneous medium on the model. Background medium using three autocorrelation functions in order to generate inhomogeneous velocity media was according to dominant wavelength of background medium and correlation length of random medium. And then we compared shot gathers. The results show that numerical modeling implemented at inhomogeneous medium depicts complex wave propagation of field data.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.78-87
• /
• 2016

The major problems of recent object tracking methods are related to the inefficient detection of moving objects due to occlusions, noisy background and inconsistent body motion. This paper presents a robust method for the detection and tracking of a moving in infrared animal videos. The tracking system is based on adaptive optical flow generation, Gaussian mixture and Kalman filtering. The adaptive Gaussian model of optical flow (GMOF) is used to extract foreground and noises are removed based on the object motion. Kalman filter enables the prediction of the object position in the presence of partial occlusions, and changes the size of the animal detected automatically along the image sequence. The presented method is evaluated in various environments of unstable background because of winds, and illuminations changes. The results show that our approach is more robust to background noises and performs better than previous methods.