http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
직물 이미지 결함 탐지를 위한 딥러닝 기술 연구: 트랜스포머 기반 이미지 세그멘테이션 모델 실험
이현상,하성호,오세환 한국정보시스템학회 2023 정보시스템연구 Vol.32 No.4
Purpose In the textile industry, fabric defects significantly impact product quality and consumer satisfaction. This research seeks to enhance defect detection by developing a transformer-based deep learning image segmentation model for learning high-dimensional image features, overcoming the limitations of traditional image classification methods. Design/methodology/approach This study utilizes the ZJU-Leaper dataset to develop a model for detecting defects in fabrics. The ZJU-Leaper dataset includes defects such as presses, stains, warps, and scratches across various fabric patterns. The dataset was built using the defect labeling and image files from ZJU-Leaper, and experiments were conducted with deep learning image segmentation models including Deeplabv3, SegformerB0, SegformerB1, and Dinov2. Findings The experimental results of this study indicate that the SegformerB1 model achieved the highest performance with an mIOU of 83.61% and a Pixel F1 Score of 81.84%. The SegformerB1 model excelled in sensitivity for detecting fabric defect areas compared to other models. Detailed analysis of its inferences showed accurate predictions of diverse defects, such as stains and fine scratches, within intricated fabric designs.
Aseptic Endocarditis in Behçet’s Disease Presenting as Tricuspid Valve Stenosis
이현상,최원숙,김균희,강정규,김나영,박선희,박영희,남은정,양동헌,박헌식,조용근,이종명,채성철 대한심장학회 2011 Korean Circulation Journal Vol.41 No.7
Aseptic endocarditis is an uncommon complication of Behçet’s disease (BD). We describe a rare case of a 39-year-old female who had BD with aseptic endocarditis of the tricuspid valve (TV) presenting as tricuspid stenosis. She was diagnosed with BD four years ago. The mucocutaneous lesions were well-controlled with colchicine and short courses of corticosteroids. She remained free of signs and symptoms of BD for one year without any medication. Three months before admission, she gradually developed dyspnea on exertion and peripheral edema. Echocardiography revealed dilated right atrium and markedly thickened TV with severe stenosis. TV replacement was performed. Pathologic examination of the valve showed fibrinoid necrotic material and inflammatory cell infiltration. Blood cultures and cultures of the excised valve were negative for microorganisms.
특허데이터 기반 한국의 인공지능 경쟁력 분석: 특허지표 및 토픽모델링을 중심으로
이현상,오세환,차오신,신선영,김규리 한국지능정보사회진흥원 2022 정보화정책 Vol.29 No.4
With the development of artificial intelligence technology, competition for artificial intelligence technology patents around the world is intensifying. During the period 2000 ~ 2021, artificial intelligence technology patent applications at the US Patent and Trademark Office have been steadily increasing, and the growth rate has been steeper since the 2010s. As a result of analyzing Korea's artificial intelligence technology competitiveness through patent indices, it is evaluated that patent activity, impact, and marketability are superior in areas such as auditory intelligence and visual intelligence. However, compared to other countries, overall Korea's artificial intelligence technology patents are good in terms of activity and marketability, but somewhat inferior in technological impact. While noise canceling and voice recognition have recently decreased as topics for artificial intelligence, growth is expected in areas such as model learning optimization, smart sensors, and autonomous driving. In the case of Korea, efforts are required as there is a slight lack of patent applications in areas such asf raud detection/security and medical vision learning. 인공지능 기술의 발전과 더불어 세계 각국의 인공지능 기술 특허를 둘러싼 경쟁도 치열해지고 있다. 2000년~2021년 간 미국 특허청의 인공지능 기술 특허출원은 꾸준히 증가하고 있는 가운데 2010년대 들어 보다 가파른 성장세를 기록하고 있다. 특허지표를 통해 한국의 인공지능 기술경쟁력을 분석한 결과, 청각지능, 시각지능 등의 세부 분야에서 특허활동성, 영향력, 시장성 등이 우위에 있는 것으로 평가된다. 그러나, 주요국과 비교하여 한국의 인공지능 기술 특허는 양적 활동성, 시장성 확보 측면에서는 상대적으로 우수하나 기술 파급력은 다소 열위에 있는 것으로 나타난다. 최근 인공지능 기술 토픽으로 노이즈 캔슬링, 음성인식 등은 감소한 반면 모델학습 최적화, 스마트센서, 자율주행 등이 활성화되면서 성장이 기대되고 있다. 한국의 경우 사기탐지/보안, 의료 비전러닝 등의 분야에서 특허출원 성과가 다소 부족하여 분발이 요구된다.