블록매칭을 이용한 이미지 모자익

이지근,정성태 원광대학교 공업기술개발연구소 2001 工業技術開發硏究誌 Vol.21 No.-

This paper presents a new image mosaic method which generates a panorama image from a video sequence recorded by a general video camera. Our method uses block matching technique to find the corresponding points between two successive images. In this paper, we propose a direction based 3-step search method. It places more search points in the direction of the motion vector in previous frame. Also, it places more search points in the initial step than K-step algorithm. But the iteration step is fixed to 3 while it is more than 3 in K-step algorithm. 8y using less iteration step, the total search points can be less than that of K-step search. Experiential results show that the proposed method is 10 times faster than the full-search method while the panorama images are almost same. Also, the proposed method produces more correct panorama image than the K-step based method while the CPU times are almost same.

4밸브 디젤기관의 흡기포트 편심과 두 흡기포트 사이의 격막이 실린더 내 선회 특성에 미치는 영향에 관한 연구

이지근,강신재,노병준,Lee, Ji-Geun,Gang, Sin-Jae,No, Byeong-Jun 대한기계학회 1997 大韓機械學會論文集B Vol.21 No.7

The effects of intake port eccentricity and a partition between the two intake ports on the incylinder swirl characteristics in a 4 valve diesel engine having the two intake ports, one is a helical intake port and the other is a tangential intake port, were investigated by using the impulse swirl meter(ISM) in a steady flow test rig. Mean flow coefficient ( $C_{f(mean)}$, swirl ratio ( $R_{s}$) and the mass flowrate through the two intake ports with and without intake port partition were measured. The results showed that the characteristics of in-cylinder swirl ratio formed by a 4-valve cylinder head were largely affected by valve eccentricity ratio ( $N_{y}$) and the existence of an intake port partition between the two intake ports. Mean flow coefficient ( $C_{f(mean)}$) increases and swirl ratio ( $R_{s}$) decreases in case of being the partition between the two intake ports. And also the mass flowrate through the tangential intake port is 19.0% and 7.7% more than that of the helical intake port in case of the two intake ports with and without partition respectively.ively.

나선형 흡기포트의 선회유동 특성에 관한 실험적 연구

이지근,유경원,노병준,강신재,Lee, Ji-Geun,Yu, Gyeong-Won,No, Byeong-Jun,Gang, Sin-Jae 대한기계학회 1997 大韓機械學會論文集B Vol.21 No.6

This experimental study was mainly investigated on the swirl flow characteristics in the cylinder generated by a helical intake port. LDA system was used for the measurement of in-cylinder velocity fields. Tangential and axial velocity profiles, with varying valve lifts, valve eccentricity ratios and axial distance, were measured. When the intake valve was set in the cylinder center, we could find that in-cylinder swirl flow fields were composed of a forced vortex motion and a free vortex motion in the vicinity of the cylinder center and the cylinder wall respectively. In case of valve eccentricity ratio, N$_{y}$ = 0.45, the vortex flow which rotates to the opposite direction of a main rotating flow in the cylinder was found. And the reverse flow toward the cylinder head surface was also found in axial velocity profile and it showed the tendency of the linear decrease in the region of 0.leq.Y/B.leq.1.2.2.

흡기포트 형상에 따른 선회비 분포특성에 관한 실험적 연구

이지근,주봉철,노병준,강신재,Lee, Ji-Geun,Ju, Bong-Cheol,No, Byeong-Jun,Gang, Sin-Jae 대한기계학회 1997 大韓機械學會論文集B Vol.21 No.6

The effect of helical intake port geometry on in-cylinder swirl flow characteristics was studied. Two helical intake ports were selected to change swirl ratio, mean flow coefficient with the variation of valve lifts, valve eccentricity ratios and axial distance. The measurements were made by using an impulse swirl meter. The port B modified to increase the swirl ratio( $R_{s}$) had the tendency of the increased non-dimensional rig swirl ( $N_{r}$) distribution in comparison with that of the port A. And the $N_{r}$ distribution was remarkably improved at low valve lifts. The modification of the geometry to increase the swirl ratio ( $R_{s}$) in helical intake port resulted in the decrease of the mean flow coefficient ( $C_{f(mean)}$) regardless of valve eccentricity ratio ( $N_{y}$). And also non-dimensional rig swirl ( $N_{r}$) in the high valve lift affected the calculation of swirl ratio considerably.onsiderably.

블록매칭을 이용한 비디오 시퀀스의 이미지 모자익

이지근,정성태 한국정보통신학회 2003 한국정보통신학회논문지 Vol.7 No.8

최근 들어 개인용 컴퓨터 성능의 향상과 인터넷 기술의 발전에 따라서 이미지 모자익은 가상 환경 구축, 관광, 광고, 의료 영상 등, 많은 응용 분야에서 관심을 모으고 있다. 이미지 모자익의 주된 문제점은 이미지들 간의 정확한 대응점을 찾는 것이다. 그러나 기존의 대부분의 모자익 기법들은 정확한 대응점을 찾기 위해서 복잡한 계산과 많은 처리 시간을 요구했으며 모자익 이미지 생성을 위해 사물이나 배경 주위를 360$^{\circ}$ 회전하면서 여려 차례 반복 촬영을 해야 하는 어려움을 가지고 있었다. 본 논문에서는 일반 비디오 카메라를 이용하여 단 한번의 촬영에 의해 생성된 연속 프레임을 사용하였고 프레임간의 모자익에 있어서 방향성을 고려한 새로운 방법의 3단계 블록매칭 방법을 적용함으로써 전체적인 모자익 처리 속도를 단축하는 방법을 제안한다. 실험 결과에 의하면 본 논문에서 제안된 방법이 기존의 블록매칭 방법인 전역 탐색이나 K­단계 탐색에 비하여 보다 효과적임을 알 수 있었다. In these days, image mosaic is getting interest in the field of advertisement, tourism, game, medical imaging, and so on with the development of internet technology and the performance of personal computers. The main problem of mage mosaic is searching corresponding points correctly in the overlapped area between images. However, previous methods requires a lot of CPU times and data processing for finding corresponding points. And they need repeated recording with a revolution of 360 degree around objects or background. This paper presents a new image mosaic method which generates a panorama image from a video sequence recorded by a general video camera. Our method finds the corresponding points between two successive images by using a new direction oriented 3­step block matching methods. Experimental results show that the suggested method is more efficient than the methods based on existing block matching algorithm, such as full search and K­step search algorithm.

SVM을 이용한 얼굴 검출 성능 향상에 대한 연구

이지근,정성태,Lee Chi-Ceun,Jung Sung-Tae 한국정보통신학회 2005 한국정보통신학회논문지 Vol.9 No.2

This paper proposes a method which improves the performance of face detection by using SVM(Support Vector Machine). first, it finds face region candidates by using AdaBoost based object detection method which selects a small number of critical features from a larger set. Next it classifies if the candidate is a face or non-face by using SVM(Support Vector Machine). Experimental results shows that the proposed method improve accuracy of face detection in comparison with existing method. 본 논문에서는 SVM(Support Vector Machine)을 이용하여 얼굴 검출 성능을 향상시키는 방법을 제안한다. 본 논문에서는 먼저 영상내의 거대한 특징 집합으로부터 중요한 작은 특징 집합을 선택하는 AdaBoost 기반 객체 검출 방법을 사용하여 얼굴 후보 영역을 검출한다. 그 다음에는 특징 벡터에 대해 SVM 기반 이진분류를 수행하여 후보 영역의 영상이 얼굴인지 아닌지를 판별한다 실험 결과 본문에서 제안한 방법은 기존의 방법에 비하여 얼굴 검출의 정확도를 향상시켰다.

Laparoscopic D1+ Lymph Node Dissection for Gastric Cancer in Jehovah’s Witness Patients: a 1:3 Matched Case Control Study

이지근,김용진,박수연 대한내시경복강경외과학회 2017 Journal of Minimally Invasive Surgery Vol.20 No.4

Purpose: Laparoscopic gastrectomy in early gastric cancer patients is accepted as standard, but it is sometimes challenging for patients who refuse blood transfusions such as Jehovah’s Witness (JW) patients, because of the risk of bleeding related to radical lymph node dissection. This study aimed to confirm the adequacy and safety of laparoscopic gastrectomy with D1+ lymphadenectomy in JW patients. Methods: From January 2009 to December 2015, 265 gastric cancer patients underwent laparoscopic gastrectomy in our institute. Among them, there were 25 JW, and they were statistically matched with 75 patients from the control groups depending on age, sex, and body mass index (BMI). In a retrospective review, patient laboratory values and their pathology results were analysed. Results: There was no significant difference when comparing the clinical characteristics of JW and control groups. There was no statistically significant difference in blood loss or operation time between the two groups. Mean blood loss was 202.4±172.6 ml in the JW group and 179.7±163.8 ml in the control group (p=0.556). The number of retrieved lymph nodes was 27.8±13.9 in the JW group and 29.3±12.1 in the control group (p=0.607). Haemoglobin and haematocrit were measured after surgery and there was no statistically significant difference between the two groups. Conclusion: Laparoscopic D1+ gastrectomy in a JW may be performed with an equivalent risk to the control group. Laparoscopic gastrectomy can be applied to Jehovah’s Witnesses if the specialied cancer center has sufficient experience in stomach cancer surgery, even if there is not enough experience in bloodless surgery.

DEVELOPMENT OF AN LIF IMAGE PROCESSING TECHNIQUE FOR MEASURING DROP SIZES IN A PRE-SWIRL SPRAY

이지근,Keiya Nishida 한국자동차공학회 2008 International journal of automotive technology Vol.9 No.4

Depth of field effects in laser sheet imaging were considered for droplet sizing of a pre-swirl spray. A pre-swirl spray is formed before the hollow-cone type main-swirl spray from a D.I. gasoline injector, and shows transient characteristics with high axial velocity. A microscopic imaging technique was applied to obtain high spatial resolution LIF tomograms of the pre-swirl spray. A 1 mm thick Nd:YAG laser sheet was used as a light source to make the LIF tomograms that were imaged using a high-resolution CCD camera. The droplet sizing of the pre-swirl spray was carried out using an image processing technique. In the image processing procedure, the laser sheet-straddling large-sized droplets were carefully taken into account to remove the errors caused by the depth of field effects from the limited thickness and the energy distribution of the laser sheet. The mean intensity of the individual droplets and the line profile of the LIF signal around the droplet edge were inspected to screen the laser sheet-straddling large-sized droplets. In order to consider the effects of the size-dependent LIF signal intensity, the size classified or ensemble-averaged mean intensity of the individual droplets was introduced. The mean droplet sizes such as AMD and SMD were calculated using only screened droplets, and they slightly increase before considering the depth of field effects.

밸브 타이밍 변화가 3기통 LPG 엔진의 성능과 Idle 특성에 미치는 영향에 관한 연구

이지근(J. K. Lee),이한풍(H. P. Lee),노병준(B. J. Rho) 한국자동차공학회 1997 한국 자동차공학회논문집 Vol.5 No.3

확률분포 통합 형태를 이용한 음성과 제스처의 멀티모달 융합

이지근(Chi-Geun Lee),한문성(Mun-Sung Han),김진태(Jin-Tae Kim) 한국정보과학회 2008 한국정보과학회 학술발표논문집 Vol.35 No.2

최근 멀티모달 융합 인식은 유비쿼터스 연구 분야에서 큰 이슈로 대두되고 있다. 특히, 음성과 제스처는 인간과 기계간의 상호작용에 있어서 가장 중요한 모달리티로 떠오르고 있다. 비록 음성인식 기술이 많은 발전을 해왔지만 잡음이 있는 환경에서 음성인식률이 저하된다는 심각한 문제를 가지고 있다. 이와 같은 경우, 음성과 동시에 발생하는 제스처는 음성의 의미를 이해하는데 좋은 대안으로 사용할 수 있다. 본 논문에서는 음성과 제스처의 멀티모달 융합 인식을 위하여 두 모달리티의 이산적 확률밀도 분포를 통합하여 하나의 새로운 확률밀도 분포를 생성하고, 이를 이용하여 음성과 제스처를 융합 인식하는 새로운 멀티모달 융합 방법을 제시한다. 실험은 실시간 환경에서 마이크로폰과 3축 가속도 센서를 이용하여 진행되었다. 본 논문에서 제시한 통합된 확률밀도 분포의 융합인식률이 기존의 단순한 확률밀도 덧셈에 의한 방법에 비하여 보다 더 효과적임을 보였다.