• Journal of KIISE:Software and Applications
• /
• v.36 no.11
• /
• pp.936-946
• /
• 2009

A graph cuts method has recently attracted a lot of attentions for image segmentation, as it can globally minimize energy functions composed of data term that reflects how each pixel fits into prior information for each class and smoothness term that penalizes discontinuities between neighboring pixels. In previous approaches to graph cuts-based automatic image segmentation, GMM(Gaussian mixture models) is generally used, and means and covariance matrixes calculated by EM algorithm were used as prior information for each cluster. However, it is practicable only for clusters with a hyper-spherical or hyper-ellipsoidal shape, as the cluster was represented based on the covariance matrix centered on the mean. For arbitrary-shaped clusters, this paper proposes graph cuts-based image segmentation using mean shift analysis. As a prior information to estimate the data term, we use the set of mean trajectories toward each mode from initial means randomly selected in $L^*u^*{\upsilon}^*$ color space. Since the mean shift procedure requires many computational times, we transform features in continuous feature space into 3D discrete grid, and use 3D kernel based on the first moment in the grid, which are needed to move the means to modes. In the experiments, we investigate the problems of mean shift-based and normalized cuts-based image segmentation methods that are recently popular methods, and the proposed method showed better performance than previous two methods and graph cuts-based automatic image segmentation using GMM on Berkeley segmentation dataset.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.1
• /
• pp.165-172
• /
• 2017

Machines are physically or chemically degenerated by continuous usage. One of the results of this degeneration is the process mean shift. Under the process mean shift, production cost, failure cost and quality loss function cost are increasing continuously. Therefore a periodic preventive resetting the process is necessary. We suppose that the wear level is observable. In this case, process mean shift problem has similar characteristics to the maintenance policy model. In the previous studies, process mean shift problem has been studied in several fields such as 'Tool wear limit', 'Canning Process' and 'Quality Loss Function' separately or partially integrated form. This paper proposes an integrated cost model which involves production cost by the material, failure cost by the nonconforming items, quality loss function cost by the deviation between the quality characteristics from the target value and resetting the process cost. We expand this process mean shift problem a little more by dealing the process variance as a function, not a constant value. We suggested a multiplier function model to the process variance according to the analysis result with practical data. We adopted two-side specification to our model. The initial process mean is generally set somewhat above the lower specification. The objective function is total integrated costs per unit wear and independent variables are wear limit and initial setting process mean. The optimum is derived from numerical analysis because the integral form of the objective function is not possible. A numerical example is presented.

• Journal of Korea Multimedia Society
• /
• v.10 no.7
• /
• pp.827-837
• /
• 2007

Conventional color-based object tracking using Mean Shift algorithm does not provide appropriate result when initial color distribution disappears. In this paper we propose a tracking algorithm that updates the object color sample when the color is changing. Mean Shift analysis is first used to derive the object candidate with maximum increase in density direction from current position. The color information of object is updated iteratively. The proposed algorithm achieves accurate tracking of objects when initial color samples are changed and finally disappeared. The validity of the effective approach is illustrated by the experimental results.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1413-1415
• /
• 2015

본 논문에서 우리는 의상영역의 유사성을 검사 시 색상분석에 있어 정확도를 향상시키기 위해 Bilateral 필터와 Mean-Shift 알고리즘을 적용하였다. 본 연구의 평가부분에서 필터를 적용한 영상이 의상영역의 구김이나 빛에 의한 영향이 필터를 적용하지 않은 영상보다 적다는 것을 실험을 통해 증명한다.

• Journal of Korean Society for Quality Management
• /
• v.33 no.3
• /
• pp.91-104
• /
• 2005

Tolerance analysis plays an important role in design and manufacturing stages for reducing manufacturing cost by improving producibility. In most production processes encountered in practice, a process mean may shift or drift in the long run although process is in control. This study discusses the feasibility of three most common inflation factors(Bender, Gilson and Six Sigma) as a correction to Root Sum of Squares(RSS) method to compensate heuristically for a shift of process mean and nonnormal component distributions from simulation experiments and proposes the guidelines for choosing the inflation factor.

• Annals of Occupational and Environmental Medicine
• /
• v.34
• /
• pp.35.1-35.12
• /
• 2022

Background: Shift work is known to be associated with cardiovascular disease (CVD). It has been found that inflammatory reactions are involved in the onset and progression of CVD. Therefore, the purpose of this study was to investigate the association between shift work and inflammatory markers. Methods: Among workers at an electronics manufacturing company, 2,329 workers who had a health checkup from January 2019 to December 2019 were targeted. The general and biochemical characteristics of daytime workers and shift workers were compared through the Independent-test and the χ² test. Through multiple linear regression analysis, the association with shift work and inflammatory markers was investigated. Through multiple logistic regression analysis, the association with shift work and high inflammatory markers Results: The mean total leukocytes, neutrophils, monocytes, lymphocytes of shift workers were significantly higher than those of daytime worker. The mean high-sensitivity C-reactive protein (hs-CRP) of shift workers was also higher than that of daytime workers but not significantly. In multiple linear regression, shift work was associated with increase of total leukocyte count (β = 0.367, p < 0.001) and hs-CRP (β = 0.140, p = 0.005) after adjusting for all variables. In multiple logistic regression analysis, shift work showed 2.27 times risk of high leukocyte count and 1.8 times risk of high hs-CRP level compared to daytime work after adjusting for all variables. Conclusions: This study confirmed that shift work is associated with high inflammatory markers. Considering that high inflammatory markers is independent indicator of CVD, the association between shift work and high inflammatory markers may help to understand the CVD risk of shift workers.

• Korean Journal of Occupational Health Nursing
• /
• v.13 no.2
• /
• pp.118-129
• /
• 2004

Purpose: The purpose of this study is to investigate effects of shift work on married nurses' role conflict and job satisfaction. Method: Study subjects consisted of married nurses employed at four general hospitals with over 500 beds located in Seoul and Kyunggi area. The data were collected from March 15th to April 7th, 2004 using the survey and the subjects were asked to reply through self-administrative method. Results: Mean value of role conflict of nurses who worked shift work was measured 3.12 out of 5, and that of nurses who did not was measured 2.98. Mean value of job satisfaction of nurses who worked shift work was measured 2.79 out of 5, and that of nurses who did not was measured 2.86. There was a significant reverse correlation between mean level of role conflict and of job satisfaction. Both groups, nurses who worked shift work and nurses who did not, showed significant reverse-correlation in two areas. In the case of nurses who worked shift work, role conflict not showed a significant correlation. Job satisfaction showed a significant correlation with the plan to work as a nurse and remuneration in the case of nurses who worked shift work. Duty of supporting family was the factor affecting role conflict and measured 4.2% in the case of nurses who worked shift work, and the plan to work as a nurse and the academic background in the case of nurses who did not work shift work. Conclusion: To reduce role conflict and to improve the degree of job satisfaction, there should be taken a measure to improve a financial compensating system for working shift work for nurses who worked shift work, and to help nurses not working shift work to design plans for their job as nurses with stability.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.7 no.3
• /
• pp.38-47
• /
• 2008

A vehicle counting system at intersection is designed and implemented using analyzing a video stream from a camera. To separate foreground image from background, we compare three different methods, among which Li's method is chosen. Blobs are extracted from the foreground image using connected component analysis and the blobs are tracked by a blob tracker, frame by frame. The primary tracker use only the size and location of blob in foreground image. If there is a collision between blobs, the mean-shift tracking algorithm based on color distribution of blob is used. The proposed system is tested using real video data at intersection. If some huristics is applied, the system shows a good detection rate and a low error rate.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06a
• /
• pp.281-282
• /
• 2008

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.1
• /
• pp.56-63
• /
• 2007

In this paper, an eye tracking method is presented using a neural network (NN) and mean-shift algorithm that can accurately detect and track user's eyes under the cluttered background. In the proposed method, to deal with the rigid head motion, the facial region is first obtained using skin-color model and con-nected-component analysis. Thereafter the eye regions are localized using neural network (NN)-based tex-ture classifier that discriminates the facial region into eye class and non-eye class, which enables our method to accurately detect users' eyes even if they put on glasses. Once the eye region is localized, they are continuously and correctly tracking by mean-shift algorithm. To assess the validity of the proposed method, it is applied to the interface system using eye movement and is tested with a group of 25 users through playing a 'aligns games.' The results show that the system process more than 30 frames/sec on PC for the $320{\times}240$ size input image and supply a user-friendly and convenient access to a computer in real-time operation.