• Archives of Plastic Surgery
• /
• 제34권1호
• /
• pp.134-136
• /
• 2007

Purpose: Erysipelas is a bacterial infection of the dermis and hypodermis, mostly of streptococcal origin, and erysipelas of upper extremity following breast cancer treatment has never been reported in the Korean literature. Methods: 39-year-old female presented to our hospital complaining of fever and painful swelling of her left upper extremity. She had a history of breast cancer and was treated with breast conserving surgery with axillary lymph node dissection, chemotherapy, and radiation. On physical examination, her left upper extremity showed vesicle, bullae, local heatness and erythema with well-defined margin. With these distinctive features of a skin lesion, we gave a diagnosis of erysipelas and started treatment with intravenous antibiotics. Results: Resolution of the signs and symptoms of erysipelas occurred after 7 days of treatment. Conclusion: The diagnosis of erysipelas with distinctive feature of skin lesion is essential and we emphasize that the prevention of any trauma are very important in these patients for prophylactic measures.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.213-231
• /
• 2014

Existing image search systems allow users to search images by keywords, or by example images through content-based image retrieval (CBIR). On the other hand, users might learn more relevant textual information about an image from its text captions or surrounding contexts within documents or Web pages. Without such contexts, it's difficult to extract semantic description directly from the image content. In this paper, we propose an annotation watermarking system for users to embed text descriptions, and retrieve more relevant textual information from similar images. First, tags associated with an image are converted by two-dimensional code and embedded into the image by discrete wavelet transform (DWT). Next, for images without annotations, similar images can be obtained by CBIR techniques and embedded annotations can be extracted. Specifically, we use global features such as color ratios and dominant sub-image colors for preliminary filtering. Then, local features such as Scale-Invariant Feature Transform (SIFT) descriptors are extracted for similarity matching. This design can achieve good effectiveness with reasonable processing time in practical systems. Our experimental results showed good accuracy in retrieving similar images and extracting relevant tags from similar images.

• 한국멀티미디어학회논문지
• /
• 제10권2호
• /
• pp.179-186
• /
• 2007

본 논문에서는 Zernike 모멘트를 이용한 새로운 얼굴 검출 기법을 제안한다. 입력 영상을 가변 크기의 영역으로 탐색하면서 Zernike 모멘트를 계산하여 신경망에 의해 얼굴과 비얼굴 영역으로 분류하여 얼굴을 검출한다. 직교 모멘트의 재구성 능력으로 인해, 분류기의 입력 특정은 화소의 수에 비해 감소될 수 있다. 또한, Zernike 모멘트의 크기는 회전에 불변한 특정을 가지므로, 회전된 얼굴 영역을 검출할 수 있다. Yale 데이터베이스의 영상에 대해 적용한 결과, 회전되지 않은 영상에서는 밝기값 정보를 사용하는 기법보다 약간 낮은 성능을 보였지만, 회전된 영상에 대해서는 월등히 높은 성능을 보였다. 국부 조명에 대한 추가적인 보상과 특징이 사용된다면, 강건한 얼굴 인식을 위한 전처리 과정의 핵심 기술로 사용할 수 있을 것이다.

• 한국ITS학회 논문지
• /
• 제11권4호
• /
• pp.131-143
• /
• 2012

본 논문은 지역적 특징을 빠르게 추출할 수 있는 SURF(Speed Up Robust Features) 알고리즘을 이용해 안경과 조명 등 자동차 환경에 적응적인 새로운 눈 상태 검출방법을 제안하였다. 또한, 베이지안 추론을 이용하여 각 운전자에 대해 세 가지 고유의 눈 상태 템플릿을 실시간적으로 생성함으로써 눈 상태 검출 성능을 향상시켰다. 주 야간, 안경 착용 시, 미착용 시 등 여러 환경에 대한 성능 실험 결과 주 야간 환경에서 각각 평균 98.1%와 96.0%의 검출률을, 공개된 ZJU데이터베이스에 대한 실험 결과 평균 97.8%의 검출률을 보임으로써 제안된 방법의 우수성을 보였다.

• 한국정보통신학회논문지
• /
• 제11권5호
• /
• pp.997-1003
• /
• 2007

이 논문에서는 LCD에 사용되는 편광필름 영상에서 결함을 검출하는 방법을 제안하였다. 제안한 방법은 결함의 지엽적인 특징을 이용하는 것이 아니라 특이값 분해를 이용하여 영상의 전역적인 정보를 반영하는 방법이다. 편광필름 영상을 특이값 분해하고 특이값 중에서 첫 번째 특이값만을 사용하여 영상을 재구성하면 재구성한 영상에서 정상 부분의 화소값과 결함 부분의 화소값들은 서로 다른 특성을 나타낸다. 입력 영상과 재구성한 영상의 화소값 비를 구하고 확률론적 방법을 사용하여 결함을 검출하였다. 제안한 방법을 이용하여 여러 가지 결함을 갖는 편광필름 영상에서 결함을 검출한 결과 검출력이 매우 우수한 것으로 나타났다.

• Bulletin of the Korean Chemical Society
• /
• 제19권1호
• /
• pp.79-82
• /
• 1998

Novel coordination polymers of general form $[Co(NCS)_2(Py_2L)_2]_n\; (Py_2L=trans-1,2-bis(4-pyridyl)ethylene$ (bpee), 1; 1,2-bis(4-pyridyl)ethane (bpea), 2) have been synthesized by slow diffusion of aqueous solution of $Co(NCS)_2$ with ethanolic solution of appropriate spacer ligand, $Py_2L$, in a mole ratio of 1 : 2. X-ray analyses on both 1 and 2 have provided similar unit and infinite structures with space group Ibam. The local geometry around the cobalt(Ⅱ) atoms is an octahedral arrangement with two NCS groups in trans position (N-Co-N, 180.0° (1); 180.0°(2)) and four pyridine units in propeller fashion. Each spacer ligand connects two cobalt(Ⅱ) ions defining the edges of a $[Co(II)]_4$ rhombus. The most fascinating feature is the occurrence of perpendicular interwoven of independent square grid sheets: this is, one molecular network is perpendicularly interpenetrated through the centers of the $[Co(II)]_4$ rhombuses of another independent network with all of the cobalt(Ⅱ) atoms in a coplanar sheet. The physicochemical properties of the present unique structures were studied.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.690-706
• /
• 2021

Classification is a substantial operation in data mining, and each element is distributed taking into account its feature values in the corresponding class. Metaheuristics have been widely used in attempts to solve satellite image classification problems. This article proposes a hybrid approach, the flower pigeons-inspired optimization algorithm (FPIO), and the local search method of the flower pollination algorithm is integrated into the pigeon-inspired algorithm. The efficiency and power of the proposed FPIO approach are displayed with a series of images, supported by computational results that demonstrate the cogency of the proposed classification method on satellite imagery. For this work, the Davies-Bouldin Index is used as an objective function. FPIO is applied to different types of images (synthetic, Alsat-2B, and Sentinel-2). Moreover, a comparative experiment between FPIO and the genetic algorithm genetic algorithm is conducted. Experimental results showed that GA outperformed FPIO in matters of time computing. However, FPIO provided better quality results with less confusion. The overall experimental results demonstrate that the proposed approach is an efficient method for satellite imagery classification.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.818-833
• /
• 2021

To address the problems of low precision rate, insufficient feature extraction, and poor contextual ability in existing text sentiment analysis methods, a mixed model account of a CNN-BiLSTM-TE (convolutional neural network, bidirectional long short-term memory, and topic extraction) model was proposed. First, Chinese text data was converted into vectors through the method of transfer learning by Word2Vec. Second, local features were extracted by the CNN model. Then, contextual information was extracted by the BiLSTM neural network and the emotional tendency was obtained using softmax. Finally, topics were extracted by the term frequency-inverse document frequency and K-means. Compared with the CNN, BiLSTM, and gate recurrent unit (GRU) models, the CNN-BiLSTM-TE model's F1-score was higher than other models by 0.0147, 0.006, and 0.0052, respectively. Then compared with CNN-LSTM, LSTM-CNN, and BiLSTM-CNN models, the F1-score was higher by 0.0071, 0.0038, and 0.0049, respectively. Experimental results showed that the CNN-BiLSTM-TE model can effectively improve various indicators in application. Lastly, performed scalability verification through a takeaway dataset, which has great value in practical applications.

• 한국컴퓨터정보학회논문지
• /
• 제24권3호
• /
• pp.77-86
• /
• 2019

The advent of Internet of Things (IoT) makes common nowadays computing environments involving programming not a single computer but several heterogeneous distributed computers together. Developing programs separately, one for each computer, increases programmer burden and testing all the programs become more complex. To address the challenge, this paper proposes an RPC-based unified programming language, UniPy, for development of MGC (eMbedded, Gateway, and Cloud) applications in IoT systems configured with popular computers such as Arduino, Raspberry Pi, and Web-based DB server. UniPy offers programmers a view of classes as locations and a very simple form of remote procedure call mechanism. Our UniPy compiler automatically splits a UniPy program into small pieces of the program at different locations supporting the necessary RPC mechanism. An advantage of UniPy programs is to permit programmers to write local codes the same as for a single computer requiring no extra knowledge due to having unified programming models, which is very different from the existing research works such as Fabryq and Ravel. Also, the structure of UniPy programs allows programmers to test them by directly executing them before splitting, which is a feature that has never been emphasized yet.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2129-2147
• /
• 2019

This paper introduces an adaptive face recognition method based on a Novel Incremental Kernel Nonparametric Discriminant Analysis (IKNDA) that is able to learn through time. More precisely, the IKNDA has the advantage of incrementally reducing data dimension, in a discriminative manner, as new samples are added asynchronously. Thus, it handles dynamic and large data in a better way. In order to perform face recognition effectively, we combine the Gabor features and the ordinal measures to extract the facial features that are coded across local parts, as visual primitives. The variegated ordinal measures are extraught from Gabor filtering responses. Then, the histogram of these primitives, across a variety of facial zones, is intermingled to procure a feature vector. This latter's dimension is slimmed down using PCA. Finally, the latter is treated as a facial vector input for the advanced IKNDA. A comparative evaluation of the IKNDA is performed for face recognition, besides, for other classification endeavors, in a decontextualized evaluation schemes. In such a scheme, we compare the IKNDA model to some relevant state-of-the-art incremental and batch discriminant models. Experimental results show that the IKNDA outperforms these discriminant models and is better tool to improve face recognition performance.