• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 춘계학술발표대회
• /
• pp.204-207
• /
• 2013

Music genre classification is an essential component for music information retrieval system. There are two important components to be considered for better genre classification, which are audio feature extraction and classifier. This paper incorporates two different kinds of features for genre classification, timbral texture and rhythmic content features. Timbral texture contains several spectral and Mel-frequency Cepstral Coefficient (MFCC) features. Before choosing a timbral feature we explore which feature contributes less significant role on genre discrimination. This facilitates the reduction of feature dimension. For the timbral features up to the 4-th order central moments and the covariance components of mutual features are considered to improve the overall classification result. For the rhythmic content the features extracted from beat histogram are selected. In the paper Extreme Learning Machine (ELM) with bagging is used as classifier for classifying the genres. Based on the proposed feature sets and classifier, experiment is performed with well-known datasets: GTZAN databases with ten different music genres, respectively. The proposed method acquires the better classification accuracy than the existing approaches.

• 대한원격탐사학회지
• /
• 제31권3호
• /
• pp.255-265
• /
• 2015

고해상도 위성영상은 실시간으로 정확한 지표 상태에 대한 정보를 수집할 수 있어 도심지 모니터링에 효율적인 수단으로 사용되고 있다. 고해상도 Synthetic Aperture Radar (SAR) 영상은 기상상태와 태양고도의 제약을 받지 않고 영상을 취득할 수 있는 장점을 가지기 때문에 최근 이들 데이터를 활용한 도심지 변화탐지 기술에 대한 관심이 증대되고 있다. 본 연구에서는 Gray-Level Co-Occurrence Matrix (GLCM)을 통한 텍스처 정보추출과 이들 특징 정보를 통합적으로 활용하는 새로운 텍스처 기반의 SAR 변화탐지 기술을 제안하였다. 제안기법의 효용성을 평가하기 위해 기존의 SAR 영상 변화탐지를 위해 많이 사용된 Non-Coherent Change Detection (NCCD) 기법과의 시각적/정량적 비교평가를 수행하였다. 실험결과 제안기법이 보다 높은 변화탐지 정확도를 보였으며 시각적으로도 우수한 결과를 도출하였다. 결과적으로 제안된 변화탐지 방법은 고해상도 SAR 위성영상을 이용한 도심지 변화정보 추출에 유용하게 적용될 수 있으리라 판단된다.

• 한국재난정보학회 논문집
• /
• 제15권3호
• /
• pp.427-439
• /
• 2019

연구목적: 다양한 목적으로 생성되는 무인비행체 기반의 공간정보를 서로 다른 SW로 생성하고, 정사영상 및 DSM의 위치정확도 분석과 3D mesh의 텍스처 매핑을 비교 분석하고자 하였다. 연구방법: 서로 다른 두 개의 SW를 이용하여 동일한 무인항공영상 데이터를 처리하고, 공간정보를 생성하였다. 생성된 공간정보 중 정사영상과 DSM은 수평위치 및 수직위치 오차의 RMSE를 계산함으로써 정량적 분석을 수행하고, 정성적 분석을 수행함으로써 무인항공사진측량 SW의 공간정보 생성 결과를 비교분석하고자 하였다. 연구결과: 각각의 SW로 생성된 정사영상 및 DSM의 위치정확도에서는 큰 차이가 없었으며, 3D mesh의 텍스쳐 매핑에서 차이를 보였다. 3D mesh의 생성에는 무인항공사진측량 SW가 영향을 미치는 것을 알 수 있었다. 결론: 무인비행체 기반의 공간분석을 위한 정사영상, DSM의 생성에는 SW에 따른 영향이 없는 것으로 나타났으나 3D 가시화를 목적으로 할 경우에는 SW에 따라 텍스처 매핑 결과가 다르게 나타나는 것을 알 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권3호
• /
• pp.1121-1139
• /
• 2015

In texture-plus-depth format, depth map compression is an important task. Different from normal texture images, depth maps have less texture information, while contain many homogeneous regions separated by sharp edges. This feature will be employed to form an efficient depth map coding scheme in this paper. Firstly, the histogram of the depth map will be analyzed to find an appropriate threshold that segments the depth map into the foreground and background regions, allowing the edge between these two kinds of regions to be obtained. Secondly, the two regions will be encoded through rate distortion optimization with a shape adaptive wavelet transform, while the edges are lossless encoded with JBIG2. Finally, a depth-updating algorithm based on the threshold and the depth range is applied to enhance the quality of the decoded depth maps. Experimental results demonstrate the effective performance on both the depth map quality and the synthesized view quality.

• International Journal of Control, Automation, and Systems
• /
• 제2권1호
• /
• pp.125-133
• /
• 2004

In this paper, we present a new method that combines the characteristics of edge in-formation and second-order neural networks for the classification of structural textures. The edges of a texture are extracted using an edge detection approach. From this edge information, classification features called second-order features are obtained. These features are fed into a second-order neural network for training and subsequent classification. It will be shown that the main disadvantage of using structural methods in texture classifications, namely, the difficulty of the extraction of texels, is overcome by the proposed method.

• 전자공학회논문지B
• /
• 제33B권4호
• /
• pp.141-147
• /
• 1996

In this paper an improved morphological algorithm for directional defect detection is proposed, where the defect is parallel to the texture image. The algorithm is based on obtaining the background image while removing the defect by comparing every directional morphological result with max or min except that of defect. The defect can of defect and the background image. For a computer simulation, it is shown that the proposed method has better performance than the conventional algorithm.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1990년도 하계학술대회 논문집
• /
• pp.542-545
• /
• 1990

Texture provides an important source of information about the local orientation of visible surfaces. In this study the 3D shape of a textured surface is recovered from its perspective projection image on the assumption that the texture is homogeneously distributed. To recover 3D structure, the distorting effects of the perspective projection must be distinguished from properties of the texture. In this study, paraperspective projection, approximation of perspective projection, has employed.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.2059-2064
• /
• 2004

Texture analysis is an important role for automatic visual insfection. This paper presents an application of wavelet extension and Gray level co-occurrence matrix (GLCM) for detection of defect encountered in textured images. Texture characteristic in low quality images is not to easy task to perform caused by noise, low frequency and small dimension. In order to solve this problem, we have developed a procedure called wavelet image extension. Wavelet extension procedure is used to determine the frequency bands carrying the most information about the texture by decomposing images into multiple frequency bands and to form an image approximation with higher resolution. Thus, wavelet extension procedure offers the ability to robust feature extraction in images. Then the features are extracted from the co-occurrence matrices computed from the sub-bands which performed by partitioning the texture image into sub-window. In the detection part, Mahalanobis distance classifier is used to decide whether the test image is defective or non defective.

• 자연과학논문집
• /
• 제5권2호
• /
• pp.33-38
• /
• 1992

텍스처럴 리전의 러프니스와 사람의 시각 시스템의 특성에 기초하여 세크멘테이션을 수행하는, 멀티미디어 텔레컨퍼런스를 위한 새로운 텍스처 세그멘테이션-베이스 영상 코우딩 기술을 제안한다. 세그멘테이션은, 텍스처의 영역이, 지각된 콘스탄트 인텐시티와 스무드 텍스처 및 러프 텍스처의 세가지 텍스처 클래스로 분류되도록 프랙탈 디멘전을 쓰레쉬호울딩하여 이루어진다. 각 세그먼트 바운더리와 각 텍스처 클래스를 위한 효과적인 코우딩 기술을 개발하여 높은 압축률과 좋은 영상 품질을 갖는 영상 코우딩 시스템을 달성하고, 이 기술의 코우딩 효율을 잘 확립된 기술 (디스크릿 코사인 트랜스폼(DCT) 영상 코우딩)의 코우딩 효율과 비교한다.

• 한국도로학회논문집
• /
• 제17권1호
• /
• pp.1-6
• /
• 2015

PURPOSES : Recently, attempts have been made to evaluate tire-pavement noise based on a measure of Mean Profile Depth (MPD). However, equivalent values of MPD appear to correspond to different levels of tire-pavement noise, which indicates that other factors such as texture wavelength need to be included to improve the accuracy of noise prediction. A single index to represent texture wavelength is proposed in this study. A consistent relationship between tire-pavement noise and texture wavelength on asphalt concrete pavement is observed. METHODS : Profile data and tire-pavement noise data were collected from a number of expressway sections in Korea. In addition, texture wavelength was defined by a Peak Number (PN), which was calculated using profile data. Statistical analysis was performed to find the relationship between the PN and tire-pavement noise. RESULTS : As a result of this study, a linear relationship between PN and tire-pavement noise is observed on asphalt concrete pavement. CONCLUSIONS : Tire-pavement noise on asphalt concrete pavement can be predicted from PN information.