http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
현영길,김종찬,김정우,도양회,김수중 한국통신학회 1999 韓國通信學會論文誌 Vol.24 No.7
다중 물체의 왜곡불변 인식을 위하여 수정합성형태소를 이용한 HMT를 제안하였다. HMT에서 중요한 문제 중의 하나는 오인식을 줄이고 다양한 모양의 왜곡된 물체를 검출하기 위하여 필요한 최적의 형태소를 결정하는 것이다. 제안된 형태소 합성방법은 이런 문제를 해결하는데 적절하다. 한 방법은 집합이론만을 이용하여 참영상의 형태소를 다단계로 합성하는 것이고, 다른 한 방법은 집합이론과 SDF합성법을 이용하여 참영상과 거짓영상의 형태소를 다단계로 합성하는 것이다. 시뮬레이션을 통하여 제안된 방법이 동일 집단의 왜곡된 물체를 인식하고, 다른 집단의 유사한 물체를 구분하여 인식할 수 있음을 확인하였다. A hit-miss transform(HMT) using modified synthetic structuring elements(SEs) for distortion-invariant recognition of multiple objects is proposed. A fundamental problem in an HMT is the determination of the optimal SE needed to improve the false alarm rate, and detect distorted objects with various shapes. The proposed synthetic methods of SE provide good solutions against this problem. One is the multistage synthesis of each true class SE using only set theory, and the other is the multistage synthesis of each true class and false class SE using set theory and SDF(synthetic discriminant function) synthesis method. Simulation results show the proposed methods can be used for the recognition of distorted intraclass objects and the discrimination of similar interclass objects.
현영길,도양회 濟州大學校 産業技術硏究所 1998 산업기술연구소논문집 Vol.9 No.1
In this paper. we proposed a method to recognize a speed limit signboard for autonomous road vehicles( ARV's) using the synthetic HMT(hit-miss transform). When images are acquired constantly by a camera of a car while ARV drives. it is difficult to detect the signboard in an instant. So. we set a limited range of distance between the camera and the signboard to have time enough to detect the signboard. However, signboard images which are acquired at each location in the limited range have different shapes each other. So, the synthetic HMT is used to detect each different shaped signboard at one time. Using the synthetic HMT, first signboards are detected and secondly signboard images are extracted. Finally speed limit numer is recognized from the extracted signboard images using the synthetic HMT again. Simulation results shows that the proposed method can be used for detection of signboard and recognition of speed limit in the limited range with only one HMT operation.
현영길,윤종수,도양회 濟州大學校 産業技術硏究所 1999 산업기술연구소논문집 Vol.10 No.1
A classification algorithm of traffic signs using a MSHMT (modified synthetic hit-miss transform) is proposed for the autonomous road vehicles(ARV's). In the case of classification of traffic signs, there are many kinds of signs with intraclass distortions and interclass similarities. The MSHMT provides a good solution with the property of distortion invariant recognition of multiple objects in noisy and cluttered scene. The proposed algorithm of traffic sign classification consists of the phase of sign detection and the phase of symbol recognition. In the phase of sign detection. structuring elements(SEs) are synthesized using only set theory to adapt to simple variations. In the phase of symbol recognition, SEs are synthesized using set theory and SDFkynthetic discriminant function) synthesis method to adapt to complex variations. Based on extensive simulations, it has been shown that the proposed algorithm is efficient for the classification of traffic signs.
현영길,윤종수,도양회 濟州大學校工科大學産業技術硏究所 1999 尖端技術硏究所論文集 Vol.10 No.1
A classification algorithm of traffic signs using a MSHMT(modified synthetic hit-miss transform) is proposed for the autonomous road vehicles(ARV's). In the case of classification of traffic signs, there are many kinds of signs with intraclass distortions and interclass similarities. The MSHMT provides a good solution with the property of distortion invariant recognition of multiple objects in noisy and cluttered scene. The proposed algorithm of traffic sign classification consists of the phase of sign detection and the phase of symbol recognition. In the phase of sign detection, structuring elements(SEs) are synthesized using only set theory to adapt to simple variations. In the phase of symbol recognition, SEs are synthesized using set theory and SDF(synthetic discriminant function) synthesis method to adapt to complex variations. Based on extensive simulations, it has been shown that the proposed algorithm is efficient for the classification of traffic signs.
현영길,도양회 濟州大學校 工科大學 産業技術硏究所 1998 尖端技術硏究所論文集 Vol.9 No.1
In this paper, we proposed a method to recognize a speed limit signboard for autonomous road vehicles(ARV's) using the synthetic HMT(hit-miss transform). When images are acquired constantly by a camera of a car while ARV drives, it is difficult to detect the signboard in an instant. So, we set a limited range of distance between the camera and the signboard to have time enough to detect the signboard. However, signboard images which are acquired at each location in the limited range have different shapes each other. So, the synthetic HMT is used to detect each different shaped signboard at one time. Using the synthetic HMT, first signboards are detected and secondly signboard images are extracted. Finally speed limit numer is recognized from the extracted signboard images using the synthetic HMT again. Simulation results shows that the proposed method can be used for detection of signboard and recognition of speed limit in the limited range with only one HMT operation.