In this study, the distribution characteristics of particulate matter (PM) in subway platforms were investigated, and the performance of hybrid filter systems was determined through the removal efficiency of PM according to various flow rates and filter structures. The hybrid filter systems were constructed in magnetic systems as (Magnet-Magnet (MM) filters and Magnet-Cascade (MC) filters). PM removal efficiencies of these filters were investigated at a subway platform for three days including weekdays and weekends. The compositions of collected PM were also analyzed. Based on the PM measurement in the subway platforms, it was confirmed that the operation of trains had a significant effect on the increase of PM concentration, and a large number of PMs were less than 1 μm in size. For the MC filter, the removal efficiency of PM1 based on the number of particles was up to 30.5%, demonstrating a relatively high removal efficiency in comparison with the MM filter. In terms of PM10, PM removal efficiencies of the MC filter with respect to the mass concentration and the number of particles were 48.3% and 14.5%, respectively. For the MC filter, it was found that the PM removal efficiency was enhanced with the increase in the flow rate. Moreover, the relatively large particle size PM (i.e., 7.5 μm - 10 μm) denoted a maximum removal efficiency of 97% in terms of the number of particles. All PMs collected by the filter were Fecontaining PMs. As a field experiment using the hybrid filter, the applicability of magnetic particle control technology was approved. Based on this result, it is expected that this study will be used as background research for the development of fine dust control technologies in a subway environment.
의료영상에서 잡음제거는 의료영상 분야에서의 중요한 도전 과제들 중의 하나이다. 최상의 진단 결과를 얻기 위해서는 잡음과 아티펙트가 제거되고, 선명하며 깨끗한 화질의 의료영상이 필요하다. CT는 의료영상에서 중요하고 가장 보편적인 모달리티이다. CT 영상에서 주요 잡음은 양자화 잡음이다. 본 논문에서는 CT 영상에서 잡음 제거를 위한 하이브리드 필터를 제안하였다. 제안된 하이브리드 필터는 바이래터럴 필터, 신경망 윤곽선 검출기, 다층 신경망 등으로 구성되어 있다. 다층 신경망은 여러 정보들을 결합하여 개선된 출력 영상을 만들기 위한 융합 연산자로서 이용되었다. RMSE, ISNR, MSR과 CNR과 같은 화질 평가 척도가 잡음 개선의 성능 평가를 위해 사용되었다. 또한, 시각적으로도 제안된 필터가 다른 필터들에 비해 우수한 결과를 보였다. 이와같은 화질 평가 척도에 의해 본 논문에서 제안된 필터는 바이래터럴 필터나 가이드 필터보다 우수하였다. 특히, 심한 잡음이 있는 상황에서 제안된 필터는 우수한 결과를 보였다.
In this paper, I present my face detection and tracking method. First, image enhancement is carried out in HSV space especially if the input image is acquired from unconstrained illumination condition. I used a method for image enhancement in HSV space based on the local processing of image. I propose a lighting invariant face detection system based upon the edge and skin tone information of the input color image. The advantage of the proposed face detection is that, it can detect faces with different size, pose, and expression under unconstrained illumination conditions. I combined the Kalman filter with Camshift to enable track recovery after occlusions and to avoid the tracking failures caused by objects and background with similar colors to face. In my tracking method, I particularly focus on face tracking. The size and position of window are obtained after Camshift iteration. Kalman filtering is used to predict the next starting iterative point of Camshift. The experimental results show that my tracking method get the better results than Camshift in occlusion sequences and dynamic backgrounds.
Though median filter is used for removing noise and smoothing image. But, the result of it has distortion around edge. And then, this paper proposes new noise removing algorithm by recursive morphological processing. Basic operation is same each other, but there is some different processing method between recursive morphology and general morphology theory. This recursive morphological filter can be viewed as the weighted order static filter, and then it has a weighted SE(structuring element). Especially using this algorithm to remove the 10% gaussian noise, this paper confirmed that PSNR is improved about 0.642~1.5757 db reserving edge well better than the results of the traditional median filter.