• Journal of Astronomy and Space Sciences
• /
• 제31권3호
• /
• pp.205-214
• /
• 2014

In this study, a star identification algorithm which utilizes pivot patterns instead of apparent magnitude information was developed. The new star identification algorithm consists of two steps of recognition process. In the first step, the brightest star in a sensor image is identified using the orientation of brightness between two stars as recognition information. In the second step, cell indexes are used as new recognition information to identify dimmer stars, which are derived from the brightest star already identified. If we use the cell index information, we can search over limited portion of the star catalogue database, which enables the faster identification of dimmer stars. The new pivot algorithm does not require calibrations on the apparent magnitude of a star but it shows robust characteristics on the errors of apparent magnitude compared to conventional pivot algorithms which require the apparent magnitude information.

• The Journal of the Acoustical Society of Korea
• /
• 제26권1E호
• /
• pp.21-26
• /
• 2007

In this paper, we propose a modified Viterbi algorithm to compensate for endpoint detection error during the decoding phase of an isolated word recognition task. Since the conventional Viterbi algorithm explores only the search space whose boundaries are fixed to the endpoints of the segmented utterance by the endpoint detector, the recognition performance is highly dependent on the accuracy level of endpoint detection. Inaccurately segmented word boundaries lead directly to recognition error. In order to relax the degradation of recognition accuracy due to endpoint detection error, we describe an unconstrained search of word boundaries and present an algorithm to explore the search space with efficiency. The proposed algorithm was evaluated by performing a variety of simulated endpoint detection error cases on an isolated word recognition task. The proposed algorithm reduced the Word Error Rate (WER) considerably, from 84.4% to 10.6%, while consuming only a little more computation power.

• The Journal of the Acoustical Society of Korea
• /
• 제15권4E호
• /
• pp.21-27
• /
• 1996

In this paper, we propose a discriminative training algorithm for the stochastic segment model (SSM) in continuous speech recognition. As the SSM is usually trained by maximum likelihood estimation (MLE), a discriminative training algorithm is required to improve the recognition performance. Since the SSM does not assume the conditional independence of observation sequence as is done in hidden Markov models (HMMs), the search space for decoding an unknown input utterance is increased considerably. To reduce the computational complexity and starch space amount in an iterative training algorithm for discriminative SSMs, a hybrid architecture of SSMs and HMMs is programming using HMMs. Given the segment boundaries, the parameters of the SSM are discriminatively trained by the minimum error classification criterion based on a generalized probabilistic descent (GPD) method. With the discriminative training of the SSM, the word error rate is reduced by 17% compared with the MLE-trained SSM in speaker-independent continuous speech recognition.

• 인터넷정보학회논문지
• /
• 제16권1호
• /
• pp.29-37
• /
• 2015

이 논문에서는 모바일 기기상에서 카메라기반 악보인식을 위한 오선 두께와 오선 간격을 추정하는 전처리 기술을 제안한다. 캡쳐된 영상은 조명이나, 흐려짐, 저해상도 등의 많은 왜곡으로 인해 인식에 어려움이 있다. 특히 복잡한 배경을 가지고 있는 악보 영상인식의 경우 더욱 그렇다. 악보 기호 인식에서 오선 두께와 오선 간격은 인식에 큰 영향을 끼친다. 이들 정보는 이진화에도 사용되는데, 복잡한 배경을 가지고 있는 경우 일반적인 이진 영상은 오선 두께와 간격을 추정하는데 만족스럽지 못하다. 따라서 우리는 에지영상에서 런-길이 엔코딩 기술을 이용해 오선 두께와 간격 추정하는 강건한 알고리즘을 제안한다. 제안된 방법은 2단계로 구성되어 있다. 첫 번째 단계는 소벨 연산자에 의해 영역별로 에지 영상을 기반으로 오선 두께와 간격을 추정한다. 각 에지 영상의 열은 런-길이 엔코딩 알고리즘에 의해 기술된다. 두 번째 단계는 안정한 경로 알고리즘을 이용한 오선 검출과 오선 위치를 추적하는 적응적 LTH알고리즘을 이용한 오선 제거이다. 실험결과 복잡한 영상의 경우에도 강건함과 높은 인식률을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권1호
• /
• pp.208-223
• /
• 2015

To solve the problem of face recognition with complex changes and further improve the efficiency, a new near-infrared face recognition algorithm which fuses E-GV-LBP and FKNN algorithm is proposed. Firstly, it transforms near infrared face image by Gabor wavelet. Then, it extracts LBP coding feature that contains space, scale and direction information. Finally, this paper introduces an improved FKNN algorithm which is based on spatial domain. The proposed approach has brought face recognition more quickly and accurately. The experiment results show that the new algorithm has improved the recognition accuracy and computing time under the near-infrared light and other complex changes. In addition, this method can be used for face recognition under visible light as well.

• 전자공학회논문지B
• /
• 제31B권7호
• /
• pp.108-118
• /
• 1994

By using a concept of interrelation vector between line segments a new algorithm for partial shape recognition of two-dimensional objects is introduced. The interrelation vector which is invariant under translation rotation and scaling of a pair of line segments is used as a feature information for polygonal shape recognition. Several useful properties of the interrelation vector are also derived in relation to efficient partial shape recognition. The proposed algorithm requires only small space of storage and is shown to be computationally simple and efficient.

• 한국CDE학회논문집
• /
• 제4권1호
• /
• pp.43-51
• /
• 1999

Producing the relevant information (features) from the CAD models of CAM, called feature recognition or extraction, is the essential stage for the integration of CAD and CAM. Most feature recognition methods, however, have problems in the recognition of intersecting features because they do not handle the intersection geometry properly. In this paper, we propose a machining feature recognition algorithm, which has a solid model consisting of orthogonal primitives as input. The algorithm calculates candidate features and constitutes the Intersection Geometry Matrix which is necessary to represent the spatial relation of candidate features. Finally, it recognizes machining features from the proposed candidate features dividing and growing systems using half space and Boolean operation. The algorithm has the following characteristics: Though the geometry of part is complex due to the intersections of design primitives, it can recognize the necessary machining features. In addition, it creates the Maximal Feature Volumes independent of the machining sequences at the feature recognition stage so that it can easily accommodate the change of decision criteria of machining orders.

• 한국음향학회지
• /
• 제20권7호
• /
• pp.55-62
• /
• 2001

음성인식의 고속화를 위한 저자들에 의한 기존의 연구에서는 탐색이 진행함에 따라 시간방향의 탐색공간 문턱치를 가변적으로 적용하여 인식률의 저하없이 인식속도를 개선시켰다. 이 방법은 탐색 공간을 효과적으로 줄일 수는 있었으나 문턱치를 결정하기 위해서 여러 번의 사전 실험을 수행하여야 하는 번거러움이 있었다. 이러한 문제점을 해결하기 위하여 본 논문에서는 이전 탐색구간에 대한 최대우도와 후보들의 우도를 이용하여 현재 탐색구간의 문턱치를 탐색이 진행하는 과정에서 자동적으로 구하는 적응 프루닝 문턱치 알고리즘을 제안하였다. 제안한 알고리즘의 유효성을 확인하기 위해 국내 행정단위 시 (도), 구 (군), 동 (읍, 면), 번지를 구성하는 단어로 구성된 주소 인식 시스템에 적용하여 기존의 방법과 제안한 방법을 비교 검토하였다. 인식실험 결과, 연결단어 인식률 96.0%, 단어 인식률이 98.7%인 경우를 기준으로 하였을 때 제안된 방법이 기존의 고정 프루닝과 가변 프루닝 문턱치에 비하여 인식률 저하없이 각각 14.4%와 9.14%의 탐색 공간을 상대적으로 줄일 수 있어 제안된 방법의 유효성을 확인할 수 있었다.

• 음성과학
• /
• 제11권4호
• /
• pp.75-88
• /
• 2004

In this paper, we propose a new approach to sequential linear regression adaptation of continuous density hidden Markov models (CDHMMs) based on transformation space model (TSM). The proposed TSM which characterizes the a priori knowledge of the training speakers associated with maximum likelihood linear regression (MLLR) matrix parameters is effectively described in terms of the latent variable models. The TSM provides various sources of information such as the correlation information, the prior distribution, and the prior knowledge of the regression parameters that are very useful for rapid adaptation. The quasi-Bayes (QB) estimation algorithm is formulated to incrementally update the hyperparameters of the TSM and regression matrices simultaneously. Experimental results showed that the proposed TSM approach is better than that of the conventional quasi-Bayes linear regression (QBLR) algorithm for a small amount of adaptation data.

• 정보처리학회논문지D
• /
• 제14D권7호
• /
• pp.809-818
• /
• 2007

본 논문에서는 컬러정보를 이용하여 교통표지판 영역을 추출하고, 추출된 이미지의 인식을 위해 오류 역전파 학습알고리즘을 적용한 교통표지판 인식시스템을 제안한다. 제안된 방법은 교통표지판의 컬러를 분석하여 영상에서 교통표지판의 후보영역을 추출한다. 후보영역을 추출하는 방법은 RGB 컬러 공간으로부터 YUV, YIQ, CMYK 컬러 공간이 가지는 특성을 이용한다. 형태처리는 교통표지판의 기하학적 특성을 이용하여 영역을 분할하고, 교통표지판 인식은 학습이 가능한 오류역전파 학습알고리즘을 이용하여 인식한다. 실험결과 제안된 시스템은 다양한 크기의 입력영상과 조명의 차이에 영향을 받지 않고 후보영역 추출과 인식에 우수한 성능이 입증되었다.