• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.341-345
• /
• 1998

본 논문은 웨이블렛 변환과 제안된 신경회로망을 이용한 홍채인식에 대한 연구이다. 인간의 생물학적 특징중에 최근 각광받는 특징인 홍채로 신원확인 시스템을 구현함을 목적으로 고신뢰도의 홍채인식 시스템을 개발중이다. 현재 개발되고 있는 신원확인을 위한 여러 가지 인식 시스템 중 홍채인식의 특성과 비교 우위적 장점을 소개하고, 경쟁학습 신경회로망에서의 효과적인 가중치 초기화 방법과 승자결정 방법에 관한 연구에 대한 실험결과를 소개한다.

• MALSORI
• /
• no.43
• /
• pp.127-136
• /
• 2002

The speaker adaptation technique is generally used to reduce the speaker difference in speech recognition. In this work, we focus on the features fitted to a linear regression-based speaker adaptation. These are obtained by feature transformation based on independent component analysis (ICA), and the transformation matrix is learned from a speaker independent training data. When the amount of data is small, however, it is necessary to adjust the ICA-based transformation matrix estimated from a new speaker utterance. To cope with this problem, we propose a smoothing method: through a linear interpolation between the speaker-independent (SI) feature transformation matrix and the speaker-dependent (SD) feature transformation matrix. We observed that the proposed technique is effective to adaptation performance.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2013.01a
• /
• pp.35-38
• /
• 2013

최근, 대용량 영상 데이터베이스가 축적되면서 영상 인식과 영상 검색 분야가 주목받고 있으며, 다양한 디바이스에 따라 생성되는 영상의 해상도가 상이하게 나타나고 있다. 본 논문에서는 내용-기반 영상 검색을 위한 새로운 칼라 기술자를 제안한다. 제안 알고리즘에서는 공간 칼라 정보에 대한 웨이블릿 변환과 채널 및 변환 서브밴드에 따른 가중치를 적용하여 칼라 특징 벡터를 추출한다. 시뮬레이션을 통하여 제안하는 알고리즘의 검색 성능을 평가하였으며, 유사한 특징 벡터 크기를 기준으로, 기존의 MPEG-7 등의 칼라 검색 기술자보다 다중-해상도의 영상 데이터베이스에서 향상된 검색율을 보임을 확인하였다. 본 논문에서 제시한 알고리즘은 단일 특성의 특징 벡터를 추출하는 검색 기술자로써, 다중 특징으로 결합하기 위한 기본 기술자로 활용될 수 있다.

• Journal of Broadcast Engineering
• /
• v.17 no.4
• /
• pp.634-639
• /
• 2012

In this paper, we propose nonlinear optimization method for feature matching from multiple view image. Typical solution of feature matching is by solving linear equation. However this solution has large error due to nonlinearity of image formation model. If typical nonlinear optimization method is used, complexity grows exponentially over the number of features. To make complexity lower, we use sparse Levenberg-Marquardt nonlinear optimization for matching of features over multiple view image.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.641-644
• /
• 2002

얼굴 특징점 추출은 현재 많은 연구가 활발히 진행되고 있는 분야로 보안, 인식 등 다양한 응용분야를 갖는다. 본 논문에서는 PC 카메라 및 주민등록증에 있는 사진을 스캔하여 얼굴 특징점을 정확하고 빠른 계산 시간안에 찾을 수 있는 새로운 방법을 제시한다. RGB 색공간을 YUV로 변환하여 Y성분을 히스토그램 균등화 시켜 휘도에 관계없이 얼굴 피부색을 추출한 후 YUV의 V성분을 변형한 V'성분을 이용하여 얼굴의 특징점을 찾는 방법이다. 실험결과 주민등록증 사진과 PC 카메라에서 입력 받은 얼굴 영상이 오류 없이 추출됨이 관찰되었다.

• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.126-131
• /
• 2002

The problem whether a given grammar G generates an LL language or not is investigated in respect of LL transformable grammars. The previous work involves a nondeterministic intricated parser construction for the characterization of LL transformable grammars. The method hence does not give the intuitive understanding of the essence of LL languages. This paper suggests a characterization of LL transformable grammars based on grammatical derivations instead of the complicated parser construction. The new characterization contributes to intuitive understanding of the essence of LL languages.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.65-74
• /
• 2012

In this paper, we explore the application of 2-D dual-tree discrete wavelet transform (DDWT), which is a directional and redundant transform, for image coding. DDWT introduces limited redundancy and allows the transform to provide approximate shift invariance and directionally selective filters while preserving the usual properties of perfect reconstruction and computational efficiency with good well-balanced frequency responses. Also, quincunx lattice yields a non separable 2D-wavelet transform, which is also symmetric in both horizontal and vertical direction. And non-separable wavelet transformation can generate sub-images of multiple degrees rotated versions. The proposed 2-D non-separable DDWT can provide efficient approximation for directional features of images schemes, such as edges and contours in images that are not aligned with the horizontal or vertical direction. Finally, non-separable image processing using DDWT services good performance.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.550-552
• /
• 2003

패턴인식에서 사용되는 모든 영상을 해석할 수 있는 시스템은 현재 어려운 문제이므로 먼저문제 영역을 해석하는 방법이 일반적이다. 이는 영상의 이해 및 특정 정보값을 사용하여 특징으로 사용하기 위하여 특징을 추출한다. 특징 추출시 정보의 손실 없이 데이터를 줄이는 작업이 연구되어오고 있지만 이는 사람의 주관적인 경험으로 알고리즘의 내부 파라미터를 결정하고 바꾸어야 하는 문제점을 가지고 있다. 본 논문에서는 웨이블릿 변환으로 얻어진 sub-band들을 특징으로 추출하고 결과를 통계적인 방법인 주성분분석을 이용하여 특징 차원을 감소시켜 인식의 정확도를 향상시키는 방법을 제안한다.

• Journal of KIISE
• /
• v.42 no.10
• /
• pp.1185-1194
• /
• 2015

A spherical panoramic image does not conform to the pin-hole camera model, and, hence, it is not possible to utilize previous techniques consisting of plane-to-plane transformation. In this paper, we propose a new method to estimate the planar geometric transformation between the planar image and a spherical panoramic image. Our proposed method estimates the transformation parameters for latitude, longitude, rotation and scaling factors when the matching pairs between a spherical panoramic image and a planar image are given. A planar image is projected into a spherical panoramic image through two steps of nonlinear coordinate transformations, which makes it difficult to compute the geometric transformation. The advantage of using our method is that we can uncover each of the implicit factors as well as the overall transformation. The experiment results show that our proposed method can achieve estimation errors of around 1% and is not affected by deformation factors, such as the latitude and rotation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.6C
• /
• pp.834-841
• /
• 2004

There can be lips transformed geometrically in the lip images according to the location or the pose of camera and speaker. This transformation of the lip images changes geometric information of original lip phases. Therefore, for enhancing global lip information by using partial information of lips to correct lip phases transformed geometrically, in this paper we propose a method that can geometrically correct lips. The method is composed of two steps - the feature-deciding step and the correcting step. In the former, it is for us to extract key points and features of source image according to the its lip model and to create that of target image according to the its lip model. In the latter, we decide mapping relation after partition a source and target image based on information extracted in the previous step into each 4 regions. and then, after mapping, we unite corrected sub-images to a result image. As experiment image, we use fames that contain pronunciation on short vowels of the Korean language and use lip symmetry for evaluating the proposed algorithm. In experiment result, the correcting rate of the lower lip than the upper lip and that of lips moving largely than little was highly enhanced.