http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
내시경적으로 제거한 식도의 과립 세포 종양 -증례보고 및 국내 문헌 고찰-
하종,이옥재,조활석,정태식,윤지향,이은정,민현주,김태효,정운태,조중현 대한소화기내시경학회 2003 Clinical Endoscopy Vol.26 No.2
Granular cell tumor is a benign tumor, commonly found in the skin, tongue, and breast but rarely in the esophagus. A 44-year-old man was referred from the private clinic because of an esophageal lesion found on endoscopy. Esophagoscopy revealed a white-yellowish polypoid lesion covered with normal looking mucosa in the upper esophagus. It was movable within the wall by pushing with forceps. Endoscopic polypectomy after ligation with elastic "O" band was performed without complication. Histologic diagnosis of granular cell tumor was made. It was stained strongly positive for S-100 protein. Another 20 cases of esophageal granular cell tumors reported in Korean literature were reviewed. (Korean J Gastrointest Endosc 2003;26:84-89) 과립세포종은 양성 종양으로 피부, 구강, 유방 등에서는 흔하지만, 식도에서는 드물게 발생한다. 저자들은 식후 상복부 불편감으로 위내시경 검사를 받은 후 식도의 점막하종양을 발견하고 내원한 44세 남자에서, ‘O’형 밴드 결찰술을 이용한 용종절제술을 시행하고 조직학적으로 과립세포종으로 확진하였기에 국내의 문헌고찰을 중심으로 보고한다.
합성 이미지를 이용한 Mask R-CNN 기반 한국 번호판 검출
하종은 제어·로봇·시스템학회 2020 제어·로봇·시스템학회 논문지 Vol.26 No.9
License plate detection on an image is the first necessary step for the automatic recognition of license plate. In this paper, we adopt Mask R-CNN [11] to detect a license plate on an image. It requires many training images to cope with over-fitting that occurs when training samples are smaller than numbers of parameters. In general, more than 200K images are required for the stable training, but it requires large amount of time and cost. In this paper, we present a method that uses already available open dataset. We use two open dataset of CCPD [8] and BDD [18]. CCDP dataset provides locations of four corner points on an image. But, they contain license plate of China. First, Korean license plate image is made by referencing the design rule. Then, Korea license plate image is projected onto the corresponding positions of CCPD image. Four corresponding points between Korea license plate and CCPD images is used in the computation of perspective transform. Two different types of training images from CCPD and BDD dataset are used in the training of Mask R-CNN, and they are applied to image that contains real Korea license plate. Training using composite images from CCPD shows better performance than that of BDD on the real Korea license plate image. Experimental results show the feasibility of presented approach. .