• 한국산학기술학회논문지
• /
• 제7권2호
• /
• pp.182-187
• /
• 2006

본 논문은 통계 기반 접근 방식인 HMM(Hidden Markov model)과 생물학의 개체명에 관한 온톨로지 정보를 이용한 생물학 문서에서의 개체명(named entity) 경계 인식 방법을 제안한다. 제안하는 방법은 31개의 자질 정보를 이용한 평탄화 기법을 사용하며 생물학 개체명의 계층 정보를 이용하여 HMM의 자료 부족 문제를 완화시킬 수 있도록 하였다. 개체명 경계 인식의 학습과 실험을 위하여 GENIA 코퍼스 ver 2.1을 사용하였으며 개체명 경계 인식 실험을 수행한 결과 모든 부류를 사용한 경우보다 정확도 및 실행 속도가 개선됨을 확인하였다.

• 한국지리정보학회지
• /
• 제11권3호
• /
• pp.136-150
• /
• 2008

항공사진이나 LiDAR 데이터를 이용하여 건물의 자동 추출에 있어서 많은 연구가 이루어졌지만, 3차원 위치정보와 영상의 형상정보라는 두 데이터의 장점을 융합하여 정확도를 향상시킬 수 있다. 이를 위하여 본 연구에서는 등고선 기반의 건물인식 알고리즘을 사용하여 LiDAR 데이터를 이용한 건물 인식 정확도를 향상시키고, 항공사진을 이용하여 건물 경계의 정교화도 추구하였다. 등고선기반 건물 인식 방법은 건물의 경계와 지붕구조물 정보를 생성할 수 있으며, 기존 TIN기반 인식 방법이나 NDSM기반 방법보다 우수한 건물 탐지 정확도를 보여주었다. 등고선으로 추정된 건물경계에 일정한 크기의 버퍼를 생성하여 항공사진의 경계영역을 한정시키고, double active contour를 사용하여 항공사진의 에지에 맞도록 건물경계를 정교화 하였다. 본 연구성과를 이용하여 향후 추출된 개체 경계의 일정 범위에서 최적의 정합을 수행하여 3차원 건물 경계를 생성할 수 있다.

• International Journal of Advanced Culture Technology
• /
• 제4권4호
• /
• pp.75-80
• /
• 2016

The process of extracting external boundary of an object is a very important process for recognizing an object in the image. The proposed extraction method consists of two processes: External Boundary Extraction and Thinning. In the first step, external boundary extraction process separates the region representing the object in the input image. Then, only the pixels adjacent to the background are selected among the pixels constituting the object to construct an outline of the object. The second step, thinning process, simplifies the outline of an object by eliminating unnecessary pixels by examining positions and interconnection relations between the pixels constituting the outline of the object obtained in the previous extraction process. As a result, the simplified external boundary of object results in a higher recognition rate in the next step, the object recognition process.

• 음성과학
• /
• 제10권1호
• /
• pp.27-39
• /
• 2003

This study attempts to verify the reliability of automatically generated segment labels as compared to those obtained by conventional labelling by hand. First of all, an autolabeller is constructed using the standard HMM speech recognition technique. For evaluation, we compare the automatically generated labels with manually annotated labels for the same speech data. The comparison is performed by calculating the temporal difference between an autolabel boundary and its corresponding hand label boundary. When the mismatched duration between two labels falls within 10 msec, we consider the autolabel as correct. The results suggest that overall 78% of autolabels are correctly obtained. It is found that the boundary of obstruents is better aligned than that of sonorants and vowels. In case of stop sound classes, strong stops in manner-of-articulation wise and velar stops in place-of-articulation wise show better performance in boundary alignment. The result suggests that more phone-specific consideration is necessary to improve autosegmentation performance.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.181-183
• /
• 2004

In this paper, We proposed an algorithm which extraction iris region from 2D image. Our method is composed of three parts : internal boundary defection and external boundary detection. Since eyelid and eyelash cover part of the boundary and the size of iris changes continuously, it is difficult to extract iris region accurately. For the interior and exterior boundary detection, we used partial differentiation of histogram. Performance of the proposed algorithm is tested and evaluated using 360 iris image samples.

• 한국멀티미디어학회논문지
• /
• 제14권4호
• /
• pp.504-516
• /
• 2011

In this paper, we will present a method to detect human hand and recognize hand gesture. For detecting the hand region, we use the feature of human skin color and hand feature (with boundary complexity) to detect the hand region from the input image; and use algorithm of optical flow to track the hand movement. Hand gesture recognition is composed of two parts: 1. Posture recognition and 2. Motion recognition, for describing the hand posture feature, we employ the Fourier descriptor method because it's rotation invariant. And we employ PCA method to extract the feature among gesture frames sequences. The HMM method will finally be used to recognize these feature to make a final decision of a hand gesture. Through the experiment, we can see that our proposed method can achieve 99% recognition rate at environment with simple background and no face region together, and reduce to 89.5% at the environment with complex background and with face region. These results can illustrate that the proposed algorithm can be applied as a production.

• 대한전자공학회논문지SP
• /
• 제43권2호
• /
• pp.65-72
• /
• 2006

교통신호등 검출과 인식 시스템은 운전자에게 경고와 보조시스템으로 필요한 장치이다. 본 논문에서는 칼라 비젼시스템을 이용한 주행중 실시간 교통신호등의 검출과 인식법에 대해 제안하고 있다. 제안하는 방법은 크게 네 가지로 구분된다 유사색 환경에서도 신호등 빛 검출이 용이하도록 HSI 색 공간에서 채도와 밝기값의 차를 이용하여 신호등의 빛을 검출하는 신호등 검출, 신호등 외곽검출과 검출된 신호 빛을 바탕으로 교통신호등 외곽 후보영역 설정과 세 검출 결과를 토대로 교통신호등을 인식하는 부분이다. 주행중 영상을 비디오 카메라로 녹화하여 제안하는 방법에 적용하여 결과를 제시하였다. 녹화시 카메라의 줌기능을 이용하여 줌에 의한 입력 영상변화시에도 신호등을 검출 및 인식한 결과를 제시하였다.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 2001년도 추계학술발표대회 논문집 제20권 2호
• /
• pp.117-120
• /
• 2001

Recognition rate of Korean digit is lower than that of other words because it is composed of similar phonemes. In this paper, a new method is proposed for the improvement of recognition rate by using the phoneme boundary information. In addition, the proposed method rarely increase cost because phoneme boundary is found by using simple method. We experimented with speech data of one man and then obtained results of enhanced speech recognition rate.

• International Journal of Advanced Culture Technology
• /
• 제7권3호
• /
• pp.134-142
• /
• 2019

As the 4th industry has been widely distributed, there is a need for a process of real-time image recognition in various fields such as identification of company employees, security maintenance, and development of military weapons. Therefore, in this paper, we will propose an algorithm that effectively recognizes a test object by comparing it with the DB model. The proposed object recognition system first expresses the outline of the test object as a set of vertices with the distances of predefined length or more. Then, the degree of matching of the structures of the two objects is calculated by examining the distances to the outline of the DB model from the vertices constituting the test object. Because the proposed recognition algorithm uses the outline of the object, the recognition process is easy to understand, simple to implement, and a satisfactory recognition result is obtained.

• 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.