• Tribology and Lubricants
• /
• 제15권2호
• /
• pp.206-211
• /
• 1999

Wear debris morphology is closely related to the wear mode and mechanism occured. Image recognition of wear debris is, therefore, a powerful tool in wear monitoring. But it has usually required expert's experience and the results could be too subjective. Development of automatic tools for wear debris recognition is needed to solve this problem. In this work, an algorithm for automatic wear debris recognition was suggested and implemented by PC base software. The presented method defined a characteristic 3-dimensional feature space where typical types of wear debris were separately located by the knowledge-based system and compared the similarity of object wear debris concerned. The 3-dimensional feature space was obtained from multiple feature vectors by using a multi-dimensional scaling technique. The results showed that the presented automatic wear debris recognition was satisfactory in many cases application.

• 한국콘텐츠학회논문지
• /
• 제6권11호
• /
• pp.243-248
• /
• 2006

간판인식은 관광지의 간판을 자동 인식하여 외국인 또는 외지인에게 편리한 관광 정보제공을 목적으로 연구되고 있다. 간판 인식 연구에서는 인식기의 훈련과 객관적인 성능 측정을 위해 간판영상 데이터베이스가 필수적이다. 이 논문은 전주 한옥마을을 대상으로 수집한 간판영상 데이터베이스에 대해 기술한다. 총 45개의 서로 다른 간판에 대해 각각 50개씩 영상을 다양한 조건에서 획득하였다. 이 데이터베이스는 패턴 인식 분야 연구를 위한 중요한 콘텐츠 이다.

• 말소리와 음성과학
• /
• 제6권2호
• /
• pp.29-34
• /
• 2014

In the Vector Taylor Series (VTS)-based noisy speech recognition methods, Hidden Markov Models (HMM) are usually trained with clean speech. However, better performance is expected by training the HMM with noisy speech. In a previous study, we could find that Minimum Mean Square Error (MMSE) estimation of the training noisy speech in the log-spectrum domain produce improved recognition results, but since the proposed algorithm was done in the log-spectrum domain, it could not be used for the HMM adaptation. In this paper, we modify the previous algorithm to derive a novel mathematical relation between test and training noisy speech in the cepstrum domain and the mean and covariance of the Multi-condition TRaining (MTR) trained noisy speech HMM are adapted. In the noisy speech recognition experiments on the Aurora 2 database, the proposed method produced 10.6% of relative improvement in Word Error Rates (WERs) over the MTR method while the previous MMSE estimation of the training noisy speech produced 4.3% of relative improvement, which shows the superiority of the proposed method.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(5)
• /
• pp.51-54
• /
• 2001

For performing Intelligent Transport System, I will implement the vehicle recognition system used image as well as Real time transmission module with TCP/IP. Generally, there are two kinds for vehicle recognition technology. Between two methods, the image-based method has a high dependency on environmental condition. Therefore, in this thesis I will propose vehicle recognition algorithm based on image using improved Gradient Method. Also I propose server-client modeling with TCP/IP, for the purpose of real time transmission of processed data and images. So I made the vehicle recognition and real time transmission system with TCP/IP for verification of proposed algorithm.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.785-788
• /
• 2000

The recognition system of a car plate is largely classified as the extraction and recognition of number plate. In this paper, we extract the number plate domain by using a thresholding method as a preprocess step. The computation of the density in a given mask provides a clue of a candidate domain whose density ratio corresponds to the properties of the number plate obtained in the best condition. The contour of the number plate for the recognition of the texts of number plate is extracted by operating Kohonen Algorithm in a localized region. The algorithm reduces noises around the contour. The recognition system with the density computation and Kohonen Algorithm shows a high performance in the real system in connection with a car number plate.

• 말소리와 음성과학
• /
• 제9권2호
• /
• pp.95-101
• /
• 2017

This paper proposes a new method to train Deep Neural Network (DNN)-based acoustic models for speech recognition of native and foreign speakers. The proposed method consists of determining multi-set state clusters with various acoustic properties, training a DNN-based acoustic model, and recognizing speech based on the model. In the proposed method, hidden nodes of DNN are shared, but output nodes are separated to accommodate different acoustic properties for native and foreign speech. In an English speech recognition task for speakers of Korean and English respectively, the proposed method is shown to slightly improve recognition accuracy compared to the conventional multi-condition training method.

• 한국음향학회지
• /
• 제20권2호
• /
• pp.21-26
• /
• 2001

본 논문에서는 잡음에 강인한 음성인식을 위해서 expectation-maximization (EM) 방식을 이용하여 잡음의 평균값을 추정하는 새로운 알고리듬을 제안하였다. 제안된 알고리듬에서는 온라인상의 인식용 음성이 직접 Bayesian 적응을 위해서 사용되며, 또한 훈련데이터를 이용하여 잡음의 평균값에 대한 사전 (prior) 분포를 알아낸 후 Bayesian 적응시에 이용한다. 잡음 음성의 모델링을 위해서는 PMC (parallel model combination) 방식을 이용하였고, 제안된 방식을 이용하여 자동차 잡음 환경 하에서 인식 실험을 수행한 결과, 기존의 PMC 방식에 비해서 향상된 인식성능을 보임을 알 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제13권2호
• /
• pp.225-236
• /
• 2010

본 논문은 카메라 영상 정보와 기울기 센서 정보를 통합한 바이모달 응급상황 인식방법을 제안한다. 제안된 방법은 어느 한 센서가 오작동 하거나 사용자가 착용형 기울기 센서를 착용하지 않거나, 영상 획득의 어려움이 있는 욕실과 같은 곳에 있는 경우에도 응급 상황을 감지하여 센서 간에 상호 협력과 보완을 함으로써 응급 상황을 인식할 수 있다. 본 논문에서는 HMM 학습 및 인식을 통해 걷는 동작, 바닥에 앉는 동작, 소파에 앉는 동작, 눕는 동작, 기절 동작을 판단할 수 있도록 하였다. 영상의 특징 벡터와 기울기 센서의 특징 벡터를 결합하여 학습하고 인식했을 때, 인식률의 향상을 가져올 수 있었다. 또한 다양한 조명의 변화에도 적응적 배경 모델을 통해 움직이는 객체를 강건하게 검출할 수 있어서 높은 인식률을 유지할 수 있었다.

• 전자공학회논문지
• /
• 제50권1호
• /
• pp.225-231
• /
• 2013

본 연구에서는 PCA알고리즘을 이용한 최적 pRBFNNs 기반 나이트비전 얼굴인식 시스템을 설계 하고자 한다. 조명이 없는 주위 상태 하에서 조도가 낮기 때문에 CCD 카메라를 이용하여 영상을 획득하는 것이 어렵다. 본 논문에서는 낮은 조도에 의해 왜곡된 이미지의 품질을 나이트 비전 카메라와 히스토그램 평활화를 사용하여 향상시킨다. 그리고 얼굴과 비얼굴 이미지 영역 사이에서 얼굴 이미지를 검출하기 위하여 Ada-Boost 알고리즘을 사용한다. 추출된 고차원 특징 데이터를 저차원의 특징 데이터로 변환하기 위하여 데이터 차원축소 기법인 주성분 분석법(Principal Components Analysis; PCA)을 사용한다. 또한 인식 모듈로서 pRBFNNs(Polynomial- based Radial Basis Function Neural Networks) 패턴분류기를 소개한다. 제안된 다항식 기반 RBFNNs은 조건부, 결론부, 추론부 세 가지의 기능적 모듈로 구성되어 있다. 조건부는 FCM (Fuzzy C-means) 클러스터링을 사용하여 입력공간을 분할하고, 결론부는 분할된 로컬 영역을 다항식 함수로 표현한다. 그리고 차분진화 (Differential Evolution; DE) 알고리즘을 사용하여 모델의 파라미터를 최적화 한다.

• 한국조리학회지
• /
• 제14권4호
• /
• pp.79-92
• /
• 2008

This study was to investigate consumers' recognition, preference, and use condition of processed food of Prunus mume(PFPM). As for the general recognition of Prunus mume, as the age is higher, and as the group of manufacture and intake has a higher level of academic attainments, the level of recognition is high. The group that manufactures and takes in PFPM at home showed high preference for Prunus mume processed food, and significant differences were shown among groups in this regard. The group of higher age and academic attainment level and those who manufactured Prunus mume at home showed high intake frequency of PFPM. 88.7% of the all respondents said that they had had Prunus mume products such as Prunus mume alcoholic beverage(76.3%), undiluted solution of Prunus mume(74.9%), Prunus mume tea(60.1%), and Prunus mume Jjangajji, or sliced vegetables preserved in soy sauce or hot pepper paste(46.3%). The rates of intake experience on another PFPM were relatively very low, and PFPM consumers in Daegu and Gyeongbuk areas were very limited. As for the prospect of Prunus mume processed food consumption, 48.8% and 46.7% of the respondents expected that it would remain in the current condition and would increase respectively. Moreover, 62.8% of the respondents said that they would purchase new PFPM satisfying such requirements above, which suggests that producing new PFPM is very positive.