• Title/Summary/Keyword: 가우시안 분포

Search Result 128, Processing Time 0.322 seconds

Gaussian Distribution-Based Face Tracking (가우시안 분포를 기반으로 한 얼굴 추적)

  • Park Soon-Young;Song Young-Sub;Kim Hang-Joon
    • Proceedings of the Korean Information Science Society Conference
    • /
    • /
    • pp.295-297
    • /
    • 2006
  • 본 논문에서는 연속 영상에서 가우시안 분포를 사용하여 사람의 얼굴을 추적하는 방법을 제안한다. 영상은 여러 개의 동질한 영역들로 이루어지고, 이 영역들 중 얼굴 영역이 있다고 가정하였다. 영상에 있는 모든 영역들을 가우시안 분포로 표현하였으며, 이들의 집합을 가우시안 분포의 혼합 모델로 표현하였다. 제안된 방범에서는 이전 프레임에서 가우시안 분포들을 찾고, 찾아진 이전 프레임의 가우시안 분포들을 이용하여 현재 프레임의 영역들을 찾는다. 이 영역들 중, 초기에 주어진 얼굴 영역이 있으며 현재 프레임의 영역들에 의해 가우시안 분포는 갱신되고 이 과정을 반복함으로써 얼굴을 추적한다. 가우시안 분포의 개수를 다양하게 변화시켜 실험을 하였고, 이를 통해 가우시안 분포의 혼합 모델로 얼굴을 추적할 수 있음을 보였다.

  • PDF

Distribution Approximation of the Two Dimensional Discrete Cosine Transform Coefficients of Image (영상신호 2차원 코사인 변환계수의 분포근사화)

  • 심영석
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.10 no.3
    • /
    • pp.130-134
    • /
    • 1985
  • In two-dimensional discrete cosine transform(DCT) coding, the measurements of the distributions of the transform coefficients are important because a better approximation yields a smaller mean square distorition. This paper presents the results of distribution tests which indicate that the statistics of the AC coefficients are well approximated to a generalized Gaussian distribution whose shape parameter is 0.6. Furthermore, from a simulation of the DCT coding, it was shown that the above approximation yields a higher experimental SNR and a better agreement between theory and simulation than the Gaussian or Laplacian assumptions.

  • PDF

Maximum-Entropy Image Enhancement Using Brightness Mean and Variance (영상의 밝기 평균과 분산을 이용한 엔트로피 최대화 영상 향상 기법)

  • Yoo, Ji-Hyun;Ohm, Seong-Yong;Chung, Min-Gyo
    • Journal of Internet Computing and Services
    • /
    • v.13 no.3
    • /
    • pp.61-73
    • /
    • 2012
  • This paper proposes a histogram specification based image enhancement method, which uses the brightness mean and variance of an image to maximize the entropy of the image. In our histogram specification step, the Gaussian distribution is used to fit the input histogram as well as produce the target histogram. Specifically, the input histogram is fitted with the Gaussian distribution whose mean and variance are equal to the brightness mean(${\mu}$) and variance(${\sigma}2$) of the input image, respectively; and the target Gaussian distribution also has the mean of the value ${\mu}$, but takes as the variance the value which is determined such that the output image has the maximum entropy. Experimental results show that compared to the existing methods, the proposed method preserves the mean brightness well and generates more natural looking images.

Efficient Path Search Method using Genetic Algorithm and SOM Algorithm (유전자 알고리즘과 SOM 알고리즘을 이용한 효율적 경로 탐색)

  • Jeong, Ji-In;Eom, Do-Sung;Kim, Kwang-Beak
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • /
    • pp.87-90
    • /
    • 2011
  • 본 논문에서는 유전자 알고리즘에 SOM 알고리즘을 적용하여 효율적으로 경로를 탐색할 수 있는 방법을 제안한다. 제안된 경로 탐색 방법은 효율적인 경로 탐색에 앞서 유전자 알고리즘에 의해 도출된 각각의 결과 좌표를 뉴런으로 설정하고 각 뉴런들의 모든 거리 값을 SOM 알고리즘에 적용하여 거리에 대한 가중치를 구한다. 뉴런 선택 조건(가장 적은 거리 가중치, 이전에 선택되지 않았던 뉴런)을 만족하는 뉴런 및 해당 뉴런의 이웃 반경 내에 존재하는 뉴런들의 연결 강도를 가우시안 분포(오차율 분포)에 적용하여 변경하고, 가장 강한 연결 강도를 가지는 승자 뉴런에 해당하는 경로를 선택한다. 이러한 과정을 뉴런의 개수만큼 반복하여 모든 뉴런들의 경로를 도출한다. 제안된 방법을 실험한 결과, 기존의 유전자 알고리즘을 이용한 방법보다 제안된 방법이 효율적인 경로를 탐색하는 것을 확인할 수 있었다.

  • PDF

Vector Quantization based Speech Recognition Performance Improvement using Maximum Log Likelihood in Gaussian Distribution (가우시안 분포에서 Maximum Log Likelihood를 이용한 벡터 양자화 기반 음성 인식 성능 향상)

  • Chung, Kyungyong;Oh, SangYeob
    • Journal of Digital Convergence
    • /
    • v.16 no.11
    • /
    • pp.335-340
    • /
    • 2018
  • Commercialized speech recognition systems that have an accuracy recognition rates are used a learning model from a type of speaker dependent isolated data. However, it has a problem that shows a decrease in the speech recognition performance according to the quantity of data in noise environments. In this paper, we proposed the vector quantization based speech recognition performance improvement using maximum log likelihood in Gaussian distribution. The proposed method is the best learning model configuration method for increasing the accuracy of speech recognition for similar speech using the vector quantization and Maximum Log Likelihood with speech characteristic extraction method. It is used a method of extracting a speech feature based on the hidden markov model. It can improve the accuracy of inaccurate speech model for speech models been produced at the existing system with the use of the proposed system may constitute a robust model for speech recognition. The proposed method shows the improved recognition accuracy in a speech recognition system.

Mel-Frequency Cepstral Coefficients Using Formants-Based Gaussian Distribution Filterbank (포만트 기반의 가우시안 분포를 가지는 필터뱅크를 이용한 멜-주파수 켑스트럴 계수)

  • Son, Young-Woo;Hong, Jae-Keun
    • The Journal of the Acoustical Society of Korea
    • /
    • v.25 no.8
    • /
    • pp.370-374
    • /
    • 2006
  • Mel-frequency cepstral coefficients are widely used as the feature for speech recognition. In FMCC extraction process. the spectrum. obtained by Fourier transform of input speech signal is divided by met-frequency bands, and each band energy is extracted for the each frequency band. The coefficients are extracted by the discrete cosine transform of the obtained band energy. In this Paper. we calculate the output energy for each bandpass filter by taking the weighting function when applying met-frequency scaled bandpass filter. The weighting function is Gaussian distributed function whose center is at the formant frequency In the experiments, we can see the comparative performance with the standard MFCC in clean condition. and the better Performance in worse condition by the method proposed here.

Noise Removal using Gaussian Distribution and Standard Deviation in AWGN Environment (AWGN 환경에서 가우시안 분포와 표준편차를 이용한 잡음 제거)

  • Cheon, Bong-Won;Kim, Nam-Ho
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.23 no.6
    • /
    • pp.675-681
    • /
    • 2019
  • Noise removal is a pre-requisite procedure in image processing, and various methods have been studied depending on the type of noise and the environment of the image. However, for image processing with high-frequency components, conventional additive white Gaussian noise (AWGN) removal techniques are rather lacking in performance because of the blurring phenomenon induced thereby. In this paper, we propose an algorithm to minimize the blurring in AWGN removal processes. The proposed algorithm sets the high-frequency and the low-frequency component filters, respectively, depending on the pixel properties in the mask, consequently calculating the output of each filter with the addition or subtraction of the input image to the reference. The final output image is obtained by adding the weighted data calculated using the standard deviations and the Gaussian distribution with the output of the two filters. The proposed algorithm shows improved AWGN removal performance compared to the existing method, which was verified by simulation.

Analysis of Subthreshold Current Deviation for Gate Oxide Thickness of Double Gate MOSFET (채널도핑농도에 따른 이중게이트 MOSFET의 문턱전압이하 전류 변화 분석)

  • Jung, Hakkee
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • /
    • pp.768-771
    • /
    • 2013
  • This paper analyzed the change of subthreshold current for channel doping concentration of double gate(DG) MOSFET. Poisson's equation had been used to analyze the potential distribution in channel, and Gaussian function had been used as carrier distribution. The potential distribution was obtained as the analytical function of channel dimension, using the boundary condition. The subthreshold current had been analyzed for channel doping concentration, and projected range and standard projected deviation of Gaussian function. Since this analytical potential model was verified in the previous papers, we used this model to analyze the subthreshold current. As a result, we know the subthreshold current was influenced on parameters of Gaussian function and channel doping concentration for DGMOSFET.

  • PDF

Signal Subspace-based Voice Activity Detection Using Generalized Gaussian Distribution (일반화된 가우시안 분포를 이용한 신호 준공간 기반의 음성검출기법)

  • Um, Yong-Sub;Chang, Joon-Hyuk;Kim, Dong Kook
    • The Journal of the Acoustical Society of Korea
    • /
    • v.32 no.2
    • /
    • pp.131-137
    • /
    • 2013
  • In this paper we propose an improved voice activity detection (VAD) algorithm using statistical models in the signal subspace domain. A uncorrelated signal subspace is generated using embedded prewhitening technique and the statistical characteristics of the noisy speech and noise are investigated in this domain. According to the characteristics of the signals in the signal subspace, a new statistical VAD method using GGD (Generalized Gaussian Distribution) is proposed. Experimental results show that the proposed GGD-based approach outperforms the Gaussian-based signal subspace method at 0-15 dB SNR simulation conditions.