• Title/Summary/Keyword: 벡터 성분분리법

Search Result 8, Processing Time 0.022 seconds

Text Area Segmentation and Layout Vectorization of Off-line Handwritten Forms (손으로 설계한 서식 문서의 문자 영역 분리 및 서식 벡터화)

  • Kim, Byeong-Yong;Gwon, O-Seok
    • The Transactions of the Korea Information Processing Society
    • /
    • v.7 no.10
    • /
    • pp.3086-3097
    • /
    • 2000
  • 본 논문에서는 손으로 자유스럽게 그린 서식 문서에서 문자 영역을 분리하고, 이 중 선 성분을 벡터화하는 방법을 제안한다. 제안된 방법은 우선 이진화 및 세선화 과정에서의 데이터 손실을 방지하기 위해 스캔한 영상에 DRC 알고리즘을 적용한다. 그리고 영상의 기울어짐을 교정하기 위해 세선화된 영상에 허프 변환을 적용하여 기울어짐을 추정하고 교정한 다음, 서식의 구조를 이루는 선 성분을 추출해 낸다. 그리고 문자 영역은 연결 요소 분석법에 의해 문자 영역을 나타내는 데이터로 변환되며, 추출된 선 성분을 정렬, 합병 및 교정처리를 통해 벡터화 된다. 제안된 방법의 실효성을 입증하기 위해 각각 25명의 다른 사람이 필기구에 제한을 두지 않고 하나는 자를 사용하여 작성하고 다른 하나는 자를 사용하지 않고 작성한 서식에 대해 실험한 결과 전체 750개의 벡터 집합 중에서 전처리를 하지 않은 경우에는 666개, 전처리를 한 경우에는 746개의 서식 벡터 검출에 성공하여 그 유효성을 확인할 수 있었다.

  • PDF

Performance Improvement of Speech Recognition Based on Independent Component Analysis (독립성분분석법을 이용한 음성인식기의 성능향상)

  • 김창근;한학용;허강인
    • Proceedings of the Korea Institute of Convergence Signal Processing
    • /
    • 2001.06a
    • /
    • pp.285-288
    • /
    • 2001
  • In this paper, we proposed new method of speech feature extraction using ICA(Independent Component Analysis) which minimized the dependency and correlation among speech signals on purpose to separate each component in the speech signal. ICA removes the repeating of data after finding the axis direction which has the greatest variance in input dimension. We verified improvement of speech recognition ability with training and recognition experiments when ICA compared with conventional mel-cepstrum features using HMM. Also, we can see that ICA dealt with the situation of recognition ability decline that is caused by environmental noise.

  • PDF

Separations and Feature Extractions for Image Signals Using Independent Component Analysis Based on Neural Networks of Efficient Learning Rule (효율적인 학습규칙의 신경망 기반 독립성분분석을 이용한 영상신호의 분리 및 특징추출)

  • Cho, Yong-Hyun
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.13 no.2
    • /
    • pp.200-208
    • /
    • 2003
  • This paper proposes a separation and feature extraction of image signals using the independent component analysis(ICA) based on neural networks of efficient learning rule. The proposed learning rule is a hybrid fixed-point(FP) algorithm based on secant method and momentum. Secant method is applied to improve the performance by simplifying the 1st-order derivative computation for optimizing the objective function, which is to minimize the mutual informations of the independent components. The momentum is applied for high-speed convergence by restraining the oscillation in the process of converging to the optimal solution. The proposed algorithm has been applied to the composite images generated by random mixing matrix from the 10 images of $512\times512$-pixel. The simulation results show that the proposed algorithm has better performances of the separation speed and rate than those using the FP algorithm based on Newton and secant method. The proposed algorithm has been also applied to extract the features using a 3 set of 10,000 image patches from the 10 fingerprints of $256\times256$-pixel and the front and the rear paper money of $480\times225$-pixel, respectively, The simulation results show that the proposed algorithm has also better extraction speed than those using the another methods. Especially, the 160 basis vectors(features) of $16\times16$-pixel show the local features which have the characteristics of spatial frequency and oriented edges in the images.

The development of solar tracking sensor and controller for improvement of generation efficiency (발전 효율향상을 위한 태양광추적 센서 및 제어기 개발)

  • Han, Ki-Bong;Han, Tae-Hee;Lee, Shin-Won;Han, Seung-Woo
    • Journal of the Korean Solar Energy Society
    • /
    • v.32 no.6
    • /
    • pp.29-36
    • /
    • 2012
  • The existing solar tracking sensor for 2 axial control system to trace latitude and longitude is made of four phototransistor. The phototransistor-making is difficult and it's manufacturing is more high-priced than a wide use phototransistor because they have to the same characteristics of each phototransistor output signal. This paper described the algorithm for supplement these weakness. The algorithm applied to signal normalizing method and vector decomposition law. The deviations of each a wide use phototransistor output signal are resolved by signal normalizing method and it is able to make a solar tracking sensor using three phototransistor by vector decomposition law. Therefore, in this paper, it is reduced the number of phototransistor that is composed of solar tracking sensor and possible to use a wide use phototransistor by the proposed algorithm.

A Study on Stroke Extraction for Handwritten Korean Character Recognition (필기체 한글 문자 인식을 위한 획 추출에 관한 연구)

  • Choi, Young-Kyoo;Rhee, Sang-Burm
    • The KIPS Transactions:PartB
    • /
    • v.9B no.3
    • /
    • pp.375-382
    • /
    • 2002
  • Handwritten character recognition is classified into on-line handwritten character recognition and off-line handwritten character recognition. On-line handwritten character recognition has made a remarkable outcome compared to off-line hacdwritten character recognition. This method can acquire the dynamic written information such as the writing order and the position of a stroke by means of pen-based electronic input device such as a tablet board. On the contrary, Any dynamic information can not be acquired in off-line handwritten character recognition since there are extreme overlapping between consonants and vowels, and heavily noisy images between strokes, which change the recognition performance with the result of the preprocessing. This paper proposes a method that effectively extracts the stroke including dynamic information of characters for off-line Korean handwritten character recognition. First of all, this method makes improvement and binarization of input handwritten character image as preprocessing procedure using watershed algorithm. The next procedure is extraction of skeleton by using the transformed Lu and Wang's thinning: algorithm, and segment pixel array is extracted by abstracting the feature point of the characters. Then, the vectorization is executed with a maximum permission error method. In the case that a few strokes are bound in a segment, a segment pixel array is divided with two or more segment vectors. In order to reconstruct the extracted segment vector with a complete stroke, the directional component of the vector is mortified by using right-hand writing coordinate system. With combination of segment vectors which are adjacent and can be combined, the reconstruction of complete stroke is made out which is suitable for character recognition. As experimentation, it is verified that the proposed method is suitable for handwritten Korean character recognition.

Geometrically Non-linear Finite Element Analysis of Space Frames (공간뼈대구조의 기하학적 비선형 유한요소해석)

  • 김문영;안성원
    • Computational Structural Engineering
    • /
    • v.10 no.1
    • /
    • pp.201-211
    • /
    • 1997
  • A clearly consistent finite element formulation for geometrically non-linear analysis of space frames is presented by applying incremental equilibrium equations based on the updated Lagrangian formulation and introducing Vlasov's assumption. The improved displacement field for symmetric cross sections is introduced based on inclusion of second order terms of finite rotations, and the potential energy corresponding to the semitangential rotations and moments is consistently derived. For finite element analysis, elastic and geometric stiffness matrices of the space frame element are derived by using the Hermitian polynomials as shape functions. A co-rotational formulation in order to evaluate the unbalanced loads is presented by separating the rigid body rotations and pure deformations from incremental displacements and evaluating the updated direction cosines of the frame element due to rigid body rotations and incremental member forces from pure deformaions. Finite element solutions for the spatial buckling and post-buckling analysis of space frames are compared with available solutions and other researcher's results.

  • PDF

Integrated Algorithm for Identification of Long Range Artillery Type and Impact Point Prediction With IMM Filter (IMM 필터를 이용한 장사정포의 탄종 분리 및 탄착점 예측 통합 알고리즘)

  • Jung, Cheol-Goo;Lee, Chang-Hun;Tahk, Min-Jea;Yoo, Dong-Gil;Sohn, Sung-Hwan
    • Journal of the Korean Society for Aeronautical & Space Sciences
    • /
    • v.50 no.8
    • /
    • pp.531-540
    • /
    • 2022
  • In this paper, we present an algorithm that identifies artillery type and rapidly predicts the impact point based on the IMM filter. The ballistic trajectory equation is used as a system model, and three models with different ballistic coefficient values are used. Acceleration was divided into three components of gravity, air resistance, and lift. And lift acceleration was added as a new state variable. The kinematic condition that the velocity vector and lift acceleration are perpendicular was used as a pseudo-measurement value. The impact point was predicted based on the state variable estimated through the IMM filter and the ballistic coefficient of the model with the highest mode probability. Instead of the commonly used Runge-Kutta numerical integration for impact point prediction, a semi-analytic method was used to predict impact point with a small amount of calculation. Finally, a state variable initialization method using the least-square method was proposed. An integrated algorithm including artillery type identification, impact point prediction and initialization was presented, and the validity of the proposed method was verified through simulation.

Target Advertisement Service using a Viewer's Profile Reasoning (시청자 프로파일 추론 기법을 이용한 표적 광고 서비스)

  • Kim Munjo;Im Jeongyeon;Kang Sanggil;Kim Munchrul;Kang Kyungok
    • Journal of Broadcast Engineering
    • /
    • v.10 no.1 s.26
    • /
    • pp.43-56
    • /
    • 2005
  • In the existing broadcasting environment, it is not easy to serve the bi-directional service between a broadcasting server and a TV audience. In the uni-directional broadcasting environments, almost TV programs are scheduled depending on the viewers' popular watching time, and the advertisement contents in these TV programs are mainly arranged by the popularity and the ages of the audience. The audiences make an effort to sort and select their favorite programs. However, the advertisement programs which support the TV program the audience want are not served to the appropriate audiences efficiently. This randomly provided advertisement contents can occur to the audiences' indifference and avoidance. In this paper, we propose the target advertisement service for the appropriate distribution of the advertisement contents. The proposed target advertisement service estimates the audience's profile without any issuing the private information and provides the target-advertised contents by using his/her estimated profile. For the experimental results, we used the real audiences' TV usage history such as the ages, fonder and time of the programs from AC Neilson Korea. And we show the accuracy of the proposed target advertisement service algorithm. NDS (Normalized Distance Sum) and the Vector correlation method, and implementation of our target advertisement service system.