• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.35-49
• /
• 2004

This paper proposes a new glasses removal method from color frontal facial image to generate gray glassless facial image. The proposed method is based on recursive PCA reconstruction. For the generation of glassless images, the occluded region by glasses should be found, and a good reconstructed image to compensate with should be obtained. The recursive PCA reconstruction Provides us with both of them simultaneously, and finally produces glassless facial images. This paper shows the effectiveness of the proposed method by some experimental results. We believe that this method can be applied to removing other type of occlusion than the glasses with some modification and enhancing the performance of a face recognition system.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.8
• /
• pp.55-61
• /
• 2010

In this paper, we proposed selective extraction method of frequency information and PCA-ELM based diagnosis system for three-phase induction motors. As the first step for diagnosis procedure, DFT is performed to transform the acquired current signal into frequency domain. And then, frequency components are selected according to discriminate order calculated by variance As the next step, feature extraction is performed by principal component analysis (PCA). Finally, we used the classifier based on Extreme Learning Machine (ELM) with fast learning procedure. To show the effectiveness, the proposed diagnostic system has been intensively tested with the various data acquired under different electrical and mechanical faults with varying load.

• Journal of Korean Society of Water and Wastewater
• /
• v.26 no.6
• /
• pp.757-766
• /
• 2012

In this study, we have examined concentration distribution and patterns of PCBs in waters, sediments and soils in an agricultural area of South Korea to investigate the relationship between PCBs sources and concentration levels. The concentration of PCBs in water samples were ranged from lower values below detection limit to 8.25 ug/L and the concentration of PCBs in sediment samples were ranged from lower values below detection limit to 76.67 ug/Kg. The concentration of PCBs in soil samples were ranged from lower values below detection limit to 23.51 ug/Kg. These contamination levels were far below the guideline values suggested for environmental quality assessment. The homologue patterns in samples varied from sample to sample, but isomer patterns were very similar with each other. PCB-138 and PCB-153 were predominant congeners in the soil and sediment, which were similar to the results obtained from previous studies. With these results, the assessment of potential sources of PCBs contamination in the sediments of the Nakdong river basin was performed. The principal components were extracted by Principal Component Analysis(PCA). As the result of PCA, it could be expected that PCBs in samples of this study were more affected by PCB products than combustion processes and mostly affected by already-known sources. The PCBs in the soil and sediment samples were related with commercial PCB products.

• Korean Journal of Plant Resources
• /
• v.30 no.3
• /
• pp.298-310
• /
• 2017

Morphological variation between cultivated and weedy types of Perilla frutescens var. frutescens and P. frutescens var. crispa were studied in 327 germplasm by examining 17 morphological characters. The germplasm between the two varieties were varied for their qualitative and quantitative characters. The seed coat color of cultivated P. frutescens var. frutescens is commonly light brown and brown while deep brown color was observed in the weedy type P. frutescens var. frutescens and P. frutescens var. crispa. The leaf size, cluster length, plant height, flower number per cluster and seed weight in cultivated P. frutescens var. frutescens were significantly (P<0.05) different from weedy type P. frutescens var. frutescens and P. frutescens var. crispa. The cultivated P. frutescens var. frutescens exhibited significantly higher plant height (158.6 cm) compared to the weedy P. frutescens var. crispa (133.8 cm). Likewise, seed weight was significantly higher in cultivated (1.9 g) than in the weedy type of P. frutescens var. frutescens (1.6 g) and P. frutescens var. crispa (1.4 g). Principal component analysis (PCA) result showed that the first and second principal component cumulatively explained 86.6% of the total variation. The cultivated type P. frutescens var. frutescens and its weedy accessions were not clearly separated with P. frutescens var. crispa by PCA. Hence it requires the use of molecular markers for better understanding of their genetic diversity.

• Journal of Korea Water Resources Association
• /
• v.48 no.9
• /
• pp.757-768
• /
• 2015

Recently, climate change has affected short time concentrated local rainfall and unexpected heavy rain which is increasingly causing life and property damage. In this research, arithmetic average analysis, weighted average analysis, and principal component analysis are used for predicting flood risk. This research is foundation for application of predicting flood risk based on annals of disaster and status of urban planning. Results obtained by arithmetic average analysis, weighted average analysis, and principal component analysis using many factors affect on flood are compared. In case of arithmetic average analysis, each factor has same weights though it is simple method. In case of weighted average analysis, correlation factors are complex by many variables and multicollinearty problem happen though it has different weights. For solving these problems, principal component analysis (PCA) is used because each factor has different weights and the number of variables is smaller than other methods by combining variables. Finally, flood risk assessment considering flood control ability and urban environment risk in former research is predicted.

• The KIPS Transactions:PartB
• /
• v.12B no.1 s.97
• /
• pp.9-16
• /
• 2005

This paper focuses on the study of the face authentication system and the robustness of fact authentication methods under illumination changes. Four different face authentication methods are tried. These methods are as fellows; PCA(Principal Component Analysis), GMM(Gaussian Mixture Modeis), 1D HMM(1 Dimensional Hidden Markov Models), Pseudo 2D HMM(Pseudo 2 Dimensional Hidden Markov Models). Experiment results involving an artificial illumination change to fate images are compared with each other. Face feature vector extraction based on the 2D DCT(2 Dimensional Discrete Cosine Transform) if used. Experiments to evaluate the above four different fate authentication methods are carried out on the ORL(Olivetti Research Laboratory) face database. Experiment results show the EER(Equal Error Rate) performance degrade in ail occasions for the varying ${\delta}$. For the non illumination changes, Pseudo 2D HMM is $2.54{\%}$,1D HMM is $3.18{\%}$, PCA is $11.7{\%}$, GMM is $13.38{\%}$. The 1D HMM have the bettor performance than PCA where there is no illumination changes. But the 1D HMM have worse performance than PCA where there is large illumination changes(${\delta}{\geq}40$). For the Pseudo 2D HMM, The best EER performance is observed regardless of the illumination changes.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.3
• /
• pp.261-270
• /
• 2017

Bad sitting postures are known to cause for a variety of diseases or physical deformation. However, it is not easy to fit right sitting posture for long periods of time. Therefore, methods of distinguishing and inducing good sitting posture have been constantly proposed. Proposed methods were image processing, using pressure sensor attached to the chair, and using the IMU (Internal Measurement Unit). The method of using IMU has advantages of simple hardware configuration and free of various constraints in measurement. In this paper, we researched on distinguishing sitting postures with a small amount of data using just one IMU. Feature extraction method was used to find data which contribution is the least for classification. Machine learning algorithms were used to find the best position to classify and we found best machine learning algorithm. Used feature extraction method was PCA(Principal Component Analysis). Used Machine learning models were five : SVM(Support Vector Machine), KNN(K Nearest Neighbor), K-means (K-means Algorithm) GMM (Gaussian Mixture Model), and HMM (Hidden Marcov Model). As a result of research, back neck is suitable position for classification because classification rate of it was highest in every model. It was confirmed that Yaw data which is one of the IMU data has the smallest contribution to classification rate using PCA and there was no changes in classification rate after removal it. SVM, KNN are suitable for classification because their classification rate are higher than the others.

• The Journal of the Korea Contents Association
• /
• v.6 no.1
• /
• pp.31-40
• /
• 2006

In this paper, we propose a gait recognition method based on gait silhouette sequences. Features of gait are affected by the variation of gait direction. Therefore, we synthesize silhouettes to canonical form by using planar homography in order to reduce the effect of the variation of gait direction. The planar homography is estimated with only the information which exist within the gait sequences without complicate operations such as camera calibration. Even though gait silhouettes are generated from an individual person, fragments beyond common characteristics exist because of errors caused by inaccuracy of background subtraction algorithm. In this paper, we use the Principal Component Analysis to analyze the deviated characteristics of each individual person. PCA used in this paper, however, is not same as the traditional strategy used in pattern classification. We use PCA as a criterion to analyze the amount of deviation from common characteristic. Experimental results show that the proposed method is robust to the variation of gait direction and improves separability of test-data groups.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.1
• /
• pp.77-85
• /
• 2006

In this paper, we propose a hierarchical classifier of object images using neural networks for content-based image classification. The images for classification are object images that can be divided into foreground and background. In the preprocessing step, we extract the object region and shape-based texture features extracted from wavelet transformed images. We group the image classes into clusters which have similar texture features using Principal Component Analysis(PCA) and K-means. The hierarchical classifier has five layes which combine the clusters. The hierarchical classifier consists of 59 neural network classifiers learned with the back propagation algorithm. Among the various texture features, the diagonal moment was the most effective. A test with 1000 training data and 1000 test data composed of 10 images from each of 100 classes shows classification rates of 81.5% and 75.1% correct, respectively.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.4
• /
• pp.47-55
• /
• 2010

In this paper, we proposed a recognition system of smile facial expression for smile treatment training. The proposed system detects face candidate regions by using Haar-like features from camera images. After that, it verifies if the detected face candidate region is a face or non-face by using SVM(Support Vector Machine) classification. For the detected face image, it applies illumination normalization based on histogram matching in order to minimize the effect of illumination change. In the facial expression recognition step, it computes facial feature vector by using PCA(Principal Component Analysis) and recognizes smile expression by using a multilayer perceptron artificial network. The proposed system let the user train smile expression by recognizing the user's smile expression in real-time and displaying the amount of smile expression. Experimental result show that the proposed system improve the correct recognition rate by using face region verification based on SVM and using illumination normalization based on histogram matching.