방향성분 특징과 Fisher Measure를 이용한 간판영상 한글인식

임준식,김수형,이귀상,양형정,이명은,Lim, Jun-Sik,Kim, Soo-Hyung,Lee, Guee-Sang,Yang, Hyung-Jung,Lee, Myung-Eun 한국정보처리학회 2009 정보처리학회논문지B Vol.16 No.3

In this paper, we propose a Korean character recognition method from outboard signboard images. We have chosen 808 classes of Korean characters by an analysis of frequencies of appearance in a dictionary of signboard names. The proposed method mainly consists of three steps: feature extraction, rough classification, and coarse classification. The first step is to extract a nonlinear directional segments feature, which is immune to the distortion of character shapes. The second step computes an ordered set of 10 recognition candidates using a minimum distance classifier. The last step reorders the recognition candidates using a Fisher discriminant measure. As experimental results, the recognition accuracy is 80.45% for the first choice, and 93.51% for the top five choices. 본 논문은 모바일 폰 기반의 간판 영상내 한글 문자인식에 관한 연구로써 인식 대상은 간판영상에서 추출된 상호명으로 하였고 인식대상 문자 수는 상호명 빈도수 기반 808자로 한정하였다. 인식과정은 특징 추출, 대분류, 상세 분류로 구성되고 특징 추출과정에서는 문자영상의 크기, 잡음 및 왜곡에 강건한 비선형 방향성분 특징을 이용하였고 대분류 과정에서는 추출된 특징과 인식 대상문자에 대하여 최소거리 분류를 수행하고 10순위까지의 후보 문자를 추출하였다. 상세 분류 과정에서는 Fisher discriminant measure 이용하여 대분류에서 발생 할 수 있는 오인 식 결과를 보완하였다. 실험결과 1순위 인식률은 80.45%이고 5순위까지의 누적 인식률은 93.51%를 보였다.

공공부문의 CRM 성과에 영향을 미치는 요인 분석

임준식,김용수,Im, Jun-Sik,Kim, Yong-Soo 대한경영정보학회 2007 경영과 정보연구 Vol.21 No.-

government is rising interest about CRM gradually. At this of time presenting visible effect, this study grasped success factors through the concept arrangement and the existing literature about CRM. The capacity of CRM and the result of CRM (interest of local department which is a variable, a specialty manpower, business cooperation between department, evaluation and compensation, system integration level that is special variable, possibility of system extension, ease of system use) analyzed to local government employee how affects through actual proof analysis.

가중 퍼지 소속함수 기반 신경망을 이용한 Wisconsin Breast Cancer 예측 퍼지규칙의 추출

임준식 한국정보처리학회 2004 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.11 No.6

This paper presents fuzzy rules to predict diagnosis of Wisconsin breast cancer using neural network with weighted fuzzy membership functions (NNWFM). NNWFM is capable of self-adapting weighted membership functions to enhance accuracy in prediction from the given clinical training data.set of small, medium, and large weighted triangular membership functions in a hyperbox are used for representingset of featured input. The membership functions are randomly distributed and weighted initially, and then their positions and weights are adjusted during learning. After learning, prediction rules are extracted directly from the enhanced bounded sums ofset of weighted fuzzy membership functions. Two number of prediction rules extracted from NNWFM outperforms to the current published results in number of rules and accuracy with 99.41%. 본 논문은 가중 퍼지소속함수 기반 신경망(Neural Network with Weighted Fuzzy Membership Functions, NNWFM)을 이용하여 Wisconsin breast cancer의 예측을 수행하는 퍼지규칙을 추출하고 있다. NNWFM는 자기적응적(self adaptive)가중 퍼지소속함수를 가지고 주어진 입력 데이터로부터 학습하여 퍼지규칙을 생성하고 이를 기반으로 예측을 수행한다. 신경망 구조의 중간 부분인 하이퍼박스(hyperbox)들은개의 대, 중, 소의 가중 퍼지소속함수 집합으로 구성되며, 학습 후 각 집합은 퍼지집합의 bounded sum을 사용하여 다시 하나의 가중 퍼지소속함수로 합성된다.개의 특징입력(feature input)은 학습된 모든 하이퍼박스에 연결되어 예측 작업을 수행한다. NNWFM으로 추출된 2개의 퍼지규칙은 99.41%의 예측 인식율을 가지며 이는 퍼지규칙의 수와 인식율에 있어 현재 발표된 논문의 결과보다 우수함을 보여준다.

웹학습 사이트 평가모델의 성능평가

임준식,김용수 한국지능시스템학회 2007 한국지능시스템학회 학술발표 논문집 Vol.17 No.2

본 연구는 인터넷 학습사이트 평가모델을 개발하여 인터넷 학습사이트들이 학생들에게 필요한 양질의 정보를 제공할 수 있도록 하고자 한다. 학습자들이 효과적으로 학습을 하기 위해서는 인터넷 학습사이트 환경이 어떠해야 하는지에 대한 정보를 파악하여 더 나은 인터넷 학습사이트 환경에 대한 정보 제공 및 개선사항을 제시하고자 한다.

Finding Fuzzy Rules for IRIS by Neural Network with Weighted Fuzzy Membership Function

임준식 한국지능시스템학회 2004 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.4 No.2

Fuzzy neural networks have been successfully applied to analyze/generate predictive rules for medical or diagnostic data. However, most approaches proposed so far have not considered the weights for the membership functions much. This paper presents a neural network with weighted fuzzy membership functions. In our approach, the membership functions can capture the concentrated and essential information that affects the classification of the input patterns. To verify the performance of the proposed model, well-known Iris data set is performed. According to the results, the weighted membership functions enhance the prediction accuracy. The architecture of the proposed neural network with weighted fuzzy membership functions and the details of experimental results for the data set is discussed in this paper.

외이도에 발생한 이차성 피부 B 세포 림프종 1예

임준식,석상혁,김석,김보영 대한이비인후과학회 부산,울산,경남 지부회 2015 임상이비인후과 Vol.26 No.1

Lymphoma is a neoplastic proliferation of the lymphoreticular system and originate most commonly within a lymph node or lymphoid tissue. But extra-nodal involvement occurs about 25-30% in non-Hodgkin’s lymphoma (NHL) and 1% in Hodgkin’s lymphoma (HL). Cutaneous lymphoma has been reported in 4% of malignant lymphoma in South Korea is presented as primary or secondary lymphoma. Especially, cutaneous lymphoma of the external auditory canal is extremely rare, and has been reported 8 cases in the literature worldwide. We report a rare case of secondary cutaneous diffuse large B cell lymphoma of the external auditory meatus which has not been reported in South Korea.

철도차량 구동계 상태기반유지보수(CBM) 시스탬용 무선센서 통합모듈 개발

임준식,임종순,이동수,이인규,김규완,오진홍,양영모 한국철도학회 2022 한국철도학회 학술발표대회논문집 Vol.2022 No.4

보류관장을 시행한 마비성 장폐색환자 12례에 대한 임상적 고찰

임준식,문병순,Lim, Joon-Seek,Moon, Byung-Soon 대한한방내과학회 1999 大韓韓方內科學會誌 Vol.20 No.1

A clinial observation was done on 12 cases of paralytic ileus patients, treated by Bo-Ryu Enema(保留灌腸), who were hospitalized from May 1, 1995 to October 31, 1996 at the Department of Oriented Internal Medicine II, Oriental Medicine Hospital. Taejon University. The results were as follows; 1. The ratio between male and female was 1 : 1.4. The distribution of age. 70' years or over, 60', 50' years generation were revealed in turn. 2. In classiffication of human coporeal constitution, Soeumin(少陰人) were 9 cases(75.0%), Taeumin(太陰人) 2 cases (16.7%), Soyangin(少陽人) 1 case (8.3%). 3. In distribution of disease on admission, Stroke sequela was the most number with 7 cases(58.3%), Stroke 3 cases(25.3%). Hypertensive encephalopathy and Brain tumor were 1 case, each other. 4. The effect of treated by Bo-Ryu Enema was as follows: Each of Excellent(良好) and Good(好戰) were 6 cases(50%) but. Fair(別無好戰) and Poor(惡化) were no case.

가중 퍼지 소속함수 기반 신경망을 이용한 Wisconsin Breast Cancer 예측 퍼지규칙의 추출

임준식,Lim Joon Shik 한국정보처리학회 2004 정보처리학회논문지B Vol.11 No.6

본 논문은 가중 퍼지소속함수 기반 신경망(Neural Network with Weighted Fuzzy Membership Functions, NNWFM)을 이용하여 Wisconsin breast cancer의 예측을 수행하는 퍼지규칙을 추출하고 있다. NNWFM는 자기적응적(self adaptive)가중 퍼지소속함수를 가지고 주어진 입력 데이터로부터 학습하여 퍼지규칙을 생성하고 이론 기반으로 예측을 수행한다. 신경망 구조의 중간 부분인 하이퍼박스(hyperbox)들은 n개의 대, 중, 소의 가중 퍼지소속함수 집합으로 구성되며, 학습 후 각 집합은 퍼지집합의 bounded sum을 사용하여 다시 하나의 가중 퍼지소속함수로 합성된다. n개의 특징입력(feature input)은 학습된 모든 하이퍼박스에 연결되어 예측 작업을 수행한다. NNWFM으로 추출된 2개의 퍼지규칙은 99.41%의 예측 인식율을 가지며 이는 퍼지규칙의 수와 인식율에 있어 현재 발표된 논문의 결과보다 우수함을 보여준다. This paper presents fuzzy rules to predict diagnosis of Wisconsin breast cancer using neural network with weighted fuzzy membership functions (NNWFM). NNWFM is capable of self-adapting weighted membership functions to enhance accuracy in prediction from the given clinical training data. n set of small, medium, and large weighted triangular membership functions in a hyperbox are used for representing n set of featured input. The membership functions are randomly distributed and weighted initially, and then their positions and weights are adjusted during learning. After learning, prediction rules are extracted directly from the enhanced bounded sums of n set of weighted fuzzy membership functions. Two number of prediction rules extracted from NNWFM outperforms to the current published results in number of rules and accuracy with 99.41%.

Tracking of Multiple Vehicles Using Occlusion Segmentation Based on Spatio-Temporal Association

임준식,김수형,이귀상,양형정,나인섭 한국콘텐츠학회 2011 International Journal of Contents Vol.7 No.4

This paper proposes a segmentation method for overlapped vehicles based on analysis of the vehicle location and the spatiotemporal association information. This method can be used in an intelligent transport system. In the proposed method, occlusion is detected by analyzing the association information based on a vehicle’s location in continuous images, and occlusion segmentation is carried out by using the vehicle information prior to occlusion. In addition, the size variations of the vehicle to which association tracking is applied can be anticipated by learning the variations according to the overlapped vehicles’ movements. To assess the performance of the suggested method, image data collected from CCTVs recording traffic information is used, and average success rate of occlusion segmentation is 96.9%.