• Title/Summary/Keyword: Eigen Vector

Search Result 67, Processing Time 0.022 seconds

Simultaneous Speaker and Environment Adaptation by Environment Clustering in Various Noise Environments (다양한 잡음 환경하에서 환경 군집화를 통한 화자 및 환경 동시 적응)

  • Kim, Young-Kuk;Song, Hwa-Jeon;Kim, Hyung-Soon
    • The Journal of the Acoustical Society of Korea
    • /
    • v.28 no.6
    • /
    • pp.566-571
    • /
    • 2009
  • This paper proposes noise-robust fast speaker adaptation method based on the eigenvoice framework in various noisy environments. The proposed method is focused on de-noising and environment clustering. Since the de-noised adaptation DB still has residual noise in itself, environment clustering divides the noisy adaptation data into similar environments by a clustering method using the cepstral mean of non-speech segments as a feature vector. Then each adaptation data in the same cluster is used to build an environment-clustered speaker adapted (SA) model. After selecting multiple environmentally clustered SA models which are similar to test environment, the speaker adaptation based on an appropriate linear combination of clustered SA models is conducted. According to our experiments, we observe that the proposed method provides error rate reduction of $40{\sim}59%$ over baseline with speaker independent model.

A Robust Hand Recognition Method to Variations in Lighting (조명 변화에 안정적인 손 형태 인지 기술)

  • Choi, Yoo-Joo;Lee, Je-Sung;You, Hyo-Sun;Lee, Jung-Won;Cho, We-Duke
    • The KIPS Transactions:PartB
    • /
    • v.15B no.1
    • /
    • pp.25-36
    • /
    • 2008
  • In this paper, we present a robust hand recognition approach to sudden illumination changes. The proposed approach constructs a background model with respect to hue and hue gradient in HSI color space and extracts a foreground hand region from an input image using the background subtraction method. Eighteen features are defined for a hand pose and multi-class SVM(Support Vector Machine) approach is applied to learn and classify hand poses based on eighteen features. The proposed approach robustly extracts the contour of a hand with variations in illumination by applying the hue gradient into the background subtraction. A hand pose is defined by two Eigen values which are normalized by the size of OBB(Object-Oriented Bounding Box), and sixteen feature values which represent the number of hand contour points included in each subrange of OBB. We compared the RGB-based background subtraction, hue-based background subtraction and the proposed approach with sudden illumination changes and proved the robustness of the proposed approach. In the experiment, we built a hand pose training model from 2,700 sample hand images of six subjects which represent nine numerical numbers from one to nine. Our implementation result shows 92.6% of successful recognition rate for 1,620 hand images with various lighting condition using the training model.

Application of AHP to Select for Priority of Permanent Traffic Volume Survey Site (AHP를 적용한 상시 교통량 조사 지점 선정 우선순위 결정에 관한 연구)

  • Oh, Ju-Sam;Lim, Sung-Han;Cho, Yoon-Ho
    • International Journal of Highway Engineering
    • /
    • v.7 no.4 s.26
    • /
    • pp.21-30
    • /
    • 2005
  • Traffic volume data have been used for the plan, the design, and the operation of highway. Since 1955, traffic survey has been nation- widely carried out at national highway and the regular survey in national highway has been conducted at the intersections of highways. However, it is critical issue to select the priority of the regular survey because it is almost impossible to conduct regular survey at all intersections of national highways. In this study, MCDM(Multiple Criteria Decision Making) using AHP(Analytic Hierarchy Process) was applied to decide the priority of the regular survey. The following standard variables for determining the priority was selected the highway plan variables[AADT, VKT, Peak Hourly Volume, Location of highway from Urban], the highway design variables[Volume(pcu), Directional Traffic Volume, Heavy Vehicle Rate], and the highway operation variables[Speed, Density, V/C]. The standard variables were quantified and normalized. Using the Eigen vector method, the weighted values of each hierarchy based on the pair-wise comparison values from the questionnaire survey were calculated. The selection of the priority of regular survey was dependent on the size of the product of the weighted values for each hierarchy and the normalized values for the standard variables. Finally, the priority of regular survey of the intersections of national highways was determined according to the order in the size of the product of two values.

  • PDF

Characterization of Korean Archaeological Artifacts by Neutron Activation Analysis (I). Multivariate Classification of Korean Ancient Coins. (중성자 방사화분석에 의한 한국산 고고학적 유물의 특성화 연구 (I). 다변량 해석법에 의한 고전 (古錢) 의 분류 연구)

  • Chul Lee;Oh Cheun Kwun;Hyung Tae Kang;Ihn Chong Lee;Nak Bae Kim
    • Journal of the Korean Chemical Society
    • /
    • v.31 no.6
    • /
    • pp.555-566
    • /
    • 1987
  • Fifty ancient Korean coins originated in Yi Dynasty have been determined for 9 elements such as Sn, Fe, As, Ag, Co, Sb, Ir, Ru and Ni by instrumental neutron activation analysis and for 3 elements such as Cu, Pb, and Zn by atomic absorption spectrometry. Bronze coins originated in early days of the dynasty contain as major constituents Cu, Pb and Sn approximately in the ratio 90 : 4 : 3, whereas, those in latter days contain in ratio 7 : 2 : 0. Brass coins which had begun in 17 century contain as major constituents Cu, Zn and Pb approximately in the ratio 7 : 1 : 1. The multivariate data have been analyzed for the relation among elemental contents through the variance-covariance matrix. The data have been further analyzed by a principal component mapping method. As the results training set of 8 class have been chosen, based on the spread of sample points in an eigen vector plot and archaeological data such as age and the office of minting. The training set and test set of samples have finally been analyzed for the assignment to certain classes or outliers through the statistical isolinear multiple component analysis (SIMCA).

  • PDF

Variation of Characteristics and Principal Component Analysis of Collected Colored Rice Cultivars (수집 유색미 계통의 형질특성 변이 및 주성분 분석)

  • 김창영;변종영;이종철
    • Korean Journal of Plant Resources
    • /
    • v.12 no.3
    • /
    • pp.186-191
    • /
    • 1999
  • This study was conducted to evaluate the growth characteristics and grain component of 10 collected colored rice cultivars to find out the possibilities of using the agronomically usefull characters to provide information for colored rice breeding and cultivation. The coefficients of variation of culm length, grains number, ripening rate, maturity time, and coat color of grain and seed were higher than those of other characters. The positive correlations were observed among heading dates, grain numbers per panicle, and 1000 grain weight, as well as between culm length and panicle length, panicle length and grain numbers per panicle, 1000 grain weight and darkness of seed coat color, while negative correlations were observed between heading dates and panicle numbers per hill, grain yield and seed coat color as well as among culm length, length, number per hill and seed coat color of brown rice, respectively. The first component of principal component analysis was consist of panicle numbers per hill, 1000 grain weight, and grain yield showing higher correlations among them which explained the variance of the sink size of respective cultivars. The second component of principal component analysis was consist of heading date, grain numbers per panicle and maturing date showing higher correlations among them which explained the variance of maturity of respective cultivars.

  • PDF

Development of Recognition Application of Facial Expression for Laughter Theraphy on Smartphone (스마트폰에서 웃음 치료를 위한 표정인식 애플리케이션 개발)

  • Kang, Sun-Kyung;Li, Yu-Jie;Song, Won-Chang;Kim, Young-Un;Jung, Sung-Tae
    • Journal of Korea Multimedia Society
    • /
    • v.14 no.4
    • /
    • pp.494-503
    • /
    • 2011
  • In this paper, we propose a recognition application of facial expression for laughter theraphy on smartphone. It detects face region by using AdaBoost face detection algorithm from the front camera image of a smartphone. After detecting the face image, it detects the lip region from the detected face image. From the next frame, it doesn't detect the face image but tracks the lip region which were detected in the previous frame by using the three step block matching algorithm. The size of the detected lip image varies according to the distance between camera and user. So, it scales the detected lip image with a fixed size. After that, it minimizes the effect of illumination variation by applying the bilateral symmetry and histogram matching illumination normalization. After that, it computes lip eigen vector by using PCA(Principal Component Analysis) and recognizes laughter expression by using a multilayer perceptron artificial network. The experiment results show that the proposed method could deal with 16.7 frame/s and the proposed illumination normalization method could reduce the variations of illumination better than the existing methods for better recognition performance.

Classification of the Korean Local Pearl Barley(Coix larcryma L.) by the Morphological Characters (재래종(在來種) 율무(의이인(薏苡仁))의 형태적(形態的) 특성(特性)에 의한 분류(分類))

  • Kim, Bo Kyeong;Choe, Bong Ho
    • Korean Journal of Agricultural Science
    • /
    • v.13 no.1
    • /
    • pp.17-32
    • /
    • 1986
  • To obtain basic information needed for developing better pearl barley varieties, a total of 148 lines of pearl barley were collected from nationwide survey except for Kangwon and Chejoo provinces and classified by principal component analysis. The results are summarized as follows : 1. Variabilities of characters for all lines except for leaf width and 100 K. Wt.(Unpolished) were high enough to indicate variation of lines. 2. Correlation coefficients among 18 characters were high enough and they showed the shape of normal distribution, more or less, inclined toward positive values. 3. The lines could be classified into four groups by correlation coefficient for 18 characters : Group I was characterized as the lines composed of grain and plant type, Group II maturity, Group III the number of tillers, and Group IV the nature of germination, respectively. 4. About 60% of the total variation could be appreciated by the first four principal components and about 89% of the total variation by the first ten principal components. 5. Contribution of characters to principal components was variable and was high at upper principal components and low at lower principal components. 6. The value of eigen vector corresponding to those which had high significant correlation coefficient between characters was almost of the same value. 7. The lines were classified into four groups by principal component analysis. 8. The lines were also classified into four groups by taxonomic distance. Group I included 79 lines, Group II 40 lines, Group III 22 lines, and Group IV 7 lines, respectively. 9. Four groups classified by taxonomic distance could be characterized as follow : Group I : medium height plant, small kernels, medium maturity, and narrow and short leaf, Group II : short height plant, small kernels, early maturity, and narrow and short leaf. Group III : tall height plant, large kernels, late maturity, and broad and long leaf. Group IV : short height plant, large kernels, medium maturity, and narrow and short leaf.

  • PDF