• The Journal of the Korea Contents Association
• /
• v.9 no.9
• /
• pp.97-104
• /
• 2009

This paper describes comparison and analysis of methodology which enables us in order to search the projection technique of optimum for projection in the plane. For this methodology, we applies the high-dimensional facial motion capture data respectively in linear and nonlinear projection techniques. The one core element of the methodology is to applies the high-dimensional facial expression data of frame unit in PCA where is a linear projection technique and Isomap, MDS, CCA, Sammon's Mapping and LLE where are a nonlinear projection techniques. And another is to find out the methodology which distributes in this low-dimensional space, and analyze the result last. For this goal, we calculate the distance between the high-dimensional facial expression frame data of existing. And we distribute it in two-dimensional plane space to maintain the distance relationship between the high-dimensional facial expression frame data of existing like that from the condition which applies linear and nonlinear projection techniques. When comparing the facial expression data which distribute in two-dimensional space and the data of existing, we find out the projection technique to maintain the relationship of distance between the frame data like that in condition of optimum. Finally, this paper compare linear and nonlinear projection techniques to projection high-dimensional facial expression data in low-dimensional space and analyze it. And we find out the projection technique of optimum from it.

• Journal of KSNVE
• /
• v.9 no.1
• /
• pp.196-205
• /
• 1999

The existence. bifurcation. and the orbital stability of periodic motions, which is called nonlinear normal mode, in a nonlinear dual mass Hamiltonian system. which has 6th order homogeneous polynomial as a nonlinear term. are studied in this paper. By direct integration of the equations of motion. Poincare Map. which is a mapping of a phase trajectory onto 2 dimensional surface in 4 dimensional phase space. is obtained. And via the Birkhoff-Gustavson canonical transformation, the analytic expression of the invariant curves in the Poincare Map is derived for small value of energy. It is found that the nonlinear system. which is considered in this paper. has 2 or 4 nonlinear normal modes depending on the value of nonlinear parameter. The Poincare Map clearly shows that the bifurcation modes are stable while the mode from which they bifurcated out changes from stable to unstable.

• Journal of Digital Contents Society
• /
• v.19 no.9
• /
• pp.1787-1793
• /
• 2018

Shadow is a common phenomenon observed in natural scenes, but it has a negative influence on image analysis such as object recognition, feature detection and scene analysis. Therefore, the process of detecting and removing shadows included in digital images must be considered as a pre-processing process of image analysis. In this paper, the existing methods for acquiring 1D invariant images, one of the feature elements for detecting and removing shadows contained in a single natural image, are described, and a method for obtaining 1D invariant images based on linear regression has been proposed. The proposed method calculates the log of the band-ratio between each channel of the RGB color image, and obtains the grayscale image line by linear regression. The final 1D invariant images were obtained by projecting the log image of the band-ratio onto the estimated grayscale image line. Experimental results show that the proposed method has lower computational complexity than the existing projection method using entropy minimization, and shadow detection and removal based on 1D invariant images are performed effectively.

• Annual Conference on Human and Language Technology
• /
• 1994.11a
• /
• pp.201-206
• /
• 1994

문서 인식 시스템의 성능을 저하시키는 가장 큰 원인 중의 하나로 문자 분할 오류를 들 수 있는데 보다 우수한 성능의 문서 인식 시스템 개발을 위해서는 정확한 문자 분할 방법이 절실히 요구된다. 기존의 문자 분할에 관한 연구들은 이진 영상을 대상으로 함으로써 접촉되거나 겹치는 문자의 경계 부분에서 문자 분할에 유용한 정보들을 잃어 문자 분할 오류를 초래할 수 있다. 하지만 명도 영상을 분석해 보면 문자의 접촉 부분에서 주로 나타나는 지형적 특징이 있으며, 문자 경계에서 명도값이 변하는 것을 관찰할 수 있는데 이와같은 명도 영상의 정보를 사용하면 보다 효과적으로 문자를 분할할 수 있을 것으로 판단된다. 본 연구에서는 이러한 점에 착안하여 명도 영상으로부터 지형적 특징을 추출하고 다단계 그래프 탐색 방법을 이용하여 명도값을 추적함으로써 비선형 문자 경계를 찾는 새로운 문자 분할 방법을 제안한다. 제안된 방법은 명도 문자열 영상을 입력으로 받아 명도 영상의 투영값과 명도 영상으로부터 추출된 지형적 특성을 이용하여 문자 분할 영역을 결정하고 문자 분할 영역내에서 다단계 그래프 탐색에 의한 비선형 문자 분할 경로를 찾는다. 그리고 문자 인식기와 결항하여 최종 문자 분할 위치를 확정하는 인식 결과를 이용한 문자 분할을 수행함으로써 문자 분할 위치 및 문자 인식 결과를 확정한다. 다양한 문서에 대한 실험 결과 제안된 방법이 이진 정보만을 사용하는 방법보다 접촉 혹은 겹친 문자 분할에 매우 효과적임을 알 수 있었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.784-787
• /
• 2006

In this paper, we propose a method for nonlinear grapheme segmentation in Korean printed character type classification. The characters are subdivided into six types based on character type information. The feature vector is consist of mesh features, vertical projection features and horizontal projection features which are extracted from gray-level images. We classify characters into 6 types using Back propagation. Character segmentation regions are determined based on character type information. Then, an optimal nonlinear grapheme segmentation path is found using multi-stage graph search algorithm. As the result, a proposed methodology is proper to classify character type and to find nonlinear char segmentation paths.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.2
• /
• pp.191-198
• /
• 2001

As a method to compensate the deterioration of the picture quality which was caused by beam profile characteristic in the CRT and the projection screen of HD projection TV, a linear scan velocity modulation(SVM) method has been employed, whose modulation velocity is linearly proportional to the variation in the video signal amplitude. However, the effect of picture quality improvement is not uniform with video signal amplitude in the linear SVM. In this paper, for the optimum SVM effect, we analyze the beam profile characteristic on the HD projection screen and we analyze the SVM effect as function of the differentiated pulse width, the differentiated pulse amplitude and the input signal amplitude. Finally we confirm that the nonlinear SVM method is necessary to get uniform image compensation in the HD projection TV, and we implement the nonlinear SVM circuit. The performance of the realized SVM circuit with nonlinear amplitude transfer characteristic is confirmed as uniform improvements in picture quality.

• Annual Conference on Human and Language Technology
• /
• 1991.10a
• /
• pp.287-299
• /
• 1991

본 논문은 하드웨어 구현이 가능한 신경 회로망을 구성하여 한글 문자 인식을 수행하였다. 먼저 입력 장치로부터 받아들인 문자 영상은 인식 속도를 높히기 위하여 특별한 전처리 과정 없이 직접 피쳐를 추출하였으며 추출한 피쳐로는 하드웨어 구현이 용이한 교차 피쳐와 투영 피쳐를 이진화로 코딩하였다. 신경 회로망의 하드웨어 구현을 가능하게 하기위해서 정수형 연결 강도와 비선형 Hard-limit 함수를 가지고 학습을 하는 Rounding 학습 방법을 도입하여 학습시켰으며 한글의 구조적 특성을 이용하여 한글을 유형별로 Module화 및 Submodule화 작업을 수행한 다음 인식하는 계층적인 문자 인식 시스템을 구성하였다. 그리고 이러한 방법을 이용하여 한글 문자 인식용 CMOS 신경회로망 Chip을 설계하였다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.4
• /
• pp.405-413
• /
• 2002

It is crucial that we should set proper standards capable of efficiently handling new corrections of maps, connections of edges on the maps, administrative districts, and inter-scale connections in order to make serial cadastral maps. This study drew a two dimensional Parameter using an indent point, as a Review Control Point, on forest screening line or boundary line of administrative district. The study also introduced a few different transformations such as Affine Transformation, N-Degree Polynomial Transformation, and Projective Transformation, the two dimensional transformation methods to apply them to the connection of cadastal·forestry maps and the connection of parcels between the administrative districts, on the forestry map designed by discretionary edges on the maps per district unit with parcel numbers and tried to apply the coordinates transformation method to connections of maps to make serial cadastral maps.

• Journal of Korean Society of Transportation
• /
• v.26 no.3
• /
• pp.187-197
• /
• 2008

While driving a highway, A driver gets lots of information through geometrical structure, traffic situation, signs on the road. He gets most of the information by visual sense. Acceleration or deceleration and driving direction depend on sight distance. Therefore, it's essential to secure a driver's sight distance for a safe drive. However, design guides of geometrical structure and sight distance suggest respective standards of horizontal and vertical alignment. They do not indicate quantitative standard of combined alignment. Currently, element separated on a two-dimensional projected plane are available, but they do not guarantee safe and pleasant design. I will use the existent model analysing three-dimensional sight distance through mathematical calculation and sort a variety of geometrical structure element and type. In these researches, we will look at how much three-dimensional sight distance is overestimated or underestimated compared to two-dimensional. I will develop a program which predicts traffic velocity on the curvature of two-lane provincial road. stopped sight distance and three-dimensional sight distance will be compared at a predicted drive velocity. I will suggest the way to evaluate road consistency.

• 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.