• 정보처리학회논문지B
• /
• 제14B권3호
• /
• pp.231-240
• /
• 2007

이 논문은 정렬 기법을 이용한 미등록 대역어 추출 모델을 제안하고 그 추출 시스템을 구현한다. 제안된 미등록 대역어 추출 모델은 일종의 구절정렬 모델로서 경계모델과 언어모델 그리고 번역 모델로 구성된다. 제안된 추출 시스템은 병렬말뭉치 구축, 단어정렬, 미등록어 추출로 구성된다. 이 논문에서는 제안된 시스템을 평가하기 위해서 약 1,500여 개의 미등록어가 포함된 2,200문장의 평가말뭉치를 구축하여 다양한 실험을 수행하였다. 실험을 통해서 제안된 모델이 미등록 대역어 추출에 매우 유용함을 알 수 있었다. 앞으로 좀 더 객관적인 평가를 위해 대량의 평가말뭉치 구축이 선행되어야 하며 좀 더 양질의 병렬말뭉치의 구축이 필요할 것이다. 또한 미등록어 추출 모델을 개선하기 다양한 연구가 추진되어야 할 것이다.

• 한국항해학회지
• /
• 제22권4호
• /
• pp.37-44
• /
• 1998

This paper presents a procedure for automated extraction of ridge shadows in noisy gray images. This procedure mainly consists of 1) a deformable model which is designed basing upon the knowledge about the shape of shadows and is expected to be useful in extracting ridge shadows especially located in low signal to noise ratio background, and 2) the scale space scheme which is also useful even if there is less information about the size and the positions of ridge shadows in advance. This procedure is applied to artificial images and its performance is evaluated experimentally.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권6호
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• 전자공학회논문지S
• /
• 제34S권6호
• /
• pp.21-29
• /
• 1997

In this paper, we propose a new approach for recovering 3-D shape and extracting the reflectance properties of surface from intensity images. Photometric stereo method(PSM) is genrally based on the direct illumination. In this paper, the reflectance function is derived by interoduceing the indirect diffuse illumination in PSM and then applied to hybrid reflectance model which consists of two components; the lambertian and the specular reflectance. Under the hybrid reflectance model and the indirect diffuse illumination circumstance, the reflectance properties of sample surface can be extracting by normal sampler and then 3-D shape of an object can be recovered based on extracting reflectance properties. This method is rapid because of using the reference table and simplifies the restriction condition about the reflectance function existing in prior studies. Th erecovery efficiency in our method is better than that in prior studies. Also, this method is applied to various types of surfaces by defining general reflectance function.

• 한국정보통신학회논문지
• /
• 제4권1호
• /
• pp.123-130
• /
• 2000

본 논문은 고정된 카메라에서 얻어진 연속 영상으로부터 능동 윤곽선 모델을 이용하여 이동 물체의 윤곽선을 추출하는 방법을 제안한다. 주위 환경 변화에 강인한 처리를 위해 적응 배경 모델을 사용하였다. 물체 분할 모델은 얻어진 배경 영상과 현재 영상의 차영상으로부터 국부 영상의 임계값 이상의 화소를 찾아 연결한 영역을 분할하며, 형태학적 필터에 의하여 이동 물체의 경계 부분에서 발생하는 잡음을 제거하였다 분할된 이동 물체 윤곽선은 능동 윤곽선 모델을 이용하여 보다 정확한 이동 물체의 경계를 추출한다. 제안한 방법을 사용하여 도로 영상에서 실험한 결과를 보였다.

• 정보처리학회논문지B
• /
• 제14B권3호
• /
• pp.145-152
• /
• 2007

본 논문에서는 LCD 모니터, LCD TV, PDP TY, OLED TV 등과 같은 평판 디스플레이 장비를 위한 적응형 칼라 영상 향상 알고리즘에 대해서 제안한다. 제안한 알고리즘은 칼라 영상에서 콘트라스트와 채도를 함께 향상 시키는 방법이다. 콘트라스트 향상을 위해서 사용하는 적응형 선형 추정 CDF(Cumulative Density Function) 기법은 콘트라스트 향상 시 밝기에 따른 조정이 가능하여 원 영상의 왜곡을 막아준다. 적응형 채도 향상 알고리즘은 채도 향상의 문제점인 Contour Artifact와 Over-Saturation이 발생하지 않는 범위내에서 제도를 향상시킨다. 또한 원 영상의 색상 분포에 따른 선택적 채도 향상 방법을 사용하여 고품질의 영상을 얻을 수 있다. 제안된 알고리즘에 의한 처리 결과와 원 영상의 화질 평가를 위해서 시각적 검증과 히스토그램 편차를 도입하였다.

• 한국멀티미디어학회논문지
• /
• 제23권9호
• /
• pp.1155-1163
• /
• 2020

Deep learning approach is emerging as a new way to improve the accuracy of tree species identification using bark image. However, the approach has not been studied enough because it is confronted with the problem of acquiring a large volume of bark image dataset. This study solved this problem by utilizing a pretrained off-the-shelf DCNN model. It compares the discrimination power of bark features extracted by each DCNN model. Then it extracts the features by using a selected DCNN model and feeds them to a multi-layer perceptron (MLP). We found out that the ResNet50 model is effective in extracting bark features and the MLP could be trained well with the features reduced by the principal component analysis. The proposed approach gives accuracy of 99.1% and 98.4% for BarkTex and Trunk12 datasets respectively.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.508-514
• /
• 2007

In order to extract some important information of a person from text, an extracting model was proposed. The person's name is recognized based on the maximal entropy statistic model and the training corpus. The sentences surrounding the person's name are analyzed according to the conceptual knowledge base. The three main elements of events, domain, situation and background, are also extracted from the sentences to construct the structure of events about the person.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.1078-1083
• /
• 1992

Extracting the process planning information from the CAD data is the key issue in integrated CAD/CAM system. In this paper, we develop algorithms for extracting the shape and setup configuration for NC machining of prismatic parts. In determining the workpart shape, the minimum-enclosing condept is applied so that the material waste is minimized. To minimize the number of setups, feature based algorithm is developed considrint the part shape, tool shape, and tool approach direction. The validity and effectiveness of the developed algorithms were tested by computer simulations.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2002년도 춘계학술대회논문집
• /
• pp.39-52
• /
• 2002

Research Direction The significant research direction in mechanical fault diagnosis area: Theorles and approaches for fault feature extracting and fault classification. Identification Complicated fault generating mechanism and its model Intelligent fault diagnosis system (including the expert system and network based remote diagnosis system) One of the Key Points： Fault feature extracting techniques based on (modern) signal processing(omitted)