• 한국콘텐츠학회논문지
• /
• 제9권4호
• /
• pp.1-11
• /
• 2009

최근 인터넷에 유통되는 유해영상이 급증하면서 이들을 자동으로 차단하는 컴퓨터비전 기술의 연구가 활발히 이루어지고 있다. 본 논문에서는 피부색상을 이용한 유해영상 분류도구를 연구 및 개발한다. 제안하는 분류도구는 2단계로 구성되며, 1단계에서는 피부색 분류기를 이용하여 입력영상에서 피부색 영역을 검출하고, 2단계에서는 영역특징 분류기를 이용하여 앞서 검출된 피부색 영역의 비율과 위치 특징을 무해 또는 유해로 분류한다. 피부색 분류기는 히스토그램 모델에 기반하여 무해영상과 유해영상의 RGB 값으로 학습되며, 영역특징 분류기는 SVM(Support Vector Machine)에 기반하여 영상의 29개 지역의 피부색 비율로 학습된다. 실험결과 제안하는 분류기는 92.80%의 검출율(Detection Rate)과 6.73%의 양성오류율(False Positive Rate)을 나타내었다.

• 식품보건융합연구
• /
• 제4권1호
• /
• pp.23-31
• /
• 2018

The main issue of CT is radiation dose reduction to patient. The purpose of this study was to estimate the image quality and dose by iterative reconstruction (IR) for adults and pediatrics. Adult and pediatric images of phantom were obtained with 120 and 140 kV, respectively, in accordance with radiation dose in terms of volume CT dose index ($CTDI_{vol}$): 10, 15, 20, 25, 30, 35 mGy. Then, the adult and the pediatric images are reconstructed by filtered-backprojection (FBP) and iterative reconstruction (IR). The images were analyzed by signal-to-noise ratio (SNR). SNR is improved when IR and 140 kV are applied to acquire adult and pediatric images. In the adult abdomen, according to diagnostic reference level, the SNR values of bone were increased about 27.84 % and 27.77 % at 120 kV and 140 kV, and the tissue's SNR values of the IR were increased about 29.84 % and 33.46 % 120 and 140 kV, respectively. Dose is reduced to 40% in adults abdomen images when using IR reconstruction. In pediatric images, the bone's SNR were also increased about 17.70% and 18.17 % at 120 kV and 140 kV. The tissue's SNR were increased about 26.73 % and 26.15 % at 120 kV and 140 kV. Radiation dose is reduced from 30% to 50% for bone and tissue images. In the case of examinations for adult and pediatric CT, IR technique reduces radiation dose to patient, and it could be applied to adult and pediatric imaging.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권5호
• /
• pp.910-924
• /
• 2010

As Internet usage has increased, the risk of adolescents being exposed to adult content and harmful information on the Internet has also risen. To help prevent adolescents accessing this content, a novel detection method for adult images is proposed. The proposed method involves three steps. First, the Image Of Interest (IOI) is extracted from the image background. Second, the IOI is distinguished from the segmented image using a novel weighting mask, and it is determined to be acceptable or unacceptable. Finally, the features (color and texture) of the IOI or original image are compared to a critical value; if they exceed that value then the image is deemed to be an adult image. A Receiver Operating Characteristic (ROC) curve analysis was performed to define this optimal critical value. And, the textural features are identified using a gray level co-occurrence matrix. The proposed method increased the precision level of detection by applying a novel weighting mask and a receiver operating characteristic curve. To demonstrate the effectiveness of the proposed method, 2850 adult and non-adult images were used for experimentation.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2006년도 하계종합학술대회
• /
• pp.795-796
• /
• 2006

Recently, blocking harmful contents such as adult images has been widely researched. However, most of adult image blocking methods use flush color model without shape information. In this paper, we present a new adult image blocking methods based on shape and color information. In the first step, the shape is considered. In the second step, adult images are detected using skin color model. Considering both shape and color, the detection rate can be increased. We evaluate adult image detection performance using sample images.

• 아동학회지
• /
• 제29권4호
• /
• pp.15-26
• /
• 2008

This study analyzed the portrayal of adult characters in 176 picture books published in Korea by variables of character's external condition(sex, name, age and occupation), type(3-dimensional or flat), conflicts, and image. Standards for analysis of the picture books were devised by the researcher. Results showed that (1) adult male characters appeared much more frequently than female; they appeared most often without names and in order of older, middle aged, young adult. They appeared most often without occupations. (2) 3-dimensional characters appeared much more than flat ones. (3) Adult conflict situations were rare and were mostly interpersonal. They often resolved their conflicts by themselves. (4) The 20 kinds of images of the adult characters were mostly humorous, warm-hearted and attentive.

• Journal of Korean Neurosurgical Society
• /
• 제54권4호
• /
• pp.302-308
• /
• 2013

Objective : MR perfusion and single photon emission computerized tomography (SPECT) are well known imaging studies to evaluate hemodynamic change between prior to and following superficial temporal artery (STA)-middle cerebral artery (MCA) anastomosis in moyamoya disease. But their side effects and invasiveness make discomfort to patients. We evaluated the ivy sign on MR fluid attenuated inversion recovery (FLAIR) images in adult patients with moyamoya disease and compared it with result of SPECT and MR perfusion images. Methods : We enrolled twelve patients (thirteen cases) who were diagnosed with moyamoya disease and underwent STA-MCA anastomosis at our medical institution during a period ranging from September of 2010 to December of 2012. The presence of the ivy sign on MR FLAIR images was classified as Negative (0), Minimal (1), and Positive (2). Regions were classified into four territories: the anterior cerebral artery (ACA), the anterior MCA, the posterior MCA and the posterior cerebral artery. Results : Ivy signs on preoperative and postoperative MR FLAIR were improved (8 and 4 in the ACA regions, 13 and 4 in the anterior MCA regions and 19 and 9 in the posterior MCA regions). Like this result, the cerebrovascular reserve (CVR) on SPECT was significantly increased in the sum of CVR in same regions after STA-MCA anastomosis. Conclusion : After STA-MCA anastomosis, ivy signs were decreased in the cerebral hemisphere. As compared with conventional diagnostic modalities such as SPECT and MR perfusion images, the ivy sign on MR FLAIR is considered as a useful indicator in detecting brain hemodynamic changes between preoperatively and postoperatively in adult moyamoya patients.

• Investigative Magnetic Resonance Imaging
• /
• 제10권2호
• /
• pp.117-120
• /
• 2006

위축뇌탈출증(atrectic cephalocele)은 중앙의 두피하부에 있는 피부로 덮힌 병변으로서 수막과 아교세포나 중추신경계 조직의 잔유물들을 포함한다. 수직동이 없거나 잔유물로 남아있는 경우 낫형동(falcin sinus)이 다시 관류하게 되어 정맥의 배출이 가능하게 된다. 위축된 뇌탈출증 또는 지속적인 낫형동은 소아에서 주로 기술되어 왔으며, 성인에서는 매우 드문 병변이다. 저자들은 성인에서 자연퇴화된 위축뇌탈출증이 지속적인 낫형동을 동반한 매우 드문증례를 보고하고자 하며 MR영상과 MR정맥조영술은 정확한 해부학적 묘사와 진단에 유용하였다.

• 한국식생활문화학회지
• /
• 제25권6호
• /
• pp.719-724
• /
• 2010

The purpose of this study was to survey public preferences for dining space image styles depending on the types of passage rites in Korea and to determine potential differences in public preferences for dining space image styles depending on the types of passage rites in terms of various general characteristics such as gender, age, family type, and preference for the image and color styles of the dining space. As a result, this study determined the following: According to a public preference survey of dining space image styles depending on the type of passage rites, our respondents showed the highest preference for casual images (27.1%) at a party for a 100-day-old baby. Additionally, our respondents showed the highest preference for casual images (27.4%) when celebrating a baby's first birthday but showed the highest preference for romantic images (35.8%) when celebrating a baby girl's first birthday. Our respondents showed the highest preference for casual images (21.4%) for graduation ceremonies. Our respondents showed the highest preference for classic images (21.7%) at coming-of-age ceremonies for new adult men, but also showed highest preference for elegant images (26.2%) at coming-of-age ceremonies for new adult women. Moreover, the respondents showed highest preference for classic images (41.0%) at traditional wedding ceremonies but elegant images (24.1%) at modern wedding ceremonies. In contrast, the respondents showed highest preference for classic images (31.3%) for a 60th birthday party. The highest preference for classic images (28.9%) was found for a diamond wedding ceremony. Respondents showed highest preference for classic images (30.4%) for a funeral ceremony Finally, our respondents showed highest preference for classic images (32.5%) at memorial services (religious ceremonies).

• 한국컴퓨터정보학회논문지
• /
• 제14권5호
• /
• pp.45-54
• /
• 2009

본 논문에서는 평균 명암 필터와 개선된 2D 허프 변환을 이용하여 영상에서 가슴 영역을 검출함으로써 음란영상을 탐지하는 새로운 방법을 제안한다. 제안된 유해물 영상 검출 방법은 크게 학습 단계, 인식 단계, 검증 단계의 3가지 주요 단계로 구성된다. 학습 단계에서는 가슴의 유두 부분 영상의 학습을 통하여 인식 단계에서 사용할 유두 평균 명암 필터를 생성한다. 인식 단계에서는 입력 영상을 받아들여 에지를 추출하고, 에지의 밀도를 이용해 연결성분을 추출한 후. 추출된 연결성분의 가로와 세로외 길이 비율을 고려하여 유두 후보영역을 결정한다. 그리고 학습된 유두 평균 명암 필터와 입력 영상의 유두 후보영역 사이의 유사도를 측정하여 가장 유사도가 높은 영역을 최종적인 유두후보영역으로 결정하며, 개선된 2D 허프 변환을 이용하여 영상에서 가슴 라인을 검출한다. 검증 단계에서는 인식 단계에서 획득한 유두 후보영역과 가슴 라인의 위치를 고려하여 가슴 영역을 판단함으로써 유해물 영상의 최종 유무를 결정한다. 실험 결과에서는 다양한 영상을 이용한 실험을 통해 제안한 방법이 가슴 영역을 효과적으로 인식할 수 있음을 보여 주었으며, 결과적으로 제안된 방법이 음란 영상의 검출에 유용하게 활용될 수 있음을 확인할 수 있었다.

• 한국산학기술학회논문지
• /
• 제14권11호
• /
• pp.5834-5840
• /
• 2013

최근 들어, 초고속의 유무선 인터넷과 스마트 기기가 널리 보급됨에 따라 사진이나 동영상 형태의 유해 영상들이 급속히 보급되고 있다. 본 논문에서는 입력되는 영상에서 음란성을 대표하는 여성의 유두 영역을 자동으로 추출하여 유해 영상을 보다 효과적으로 탐지하는 새로운 방법을 제안한다. 제안된 알고리즘은 먼저 입력된 영상의 RGB 색상공간을 $YC_bC_r$ 공간으로 변환하여 사람의 피부색상 영역을 검출한다. 그리고 본 논문에서 새롭게 정의한 유두 맵을 적용하여 검출된 피부 영역으로부터 유두의 후보 영역들을 추출한다. 그런 다음, 기하학적인 특징을 사용하여 유두의 후보영역 중에서 실제 유두 영역만을 강건하게 필터링하고, 여성의 유두 영역을 포함하고 있는 영상을 유해한 영상이라고 판단한다. 성능을 비교 평가하는 실험결과에서는 제안된 색상과 기하학적인 특징 기반의 알고리즘이 유해 영상을 기존의 방법에 비해 보다 정확하게(4.1% 향상) 탐지한다는 것을 실험을 통해 보여준다.