• 융합신호처리학회논문지
• /
• 제2권2호
• /
• pp.13-19
• /
• 2001

기존의 프랙탈 영상복원은 모든 치역 블럭에 대해 반복축소변환을 수행하므로 복원시 많은 계산량이 요구되었다. 이를 개선하기 위해 각 치역 블럭마다 반복축소변환이 필요한 영역과 필요하지 않은 영역으로 구분하는 방법이 제시된 바 있다. 반복축소변환이 필요 없는 영역을 데이타 의존영역이라 하고, 데이타 의존영역이 확장될수록 반복축소변환 영역은 줄어든다. 그래서 본 논문에서는 정의역 블록의 탐색 영역을 치역과 비슷한 영역으로 제한하여, 정의역 블럭이 더 많이 중복되도록 부호화하여 데이타 의존영역을 최대화 즉, 반복축소변환 영역을 최소화한다. 반복축소변환 영역이 최소가 되는 정의역을 정의역 최소화 기법으로 정의한다. 그래서 정의역 최소화 기법을 이용하여 프랙탈 영상 복원시 화질에 거의 영향을 미치지 않고, 반복축소변환에 필요한 계산량을 감소시켜 고속 복원이 가능하다.

• Radiation Oncology Journal
• /
• 제35권3호
• /
• pp.274-280
• /
• 2017

Purpose: To see the gross tumor volume (GTV) dependency according to the phase selection and reconstruction methods, we measured and analyzed the changes of tumor volume and motion at each phase in 20 cases with lung cancer patients who underwent image-guided radiotherapy. Materials and Methods: We retrospectively analyzed four-dimensional computed tomography (4D-CT) images in 20 cases of 19 patients who underwent image-guided radiotherapy. The 4D-CT images were reconstructed by the maximum intensity projection (MIP) and the minimum intensity projection (Min-IP) method after sorting phase as 40%-60%, 30%-70%, and 0%-90%. We analyzed the relationship between the range of motion and the change of GTV according to the reconstruction method. Results: The motion ranges of GTVs are statistically significant only for the tumor motion in craniocaudal direction. The discrepancies of GTV volume and motion between MIP and Min-IP increased rapidly as the wider ranges of duty cycles are selected. Conclusion: As narrow as possible duty cycle such as 40%-60% and MIP reconstruction was suitable for lung cancer if the respiration was stable. Selecting the reconstruction methods and duty cycle is important for small size and for large motion range tumors.

• 한국측량학회지
• /
• 제17권2호
• /
• pp.167-176
• /
• 1999

각종 영상매체와 수치영상처리 기술이 발전함에 따라 수치영상을 이용한 대상물의 정량적 또는 정성적 분석에 관한 연구가 활발히 진행되고 있다. 그러나 높은 정확도의 영상해석에 있어 고해상도의 영상획득 시스템에 대한 의존도가 매우 높은 실정이며 이들은 고가의 장비라는 문제점을 안고 있다. 본 연구에서는 저가의 영상획득 시스템에 의해 획득한 다중영상을 강화ㆍ분석하여 최적의 강화조건을 도출하고 이를 적용하여 3차원 정확도 분석을 실시하였다. 저해상도의 원시영상과 최적의 조건에 의해 강화한 영상을 이용하여 평균 3차원 위치오차를 분석한 결과, 강화영상은 원시영상에 비해 10％정도 향상된 정확도를 보였다.

• 정보보호학회논문지
• /
• 제27권5호
• /
• pp.1059-1068
• /
• 2017

바이오해싱 기법은 생체 인식 템플릿으로부터 효과적으로 비트스트링 키를 생성할 수 있지만, 토큰 같은 사용자 입력 요소에 대한 의존도가 높아 토큰 도난 시 성능이 하락한다. 이러한 한계점을 개선하기 위하여, 본 논문에서는 얼굴 사진과 사용자 입력정보로부터 안전한 키를 생성하는 기법을 제시한다. 바이오해싱 기법과 GPT 기법을 사용하여, 인증 시사용자 입력정보에 대한 의존도를 조정하고, 충분한 길이의 안전한 키를 생성하도록 구성하였다. 제시한 기법을 입증하기 위하여 다양한 실험을 진행하고 결과를 보였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(5)
• /
• pp.51-54
• /
• 2001

For performing Intelligent Transport System, I will implement the vehicle recognition system used image as well as Real time transmission module with TCP/IP. Generally, there are two kinds for vehicle recognition technology. Between two methods, the image-based method has a high dependency on environmental condition. Therefore, in this thesis I will propose vehicle recognition algorithm based on image using improved Gradient Method. Also I propose server-client modeling with TCP/IP, for the purpose of real time transmission of processed data and images. So I made the vehicle recognition and real time transmission system with TCP/IP for verification of proposed algorithm.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권1호
• /
• pp.124-131
• /
• 2024

Breast cancer classification using ultrasound, while widely employed, faces challenges due to its relatively low predictive value arising from significant overlap in characteristics between benign and malignant lesions, as well as operator-dependency. To alleviate these challenges and reduce dependency on radiologist interpretation, the implementation of automatic breast cancer classification in ultrasound image can be helpful. To deal with this problem, we propose a semi-supervised deep learning framework for breast cancer classification. In the proposed method, we could achieve reasonable performance utilizing less than 50% of the training data for supervised learning in comparison to when we utilized a 100% labeled dataset for training. Though it requires more modification, this methodology may be able to alleviate the time-consuming annotation burden on radiologists by reducing the number of annotation, contributing to a more efficient and effective breast cancer detection process in ultrasound images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권9호
• /
• pp.4665-4683
• /
• 2019

Previous methods build image annotation model by leveraging three basic dependencies: relations between image and label (image/label), between images (image/image) and between labels (label/label). Even though plenty of researches show that multiple dependencies can work jointly to improve annotation performance, different dependencies actually do not "work jointly" in their diagram, whose performance is largely depending on the result predicted by image/label section. To address this problem, we propose the adaptive attention annotation model (AAAM) to associate these dependencies with the prediction path, which is composed of a series of labels (tags) in the order they are detected. In particular, we optimize the prediction path by detecting the relevant labels from the easy-to-detect to the hard-to-detect, which are found using Binary Cross-Entropy (BCE) and Triplet Margin (TM) losses, respectively. Besides, in order to capture the inforamtion of each label, instead of explicitly extracting regional featutres, we propose the self-attention machanism to implicitly enhance the relevant region and restrain those irrelevant. To validate the effective of the model, we conduct experiments on three well-known public datasets, COCO 2014, IAPR TC-12 and NUSWIDE, and achieve better performance than the state-of-the-art methods.

• 정보처리학회논문지B
• /
• 제8B권2호
• /
• pp.155-163
• /
• 2001

본 논문에서는 다중 모달리티 영상으로부터 의미 있는 정보를 제공하기 위하여 상호정보 최적화를 통한 영상정합 방법을 제안한다. 본 방법은 두 영상이 기하학적으로 정합되면 상호정보가 최대화된다는 가정 하에 두 영상에서 대응되는 위치의 명암도간 통계적 의존관계나 정보중복성을 계산하는 상호정보를 통하여 영상간 변형관계를 추정함으로써 영상을 정합한다. 실험결과로는 뇌 컴퓨터단층촬영영상의 상호정보를 최적화한 정합결과와 가우시안형 잡음 첨가에 따른 정합 비교 결과를 제시한다. 본 방법은 기존 정합방법에서 사용하는 영상분할이나 특징점 추출에 의한 정합이 아닌 영상 자체 정보를 사용함으로써 사용자와의 상호작용이 불필요하며 정합의 정확도를 향상시킬 수 있고 잡음에도 견고하다.

• Journal of the Optical Society of Korea
• /
• 제12권4호
• /
• pp.319-325
• /
• 2008

We propose a phase contrast filter using photopolymer, for the phase contrast projection display. The photopolymer has high photosensitivity such that its optically induced refractive index change has a linear dependency on the illuminating light intensity. We implemented a phase contrast projection display using photopolymer as a phase contrast filter. By controlling the refractive index change of the photopolymer, we successfully convert an input phase image into a high contrast intensity image. We also investigated the effect of the photopolymer illumination condition on the quality of the displayed intensity image. As a projector, we achieved 82% phase to intensity conversion efficiency, which implies that the proposed method can potentially have much higher light efficiency than conventional projection display.

• 대한간호학회지
• /
• 제35권7호
• /
• pp.1343-1352
• /
• 2005

Purpose: This study was designed to identify the degree of self-image and social support among Korean-Chinese adolescents and investigate the relationship between these variables. Method: A total of 621 Korean-Chinese adolescents in five middle schools in YanBian, China were recruited from March 1st to the 9th, 2005. Data was analysed using descriptive statistics, Pearson correlation coefficient, t-test, and ANOVA with the SPSS 11.5 program. Result: In Korean-Chinese adolescents, the total self-image score was statistically different for age, parents' education status, parents' job and living with parents. In the 12 subscales, scoresof emotional tone, impulse control, sexuality, social functioning, vocational attitudes and self-reliance had significant differences between groups regarding gender. The total self-image was in the average range. However, areas of mental health and family function were lower than average and the scale of idealism washigher than average. The adolescents perceived parent's support was higher then friend's support. There was a positive correlation between self-image and social support. Conclusion: The findings suggest there is a need to examine self-image and social support of Korean- Chinese adolescents according to their parents' marital status and a need to develop a program to help these broken family's adolescents.