• Korean Journal of Digital Imaging in Medicine
• /
• v.12 no.1
• /
• pp.59-64
• /
• 2010

We examined the accuracy and efficiency of phantom by applying the designed phantom in order to check daily quality assurance easily by objective criteria and to confirm daily quality assurance of linear accelerator, simulator, and CT-simulator. The results of 10 weeks of linear accelerator output dose using American Association of Physicists in Medicine(AAPM) daily quality assurance guide were measured within ${\pm}1%$ of error. Mechanical check of laser alignment, optical distance indicator(ODI), CT scanner laser and alignment of gantry lasers with the center of imaging plane were measured within ${\pm}1mm$. Daily average working time for daily quality assurance of radiation therapy equipments was 38 minutes. The designed phantom was easy to install and daily quality assurance was possible with only one installation. The aspects reproducibility and efficiency as well as accuracy of quality assurance were excellent.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.21 no.4
• /
• pp.293-299
• /
• 2003

In the future, the design of road should be convenient in using of high-technology information and it needs the design of alignment that is able to make the maximum vehicles inducement function appropriated for CNS(Car Navigation System). So it needs to analysis appropriately the alignment of road for the improvement design of road which is established and to make the design of road and the coordinate of the main points. Therefore, this research had acquired the road data by RTK-GPS to accurate the analysis of road alignment and compared with Total Station. As the result, we could acquire the design source of the road alignment using RTK-GPS. Also, it was estimated the accuracy after comparing the design with RTK-GPS coordinates. We made an analysis of the degree of slant or the ups and downs of surface. We made an analysis of three dimensional visual information which was included in GSIS concept and estimated the accuracy. Finally, we analyzed the earth volume calculation by comparing with Total Station.

• Journal of Korea Society of Industrial Information Systems
• /
• v.22 no.2
• /
• pp.61-70
• /
• 2017

In This Paper, the Classification Speed of Vehicle Headlight Modules is Improved by a CPU-based Parallel Processing Using OpenMP. Also, a Classification Method of Headlight Modules which Extracts their Features after Revising their Alignment is Proposed. To Analyze the Performance of the Proposed Method, the Discrimination Accuracy and the Processing Speed were Compared with the Method Using Gray Image and the Method Using Line Detection. As the Results of the Analysis, in the Discrimination Accuracy, the Proposed Method and the Line Detection Method Showed good Performance, but the Proposed Method Showed Better Performance than the Line Detection Method by the Processing Speed. Also, the Gray-based Method was the Best in Processing Speed, but the Proposed Method is Better than the Gray-based Method in the Discrimination Accuracy.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.9
• /
• pp.112-123
• /
• 1994

In this paper, inspection and subpixed alignment algorithms of SMD's (Surface Mounting Devices) using fuzzy morphology are proposed. First, camera calibration is performed and then the inspection algorithm detects defects such as lead bending and breaking using the ruler generated by fuzy morphology. The SMD having no defects is tested whether it is mounted in the specified position or not. The proposed subpixel alignment algorithm detects accurately orientation and position using subpixel interpolation. It consists of two parts: preprocessing and main processing steps, in which corner points and coarse orientation of a SMD are detected, and interpolation is used to obtain final parameters with wubpixel accuracy. The computer simulation shows that the proposed algorithms give more accurate parameters, and they can be applied to fast and accurate automatic surface mounting systems.

• Phonetics and Speech Sciences
• /
• v.6 no.3
• /
• pp.139-145
• /
• 2014

The paper describes methods of conducting vowel analysis from a large-scale corpus with the aids of forced alignment and optimal formant ceiling methods. 'Read Style Corpus of Standard Korean' is used for building the forced alignment system and a subset of the corpus for the processing and extraction of features for vowel analysis based on optimal formant ceiling. The results of the vowel analysis are reliable and comparable to the results obtained using traditional analytical methods. The findings indicate that the methods adopted for the analysis can be extended and be used for more fine-grained analysis without time-consuming manual labeling without losing accuracy and reliability.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.8 no.3 s.22
• /
• pp.5-10
• /
• 2005

This paper presents the new in-flight alignment method using the flight distance of vehicle in order to improve the performance of the heading error estimation. In the proposed method, the Kalman filter having the difference between GPS and SDINS position as measurements is used for levelling of SDINS and heading error is estimated utilizing the flight distance information. It is shown in the simulation results that the in-flight method proposed in this paper has the high accuracy in heading error estimation and the heading error can be very quickly estimated at the high speed vehicle, compared with the existing method using the Kalman filter.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3177-3195
• /
• 2014

In many moving object detection problems of an aerial video, accurate and robust stabilization is of critical importance. In this paper, a novel accurate image alignment algorithm for aerial electronic image stabilization (EIS) is described. The feature points are first selected using optimal derivative filters based Harris detector, which can improve differentiation accuracy and obtain the precise coordinates of feature points. Then we choose the Delaunay Triangulation edges to find the matching pairs between feature points in overlapping images. The most "useful" matching points that belong to the background are used to find the global transformation parameters using the projective invariant. Finally, intentional motion of the camera is accumulated for correction by Sage-Husa adaptive filtering. Experiment results illustrate that the proposed algorithm is applied to the aerial captured video sequences with various dynamic scenes for performance demonstrations.

• Journal of Korea Multimedia Society
• /
• v.24 no.8
• /
• pp.1020-1025
• /
• 2021

Facial alignment is very important task for human life. And facial landmark detection is one of the instrumental methods in face alignment. We introduce the stacked hourglass networks with transposed convolutional layers for facial landmark detection. our method substitutes nearest neighbor upsampling for transposed convolutional layer. Our method returns better accuracy in facial landmark detection compared to stacked hourglass networks with nearest neighbor upsampling.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.22 no.1
• /
• pp.63-71
• /
• 2004

This research is to reconstruction of railway alignment using GPS data, an investigation is made on the method of optimum simplification for reduction of unnecessary linear data, improve the accuracy by using four simplification algorithms among the methods. By applying two measured of displacement between observed data and it's simplification methods have been evaluated. The results showed that the complexities of lines is not practical to investigate simplification algorithms, the Douglas-Peucker method produced a little displacement between observed data and it's simplification. Its by using the Douglas-Peucker method to observed linear GPS data in railway track, design elements of horizontal alignment have been calculated. Then we could know that obtain the good results fur reconstruction of alignment elements through the methods and algorithns of this study.

• Journal of KIISE
• /
• v.43 no.3
• /
• pp.289-295
• /
• 2016

Malware authors spread malware variants in order to evade detection. It's hard to detect malware variants using static analysis. Therefore dynamic analysis based on API call information is necessary. In this paper, we proposed a malware family recommendation method to assist malware analysts in classifying malware variants. Our proposed method extract API call information of malware families by dynamic analysis. Then the multiple sequence alignment technique was applied to the extracted API call information. A signature of each family was extracted from the alignment results. By the similarity of the extracted signatures, our proposed method recommends three family candidates for unknown malware. We also measured the accuracy of our proposed method in an experiment using real malware samples.