• 한국컴퓨터산업학회논문지
• /
• 제4권10호
• /
• pp.631-642
• /
• 2003

본 논문에서는 웹상에서 자신을 대신하는 아바타 제작시 본인의 얼굴과 닮은 얼굴을 생성하기 위해 사진으로부터 개인의 특징정보를 추출하는 방법과 추출된 특징정보에 따라 해당하는 이목구비를 준비된 분류기준에 의해 특정 클래스로 분류해 내는 방법을 제안한다. 특징정보 추출은 눈, 코, 입, 턱선으로 나누어 진행되어졌으며, 각 이목구비의 특징점과 분류기준을 각각 제시하였다. 추출 된 특징정보들은 전문 디자이너에 의해 그려진 이목구비 이미지들과 유사도를 계산하는데 사용되었으며, 여기서 가장 유사한 이미지를 턱선 벡터이미지에 합성하여 아바타 얼굴을 얻어낼 수 있었다.

• 사상체질의학회지
• /
• 제17권2호
• /
• pp.46-51
• /
• 2005

1. Objectives The purpose of this study is to objectify the diagnosis of Sasang Constitution. Using the methods of this study, it will improve to classificate Sasang Constitution. 2. Methods 1) Automatic feature extraction of human frontal faces for Sasang Constitution classification. 2) Color feature extraction of human frontal faces (1)Erosion filtering (skin-white, the other-black) (2) Median median 3. Results and Conclusions Observing a person's shape has been the major method for Sasang Constitution classification, which usually has been dependent upon doctor's intuition as of these days. We are developing an automatic system which provides objective basic data for Sasang Constitution classification. For this, in this paper, firstly, the signal processing techniques are applied to automatic feature extraction of human frontal faces for Sasang Constitution classification. The experiment is conducted to verify the effectiveness of the proposed system.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.6-10
• /
• 2007

Classification of hyperspectral images is challenging. A very high dimensional input space requires an exponentially large amount of data to adequately and reliably represent the classes in that space. In other words in order to obtain statistically reliable classification results, the number of necessary training samples increases exponentially as the number of spectral bands increases. However, in many situations, acquisition of the large number of training samples for these high-dimensional datasets may not be so easy. This problem can be overcome by using multiple classifiers. In this paper we compared the effectiveness of two approaches for creating multiple classifiers, feature selection and feature extraction. The methods are based on generating multiple feature subsets by running feature selection or feature extraction algorithm several times, each time for discrimination of one of the classes from the rest. A maximum likelihood classifier is applied on each of the obtained feature subsets and finally a combination scheme was used to combine the outputs of individual classifiers. Experimental results show the effectiveness of feature extraction algorithm for generating multiple classifiers.

• 전기학회논문지
• /
• 제61권5호
• /
• pp.757-762
• /
• 2012

In this paper, the multi feature extraction algorithm for estimation of wrist movements based on Electromyogram(EMG) is proposed. For the extraction of precise features from the EMG signals, the difference absolute mean value(DAMV), the mean absolute value(MAV), the root mean square(RMS) and the difference absolute standard deviation value(DASDV) to consider amplitude characteristic of EMG signals are used. We figure out a more accurate feature-set by combination of two features out of these, because of multi feature extraction algorithm is more precise than single feature method. Also, for the motion classification based on EMG, the linear discriminant analysis(LDA), the quadratic discriminant analysis(QDA) and k-nearest neighbor(k-NN) are used. We implemented a test targeting twenty adult male to identify the accuracy of EMG pattern classification of wrist movements such as up, down, right, left and rest. As a result of our study, the LDA, QDA and k-NN classification method using feature-set with MAV and DASDV showed respectively 87.59%, 89.06%, 91.75% accuracy.

• Journal of Electrical Engineering and Technology
• /
• 제13권6호
• /
• pp.2468-2478
• /
• 2018

We propose the Sparse Feature Convolutional Neural Network (SFCNN) to reduce the volume of convolutional neural networks (CNNs). Despite the superior classification performance of CNNs, their enormous network volume requires high computational cost and long processing time, making real-time applications such as online-training difficult. We propose an advanced network that reduces the volume of conventional CNNs by producing a region-based sparse feature map. To produce the sparse feature map, two complementary region-based value extraction methods, cluster max extraction and local value extraction, are proposed. Cluster max is selected as the main function based on experimental results. To evaluate SFCNN, we conduct an experiment with two conventional CNNs. The network trains 59 times faster and tests 81 times faster than the VGG network, with a 1.2% loss of accuracy in multi-class classification using the Caltech101 dataset. In vehicle classification using the GTI Vehicle Image Database, the network trains 88 times faster and tests 94 times faster than the conventional CNNs, with a 0.1% loss of accuracy.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2003년도 가을 학술발표논문집 Vol.30 No.2 (1)
• /
• pp.4-6
• /
• 2003

A holistic representation, such as sparse ceding or independent component analysis (ICA), was successfully applied to explain early auditory processing and sound classification. In contrast, Part-based representation is an alternative way of understanding object recognition in brain. In this paper. we employ the non-negative matrix factorization (NMF)［1］which learns parts-based representation for sound classification. Feature extraction methods from spectrogram using NMF are explained. Experimental results show that NMF-based features improve the performance of sound classification over ICA-based features.

• 대한원격탐사학회지
• /
• 제26권6호
• /
• pp.665-673
• /
• 2010

The role of remote sensing in phenological studies is increasingly regarded as a key in understanding large area seasonal phenomena. This paper describes the application of Moderate Resolution Imaging Spectroradiometer (MODIS) time series data for vegetation classification using seasonal variation patterns. The vegetation seasonal variation phase of Seoul and provinces in Korea was inferred using 8 day composite MODIS NDVI (Normalized Difference Vegetation Index) dataset of 2006. The seasonal vegetation classification approach is performed with reclassification of 4 categories as urban, crop land, broad-leaf and needle-leaf forest area. The BISE (Best Index Slope Extraction) filtering algorithm was applied for a smoothing processing of MODIS NDVI time series data and fuzzy classification method was used for vegetation classification. The overall accuracy of classification was 77.5% and the kappa coefficient was 0.61%, thus suggesting overall high classification accuracy.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.125-127
• /
• 2004

High-resolution satellite images offer abundance information of the earth surface for remote sensing applications. The information includes geometry, texture and attribute characteristic. The pixel-based image classification can't satisfy high-resolution satellite image's classification precision and produce large data redundancy. Object-oriented information extraction not only depends on spectrum character, but also use geometry and structure information. It can provide an accessible and truly revolutionary approach. Using Beijing Spot 5 high-resolution image and object-oriented classification with the eCognition software, we accomplish the cultures' precise classification. The test areas have five culture types including water, vegetation, road, building and bare lands. We use nearest neighbor classification and appraise the overall classification accuracy. The average of five species reaches 0.90. All of maximum is 1. The standard deviation is less than 0.11. The overall accuracy can reach $95.47\%.$ This method offers a new technology for high-resolution satellite images' available applications in remote sensing culture classification.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.525-528
• /
• 2009

Recently, image classification has been an important task in various fields. Generally, the performance of image classification is not good without the adjustment of image features. Therefore, it is desired that the way of automatic feature extraction. In this paper, we propose an image classification method which adjusts image features automatically. We assume that texture features are useful in image classification tasks because natural images are composed of several types of texture. Thus, the classification accuracy rate is improved by using distribution of texture features. We obtain texture features by calculating image features from a current considering pixel and its neighborhood pixels. And we calculate image features from distribution of textures feature. Those image features are adjusted to image classification tasks using Genetic Algorithm. We apply proposed method to classifying images into "head" or "non-head" and "male" or "female".

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 C
• /
• pp.1030-1032
• /
• 1998

In this paper, an efficient feature vector extraction method and MLP neural network are utilized to automatically detect and classify power quality disturbances, where the proposed classification procedure consists of the following three parts: i.e., (i) PQ disturbance detection using discrete wavelet transform. (ii) feature vector extraction from the detected disturbance. using several methods, such as FFT, DWT, Fisher's criterion. etc.. and (iii) classification of the corresponding type of each PQ disturbance by recognizing the pattern of the extracted feature vector. To demonstrate the performance and, applicability of the proposed classification algorithm. some test results obtained by analyzing 10-class PQ disturbances are also provided.