• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권4호
• /
• pp.308-318
• /
• 2012

Captions include information which relates to the images. In order to obtain the information in the captions, text extraction methods from images have been developed. However, most existing methods can be applied to captions with a fixed height or stroke width using fixed pixel-size or block-size operators which are derived from morphological supposition. We propose an edge connected components based method that can extract Korean captions that are composed of various sizes and fonts. We analyze the properties of edge connected components embedding captions and build a decision tree which discriminates edge connected components which include captions from ones which do not. The images for the experiment are collected from broadcast programs such as documentaries and news programs which include captions with various heights and fonts. We evaluate our proposed method by comparing the performance of the latent caption area extraction. The experiment shows that the proposed method can efficiently extract various sizes of Korean captions.

• 전자공학회논문지B
• /
• 제28B권5호
• /
• pp.382-393
• /
• 1991

In this paper, we propose a method for recognizing printed Korean characters using the Preceding Layer Driven multi-layer perceptron. The new learning algorithm which assigns the weight values to an integer and makes use of the transfer function as the step function was presented to design the hardware. We obtained 522 Korean character-image as an experimental object through scanner with 600DPI resolution. The preprocessing for feature extraction of Korean character is the separation of individual character, noise elimination smoothing, thinnig, edge point extraction, branch point extraction, and stroke segmentation. The used feature data are the number of edge points and their shapes, the number of branch points, and the number of strokes with 8 directions.

• 한국정보통신학회논문지
• /
• 제18권3호
• /
• pp.687-696
• /
• 2014

본 논문은 사용자의 입력, 색상 및 깊이 정보를 이용한 의미론적 물체 분할 방법을 제안한다. 의미있는 영역을 깊이영상에서 유사한 깊이 정보와 사용자 스트로크 입력의 중심에 위치한다고 가정한다. 제안된 방법은 스트로크 입력을 이용하여 관심 영역을 설정하고, 색상과 깊이 정보를 이용하여 의미있는 영역을 검출한다. 구체적으로 제안방법은 관심영역에 대해 색상과 깊이 정보를 이용한 과분할 과정과 과분할 영역에 대해 깊이 정보를 이용한 의미론적 물체 추출과정으로 구성되어 있다. 과분할 과정에서 적응적 임계값 적용 및 형태학적 기울기에 대한 적응적인 가중치 적용을 통한 마커 추출 방법을 제안하였다. 의미론적 물체 추출과정에서는 관심영역의 가장자리 영역에서 내부 영역으로의 순서대로 전체 깊이의 평균과 차이를 이용하여 추출하고자 하는 물체 영역인지 아닌지를 결정하도록 하였다. 실험 결과에서 제안한 방법이 효과적으로 의미있는 물체 추출 결과를 얻을 수 있음을 보인다.

• 한국정보전자통신기술학회논문지
• /
• 제9권2호
• /
• pp.229-236
• /
• 2016

본 논문에서는 3차원 공간에서 손 위치를 추적하고 움직임 궤적을 분석하여 원거리에서 판서가 가능한 기술을 제안한다. 3차원 공간에서 손으로 입력하는 한글 음절은 글자 획과 이동 획이 구분되지 않아 음절의 종류를 구분하기 힘들다. 이에 본 논문에서는 한글 음절을 구성하는 획을 글자 획과 이동 획으로 구분한 후 이동 획은 제거하고 글자 획만을 출력하는 방법을 제안한다. 우선, 필기체 음절의 궤적에서 획의 끝 점을 검출하고, 검출한 끝 점 정보를 이용하여 입력 음절을 획 단위로 분리한다. 음절 집합으로부터 8가지의 획 패턴을 정의한 후 분리한 획에 대해서는 방향 코드를 기반으로 획 패턴을 분류한다. 그리고 이를 기반으로 최종적으로 획의 유형을 글자 획과 이동 획으로 분류한다. 분류된 획의 유형을 기반으로 입력된 음절에서 이동 획은 제거하고 글자 획만을 출력하여 가독성이 있는 음절 표시가 가능하도록 한다. 360개의 음절 집합에 대해 정확도를 측정하여 획의 패턴은 88.3%, 획의 유형 구분은 91.1%의 정확도를 얻었다.

• 대한한방내과학회지
• /
• 제42권3호
• /
• pp.323-339
• /
• 2021

Objectives: This study investigates the effect of electro-acupuncture on aphasia after stroke. Methods: A search of OASIS, NDSL, PubMed, Cochrane, and CNKI was executed between 4 January 2021 and 4 February 2021, with no limitation on publication year. Extraction and selection from the studies were made by 3 authors. The quality of the studies was evaluated using Cochrane's risk of bias (RoB) tool. Results: 10 studies met the selection criteria. As the treatment site for electro-acupuncture, GV20 (Baihui) was used the most. In all studies, the region located on the head was used for treatment without distinguishing between acupoints and areas of scalp acupuncture, and the stimulation was organized into 3 conditions: speed, intensity, and time. The outcome indicators used before and after treatment focused on the evaluation of language function and the degree of aphasia. The results showed that using electro-acupuncture with speech rehabilitation therapy for aphasia after stroke was more effective than using speech rehabilitation therapy alone. Conclusions: In this review, electro-acupuncture for aphasia after stroke was found to have a significant effect compared to the previous treatment alone. However, because of limitations, information was not reliable enough. Additional research is needed to produce more objective evidence.

• 웰빙융합연구
• /
• 제5권1호
• /
• pp.1-7
• /
• 2022

Purpose: This study aimed to investigate spatial and temporal features of motor control in an individual with hemiparesis during the curvilinear gait (CG) and proposed an exercise guideline. Research design, data and methodology: An individual aged 63 with hemiparesis by stroke disease was participated in the study. Autoencoder (AE) was used to extract four motor modules from eight muscle activities of the paretic leg during CG. After extraction, each module of four modules was operationally defined by numbering from M1 to M4 according to spatial and temporal features and compared with results reported in a previous study. Results: As a result, an individual with hemiparesis had motor module problems related to difficulty of weight acceptance (module 1), compensation for the weakness of ankle plantar flexor (module 2), a spastic synergistic pattern (module 3) and difficulty with transition from the swing to stance phase (module 4) in terms of spatial features. Also, a delayed activation timing of temporal motor module (module 2) related to the forward propulsion during CG was observed. Conclusions: Gait rehabilitation for the stroke will need to consider clinical significances in respect of the deterioration of motor module and provide the tailored approaches for each gait phase.

• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2006년도 학술대회 1부
• /
• pp.526-534
• /
• 2006

이 논문에서는 트루타입 폰트의 글자 외곽선 데이터를 이용하여 자동으로 한자의 획을 분리하고 획 순서를 정하는 방법을 제안한다. 트루타입 폰트에는 글자의 외곽선 정보가 벡터 형식으로 저장되어 있으며, 이러한 벡터들은 일정한 규칙으로 배열되어 있다. 이와 같은 벡터들의 배치를 이용하여 한자의 획이 될 수 있는 벡터들의 집합을 조합하여 독립적인 획을 분리해 내고, 글자를 획 별로 분리하여 본래 트루타입 폰트의 저장 형식과 동일한 파일 형식으로 저장한다. 또한 분리된 모든 획에 대하여, 획 이름을 정의하고, 정의된 획들 간의 위치와 상관관계를 이용하여, 획 사이의 우선순위를 결정하여 획 순서를 부여한다. 이 작업들은 사람의 작업 없이 순수하게 자동으로 이루어지므로, 시간과 노력을 최소화 할 수 있다. 게다가, 획 별로 분리되고 순서대로 정리된 한자들은 트루타입 폰트에 저장되어 있는 모양과 특성을 그대로 가지고 있으므로, 단순히 폰트 자체로써 사용할 수도 있을 뿐만 아니라, 한자 학습 컨텐츠로도 이용이 가능하며, 각종 애니메이션 효과 등 다양한 분야에서 융통성 있게 활용될 수 있다.

• Journal of Multimedia Information System
• /
• 제4권1호
• /
• pp.39-42
• /
• 2017

Communication between human and machine is having been researched from last few decades and still it's a challenging task because human behavior is unpredictable. When it comes on handwritten digits almost each human has their own writing style. Handwritten digit recognition plays an important role, especially in the courtesy amounts on bank checks, postal code on mail address etc. In our study, we proposed an efficient feature extraction system for recognizing single digit number drawn by mouse or by a finger on a screen. Our proposed method combines basic image processing and reading the strokes of a line drawn. It is very simple and easy to implement in various platform as compare to the system which required high system configuration. This system has been designed, implemented, and tested successfully.

• Journal of Korean Neurosurgical Society
• /
• 제46권3호
• /
• pp.226-231
• /
• 2009

Objective : We describe our clinical experiences and outcomes in patients who had thromboembolic complications occurring during endovascular treatment of intracerebral aneurysms with a review of the literature. The types of thromboembolic complications were divided and the treatment modalities for each type were described. Methods : Between August 2004 and March 2009 we performed endovascular embolization with Guglielmi detachable coils for 173 patients with 189 cerebral aneurysms, including ruptured and unruptured aneurysms at our hospital. Sixty-eight patients were males and 105 patients were females. The age of patients ranged from 22-82 years (average, 58.8 years). We retrospectively evaluated this group with regard to complication rates and outcomes. The types of thromboembolic complications were classified into the following three categories: mechanical obstruction, distal embolic stroke, and stent-induced complications, which corresponded to types I, II, and III, respectively. A comparison of the clinical results was made for each type of complication. Results : Only eight patients had a thromboembolic complication during or after a procedure (4.6%). Of the eight patients, two had a mechanical obstruction as the causative factor; the other three patients had distal embolic stroke as the causative factor. The remaining three patients had stent-induced complications. In cases of mechanical obstruction, recanalization occurred due to the use of intra-arterial thrombolytic agents in one of two patients. Nevertheless, a poor prognosis was seen. In the cases of stent-induced complications, in one of three patients in whom a thrombus developed following stent insertion, a middle cerebral artery territory infarct developed with a poor prognosis despite the use of wiring and an intra-arterial thrombolytic agent. In the cases of distal embolic stroke, all three patients achieved good results following the use of antiplatelet agents. Conclusion : Treatment for thromboemboic complications due to mechanical obstruction and stent-induced complications include antiplatelet and intra-arterial thrombolytic agents; however, this cannot guarantee a sufficient extent of effectiveness. Therefore, active treatments, such as balloon angioplasty, stent insertion, and clot extraction, are helpful.

• 대한전기학회논문지:전기기기및에너지변환시스템부문B
• /
• 제48권5호
• /
• pp.241-248
• /
• 1999

Recently, many linear motion generators and motors are rapidly finding applications that ranges from short stroke linear motion vibrators, such as dynamic cone type loudspeakers to stirling engine driven linear reciprocating alternators, compressors, textile machines etc. The stroke-length may go up to 2m, and the maximum speed is in the range of 5 to 10m/s with oscillating frequency as high as 15 kHz. Therefore, the linear oscillating actuators(LOAs) may be considered as variable speed drivers of precise controller with stoke-length and reversal periods during the reciprocating motion. In this paper, the design, fabrication, experiments, and extraction of control parameters of a moving coil type LOA for driving of linear reciprocating motion control systems, are treated. The actuator consists of the NdFeB permanent magnets with high specific energy as the stator produced magnetic field, a coil-wrapped nonmagnetic hollow rectangular bobbin structure, and an iron core as a pathway for magnetic flux. Actually, the design is accomplished by using FEM analysis for the basic configuration of a magnetic circuit, and characteristic equations for coil design. In order to apply as the drivers of a linear motion reciprocating control system, the control parameters and circuit parameters, such as input voltage-stoke, exciting frequency-stoke, coil inductance and so on, are extracted from the analysis and experiments on concerning a fabricating LOA.