• 한국정보전자통신기술학회논문지
• /
• 제16권6호
• /
• pp.369-377
• /
• 2023

산업 제조 분야에서 품질 관리는 불량률을 최소화하는 핵심 요소로, 미흡한 관리는 추가적인 비용 발생과 생산 지연을 야기할 수 있다. 본 연구는 제조품의 텍스쳐 결함 감지의 중요성을 중심으로, 보다 정밀한 결함 감지 방법을 제시한다. DFR(Deep Feature Reconstruction) 모델은 특징맵의 조합 및 재구성을 통한 접근법을 채택하였지만, 그 방식에는 한계가 있었다. 이에 따라, 우리는 제한점을 극복하기 위해 통계적 방법론을 활용한 새로운 손실 함수와 스킵 연결구조를 통합하고 파라미터 튜닝을 진행하였다. 이 개선된 모델을 MVTec-AD 데이터세트의 텍스쳐 카테고리에 적용한 결과, 기존 방식보다 2.3% 높은 결함 분할 AUC를 기록하였고, 전체적인 결함 감지 성능도 향상되었다. 이 결과는 제안하는 방법이 특징맵 조합의 재건축을 통한 결함 탐지에 있어서 중요한 기여함을 입증한다.

• 제어로봇시스템학회논문지
• /
• 제18권5호
• /
• pp.453-464
• /
• 2012

This is a research of an adaptive longitudinal control system for situated cognition in wide range, traffic accidents reduction and safety driving environment by integrated system which graft a road infrastructure's information based on IT onto the intelligent vehicle combined automobile and IT technology. The road infrastructure installed by laser scanner in intersection, speed limited area and sharp curve area where is many risk of traffic accident. The road infra conducts objects recognition, segmentation, and tracking for determining dangerous situation and communicates real-time information by Ethernet with vehicle. Also, the data which transmitted from infrastructure supports safety driving by integrated with laser scanner's data on vehicle bumper.

• ETRI Journal
• /
• 제33권3호
• /
• pp.423-433
• /
• 2011

This paper introduces an adaptive and integrated utterance verification (UV) framework using minimum verification error (MVE) training as a new set of solutions suitable for real applications. UV is traditionally considered an add-on procedure to automatic speech recognition (ASR) and thus treated separately from the ASR system model design. This traditional two-stage approach often fails to cope with a wide range of variations, such as a new speaker or a new environment which is not matched with the original speaker population or the original acoustic environment that the ASR system is trained on. In this paper, we propose an integrated solution to enhance the overall UV system performance in such real applications. The integration is accomplished by adapting and merging the target model for UV with the acoustic model for ASR based on the common MVE principle at each iteration in the recognition stage. The proposed iterative procedure for UV model adaptation also involves revision of the data segmentation and the decoded hypotheses. Under this new framework, remarkable enhancement in not only recognition performance, but also verification performance has been obtained.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2003년도 춘계종합학술대회
• /
• pp.165-170
• /
• 2003

본 논문에서는 임의의 장면에도 얼굴 인식에 영향을 받지 않는 통합된 얼굴 인식 방법을 제안한다. 크기 정규화는 피부 색 분할과 log-poler 매핑 절차의 새로운 조합을 통하여 얻어지고, 주요 얼굴 구성 요소 분석은 자세 변화들을 처리하기 위하여 제안된 멀티 뷰 접근을 통해 이루어진다. 주어진 컬러 입력 이미지로부터 검출기는 얼굴을 원형 경계 안에 둘러싸고 코의 위치를 표시하며 다음 인식을 위해, 원형 경계 내에 배치하는 방사형 격자는 특징 벡터 코 중심에 두었다. 컬러로 분할된 영역의 폭으로서 얼굴의 크기를 평가하고, 추출된 특징 벡터는 평가된 크기에 의하여 정규화된 크기이다. 특징 벡터는 얼굴 인식을 위해 훈련된 신경망 분류자에게 입력된다. 시스템은 서로 다른 복합적인 배경에서 다양한 크기와 자세를 가진 20명의 얼굴 데이터 베이스를 사용하여 실험한 결과 얼굴 인식기의 수행능력은 매우 작은 크기의 얼굴 이미지 외에는 87%에서 92%의 평균 인식율을 얻을 수 있었다.

• 한국정보통신학회논문지
• /
• 제7권6호
• /
• pp.1312-1317
• /
• 2003

본 논문에서는 임의의 장면에도 얼굴 인식에 영향을 받지 않는 통합된 얼굴 인식 방법을 제안한다. 크기 정규화는 피부 색 분할과 log-polar 매핑 절차의 새로운 조합을 통하여 얻어지고, 주요 얼굴 구성 요소 분석은 자세 변화들을 처리하기 위하여 제안된 멀티 뷰 접근을 통해 이루어진다. 주어진 컬러 입력 이미지로부터 검출기는 얼굴을 원형 경계 안에 둘러싸고 코의 위치를 표시하며 다음 인식을 위해, 원형 경계 내에 배치하는 방사형 격자는 특징 벡터 코 중심에 두었다. 컬러로 분할된 영역의 폭으로서 얼굴의 크기를 평가하고, 추출된 특정 벡터는 평가된 크기에 의하여 정규화 된 크기이다. 특징 벡터는 얼굴 인식을 위해 훈련된 신경망 분류자에게 입력된다. 시스템은 서로 다른 복합적인 배경에서 다양한 크기와 자세를 가진 20 명의 얼굴 데이터 베이스를 사용하여 실험한 결과 얼굴 인식기의 수행능력은 매우 작은 크기의 얼굴 이미지 외에는 87%에서 92%의 평균 인식율을 얻을 수 있었다.

• Genomics & Informatics
• /
• 제10권3호
• /
• pp.194-199
• /
• 2012

In addition to single-nucleotide polymorphisms (SNP), copy number variation (CNV) is a major component of human genetic diversity. Among many whole-genome analysis platforms, SNP arrays have been commonly used for genomewide CNV discovery. Recently, a number of CNV defining algorithms from SNP genotyping data have been developed; however, due to the fundamental limitation of SNP genotyping data for the measurement of signal intensity, there are still concerns regarding the possibility of false discovery or low sensitivity for detecting CNVs. In this study, we aimed to verify the effect of combining multiple CNV calling algorithms and set up the most reliable pipeline for CNV calling with Affymetrix Genomewide SNP 5.0 data. For this purpose, we selected the 3 most commonly used algorithms for CNV segmentation from SNP genotyping data, PennCNV, QuantiSNP; and BirdSuite. After defining the CNV loci using the 3 different algorithms, we assessed how many of them overlapped with each other, and we also validated the CNVs by genomic quantitative PCR. Through this analysis, we proposed that for reliable CNV-based genomewide association study using SNP array data, CNV calls must be performed with at least 3 different algorithms and that the CNVs consistently called from more than 2 algorithms must be used for association analysis, because they are more reliable than the CNVs called from a single algorithm. Our result will be helpful to set up the CNV analysis protocols for Affymetrix Genomewide SNP 5.0 genotyping data.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.87-94
• /
• 2007

This paper introduces BEYTrans (Better Environment for Your TRANSlation), the first experimental environment for free online collaborative computer-aided translation. The requirements and functionalities related to individual translators and communities of translators are distinguished and described. These functionalities have been integrated in a Wiki-based complete environment, equipped with all currently possible asynchronous linguistic resources and translation aids. Functions provided by BEYTrans are also compared with existing CAT systems and ongoing experiments are discussed.

• 제어로봇시스템학회논문지
• /
• 제15권9호
• /
• pp.899-905
• /
• 2009

There are many different types of surface defects on semiconductor Integrated Chips (IC's) caused by various factors during manufacturing process, such as Scratch, Flash, Resin bleed, and Melting. These defects must be detected and classified by an inspection system for productivity improvement and effective process control. Among defects, in particular, Resin bleed and Melting are the most difficult ones to classify accurately. The brightness value and the shape of Resin bleed and Melting defects are so similar that normally it is difficult to classify the Resin bleed and Melting. In this paper, we propose a segmenting method and a set of features for detecting and classifying the Resin bleed and Melting defects.

• 재무관리연구
• /
• 제15권2호
• /
• pp.401-419
• /
• 1998

This paper examines the international arbitrage pricing model (IAPM) in regional equity markets setting. Factor analyses are used to estimate the international common risk factors. And the cross-sectional regression analyses are used to test the validity of regional IAPMs and Chow tests are used to evaluate the integration of regional equity markets. The results of factor analyses show that the number of common factors in each regional group is seven. The cross-sectional regression results lead us not to reject that the IAPMs are regionally valid but Chow test results lead us to reject that regional equity markets are integrated.

• 한국통신학회논문지
• /
• 제24권9B호
• /
• pp.1755-1766
• /
• 1999

A region-based video codec based on the H.263+ standard is examined and its associated novel rate control scheme is proposed in this work. The region-based coding scheme is a hybrid method that consists of the traditional block DCT coding and the object-based coding. Basically, we adopt H.263+ as the platform, and develop a fast macroblock-based segmentation method to implement the region-based video codec. The proposed rate control solution includes rate control in three levels: encoding frame selection, frame-layer rate control and macroblock-layer rate control. The goal is to enhance the visual quality of decoded frames at low bit rates. The efficiency of proposed rate control scheme applied to the region-based video codes is demonstrated via several typical test sequences.