• Journal of KIISE:Software and Applications
• /
• v.31 no.1
• /
• pp.54-60
• /
• 2004

Face recognition is one of the problems to be solved by appearance based matching technique. However, the appearance of face image is very sensitive to variation in illumination. One of the easiest ways for better performance is to collect more training samples acquired under variable lightings but it is not practical in real world. ]:n object recognition, it is desirable to focus on feature extraction or normalization technique rather than focus on classifier. This paper presents a simple approach to normalization of faces subject to directional illumination. This is one of the significant issues that cause error in the face recognition process. The proposed method, ICR(illumination Compensation based on Multiple Linear Regression), is to find the plane that best fits the intensity distribution of the face image using the multiple linear regression, then use this plane to normalize the face image. The advantages of our method are simple and practical. The planar approximation of a face image is mathematically defined by the simple linear model. We provide experimental results to demonstrate the performance of the proposed ICR method on public face databases and our database. The experimental results show a significant improvement of the recognition accuracy.

• Proceedings of the Korean Society of Medical Physics Conference
• /
• 2004.11a
• /
• pp.64-66
• /
• 2004

When examing patients with DRs it is necessary to remove bad pixels and lines and to correct non-uniform offsets and x-ray field. For non-uniformity correction a flat field x-ray image is needed, and to obtain it the center of detector is usually aligned with the focal spot of the x-ray tube, which is conserved when examing patients to preserve the flat field. In some of radiographic techniques, however, it is necessary to move the x-ray tube off the center position of detector or tilt the detector. We investigated the effect of detector tilting on the non-uniformity correction, and propose a method to reduce the effect using a new algorithm. The flat field of X-ray in the DR detector could be guaranteed with this result.

• Journal of Broadcast Engineering
• /
• v.17 no.3
• /
• pp.519-528
• /
• 2012

Voice activity detection (VAD) is generally conducted by extracting features from the acoustic signal and a decision rule. The performance of such VAD algorithms driven by the input acoustic signal highly depends on the acoustic noise. When video signals are available as well, the performance of VAD can be enhanced by using the visual information which is not affected by the acoustic noise. Previous visual VAD algorithms usually use single visual feature to detect the lip activity, such as active appearance models, optical flow or intensity variation. Based on the analysis of the weakness of each feature, we propose to combine intensity change measure and the optical flow in the mouth region, which can compensate for each other's weakness. In order to minimize the computational complexity, we develop simple measures that avoid statistical estimation or modeling. Specifically, the optical flow is the averaged motion vector of some grid regions and the intensity variation is detected by simple thresholding. To extract the mouth region, we propose a simple algorithm which first detects two eyes and uses the profile of intensity to detect the center of mouth. Experiments show that the proposed combination of two simple measures show higher detection rates for the given false positive rate than the methods that use a single feature.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.1
• /
• pp.25-33
• /
• 2018

Renewable energy has been of interests in the area of modern alternative fuels. Biogas is produced in waste landfill sites through anaerobic digestion processes, including hydrolysis, acidogenesis, organic acid fermentation (acetogenesis), and methane fermentation (methanogenesis). High contents of fine dust and moisture limited its utilization for direct combustion, town gas and vehicle fuel. Thus, this study proposed a new design for a cooling device using a centrifugal cyclone for simultaneous removal of fine dust and moisture as a pretreatment in the purification processes. A heat exchanger and an ID fan, which are installed inside and outside of the cyclone, in order to cool the humid gas below the freezing point and form a foggy mist. Such an atmosphere enhanced to capture fine dust as recirculating the cold mist flow. The water removal rate was 80.8% at a relative humidity of 95%, and the particle removal efficiency was 98.3% for $2.5{\mu}m$. Simultaneous removal efficiency was 70.8% and 99.6% for particle and moisture respectively.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.5
• /
• pp.21-27
• /
• 1999

In this paper, we propose an improved MLP-based English pronunciation dictionary generator to apply to the variable vocabulary word recognizer. The variable vocabulary word recognizer can process any words specified in Korean word lexicon dynamically determined according to the current recognition task. To extend the ability of the system to task for English words, it is necessary to build a pronunciation dictionary generator to be able to process words not included in a predefined lexicon, such as proper nouns. In order to build the English pronunciation dictionary generator, we use context-dependent grapheme-to-phoneme multi-layer perceptron(MLP) architecture for each grapheme. To train each MLP, it is necessary to obtain grapheme-to-phoneme training data from general pronunciation dictionary. To automate the process, we use dynamic programming(DP) algorithm with some distance metrics. For training and testing the grapheme-to-phoneme MLPs, we use general English pronunciation dictionary with about 110 thousand words. With 26 MLPs each having 30 to 50 hidden nodes and the exception grapheme lexicon, we obtained the word accuracy of 72.8% for the 110 thousand words superior to rule-based method showing the word accuracy of 24.0%.

• Journal of Korean Society of Environmental Engineers
• /
• v.36 no.7
• /
• pp.461-468
• /
• 2014

Biochar is a carbon rich solid produced by the pyrolysis of biomass such as energy crops, forestry residues, and wood wastes. Biochar returned to soil is to mitigate climate change and the feedstock of wood wastes reduces fossil fuel consumption as well as disposal costs. This study was practiced to evaluate a biochar system by gasification in terms of global warming regarding the soil application of the produced biochar. Life cycle assessment methodology was used to analyze the environmental impacts of the system, and the functional unit was 1 tonne of wood wastes. The result shows that the biochar system by using wood wastes as feedstock produces 4.048E-01 $kgCO_2-eq$ from the pre-treatment process as chipping and drying, 4.579E-01 $kgCO_2-eq$ from the pyrolysis process, and 9.070E-02 $kgCO_2-eq$ from the spreading to agricultural land, therefore total 9.534E-01 $kgCO_2-eq$ are generated. About 252 kg of $CO_2$ is still stored in the produced biochar in soil after carbon offsetting of the system. Therefore, the net carbon of the system is -251 kg of $CO_2-eq$.

• Journal of KIISE:Software and Applications
• /
• v.37 no.1
• /
• pp.29-38
• /
• 2010

We propose an interactive projection technique to display details of a large image in a high resolution and brightness by tracking a portable projector. A closed-loop based tracking method is presented to update the projected image while a user changes the position of the detail area by moving the portable projector. A marker is embedded in the large image to indicate the position to be occupied by the detail image projected by the portable projector. The marker is extracted in sequential images acquired by a camera attached to the portable projector. The marker position in the large display image is updated under a constraint that the center positions of marker and camera frame coincide in every camera frame. The image and projective transformation for warping are calculated using the marker position and shape in the camera frame. The marker's four corner points are determined by a four-step segmentation process which consists of camera image preprocessing based on HSI, edge extraction by Hough transformation, quadrangle test, and cross-ratio test. The interactive projection system implemented by the proposed method performs at about 24fps. In the user study, the overall feedback about the system usability was very high.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.6
• /
• pp.315-320
• /
• 2017

Estimating the correct pose of augmented objects on the real camera view efficiently is one of the most important questions in image tracking area. In computer vision, Homography is used for camera pose estimation in augmented reality system with markerless. To estimating Homography, several algorithm like SURF features which extracted from images are used. Based on extracted features, Homography is estimated. For this purpose, RANSAC algorithm is well used to estimate homography and DCS-RANSAC algorithm is researched which apply constraints dynamically based on Constraint Satisfaction Problem to improve performance. In DCS-RANSAC, however, the dataset is based on pattern of feature distribution of images manually, so this algorithm cannot classify the input image, pattern of feature distribution is not recognized in DCS-RANSAC algorithm, which lead to reduce it's performance. To improve this problem, we suggest the KCS-RANSAC algorithm using K-means clustering in CS-RANSAC to cluster the images automatically based on pattern of feature distribution and apply constraints to each image groups. The suggested algorithm cluster the images automatically and apply the constraints to each clustered image groups. The experiment result shows that our KCS-RANSAC algorithm outperformed the DCS-RANSAC algorithm in terms of speed, accuracy, and inlier rate.

• Proceedings of the Korean Society of Soil and Groundwater Environment Conference
• /
• 2001.04a
• /
• pp.107-110
• /
• 2001

제철소에서 매년 대량 발생되어 주로 매립처분되고 있는 제강분진의 재활용 방안으로서, 폐수처리분야에 널리 사용되고 있는 펜톤산화공정의 반응촉매원인 Fe 공급원으로서 제강분 진의 활용 가능성에 대한 연구를 수행하였다. 본 연구에서는 포항제철소에서 제철부산물로 발생되는 제강분진을 전처리 없이 산화촉매로 사용하여 김포 수도권 매립지의 침출수 처리 공정에서 펜톤산화조에 유입되는 원수를 대상으로 과산화수소에 의한 산화처리 실험을 수행하였다. 반응은 회분식으로 수행하였으며, 일반적으로 알려진 펜톤산화반응의 주요 반응조 건인 운전 pH, 과산화수소 주입량 및 분할주입, 제강분진의 주입량 등의 변화에 따른 각 조 건별 시간에 따른 반응결과를 알아보았다. 또한 기존의 Fe 공급원으로 사용되고 있는 FeSO$_4$와 처리성능 및 적용조건에 대한 비교 실험도 수행하였다. 침출수 수질변화는 TOC (Total Organic Carbon) analyzer를 사용하여 측정한 TOC값으로 나타냈으며, pH controller 와 정량펌프를 사용하여 HCl과 NaOH주입을 통해 반응기간동안 일정 pH를 유지하였다. 본 연구결과, 최적 pH 조건인 4에서 최대 75% TOC 제거율을 나타내었으며, 대부분의 반응은 30분 이내에 이루어졌다. 주어진 실험조건에서 FeSO$_4$와 비교하여 반응속도와 처리효율에서 향상된 결과를 나타내었으며 반응 후 응집침전실험에서도 보다 높은 처리효과를 얻을 수 있었다. 결론적으로, 과산화수소/제강분진 시스템을 이용한 화학적 산화처리방법은 경제성과 처리성능에서 기존의 펜톤산화공정의 대체방안으로서 향 후 적용가능성이 높을 것으로 기대된다.g, 200 mg/kg, 300 mg/kg의 순서로 함량이 점차 감소하는 결과를 얻을 수 있었다. 이상의 결과를 종합하여 볼 때 가자 메탄올추출물은 PQ 유도독성을 신장 및 폐조직에서 효과적으로 경감시키는 것으로 나타났다.ted retailers ("sellers") must accept end-of-life items returned to them by the consumers. At the local level, Taipei City implements a pay-as-you-throw program, whereby citizens pay waste collection and treatment fees through the purchase of special trash bags approved by the Taipei City Government. However. recyclables that are separated by citizens are collected free-of-charge by the City. Taichung City and Kaohsiung City, on the other hand, enforce mandatory sorting schemes, whereby citizens face penalties if they don't separate recyclables from the trash before pick-up. These programs have resulted in a significant reduction in municipal waste. Per capita waste collected per day has dropped from 1.143

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.1
• /
• pp.17-25
• /
• 2020

We present a novel multi-core CPU based parallel algorithm for the cell-connectivity information extraction algorithm, which is one of the preprocessing steps for volume rendering of unstructured grid data. We first check the synchronization issues when parallelizing the prior serial algorithm naively. Then, we propose a 3-step parallel algorithm that achieves high parallelization efficiency by removing synchronization in each step. Also, our 3-step algorithm improves the cache utilization efficiency by increasing the spatial locality for the duplicated triangle test process, which is the core operation of building cell-connectivity information. We further improve the efficiency of our parallel algorithm by employing a memory pool for each thread. To check the benefit of our approach, we implemented our method on a system consisting of two octa-core CPUs and measured the performance. As a result, our method shows continuous performance improvement as we add threads. Also, it achieves up to 82.9 times higher performance compared with the prior serial algorithm when we use thirty-two threads (sixteen physical cores). These results demonstrate the high parallelization efficiency and high cache utilization efficiency of our method. Also, it validates the suitability of our algorithm for large-scale unstructured data.