• 정보처리학회논문지B
• /
• 제11B권4호
• /
• pp.421-428
• /
• 2004

MPEG극 텍스쳐 서술자에는 균등 질감(Homogeneous Texture), 경계 히스토그램(Edge Histogram), 텍스쳐 브라우징(Texture Browsing) 서술자가 있다. 본 논문에서는 이들 텍스쳐 서술자를 이용하여 홍채 인식에 대한 성능을 비교 분석한다. 전처리 과정을 통해 추출된 560장의 흥채 영상을 이용하여, 세 서술자에 대한 각 계수에 대한 군집화 효율성 비교와 에러 분포 비교를 통해 서로 다른 홍채 그룹에 대한 변별 능력을 비교한다. 실험 결과를 통해 세 서술자 중 균등 질감 서술자가 홍채 패턴을 인식하는 데 있어서 가장 효율적인 서술자로 나타났다. 그러나, 실험결과는 기존의 홍채 인식 방법에 비해, MPEG-7 텍스쳐 서술자를 이용한 홍채 인식에 인식 성능 향상을 위한 노력이 필요함을 알 수 있다.

• 한국게임학회 논문지
• /
• 제8권2호
• /
• pp.57-68
• /
• 2008

텍스처 매핑(texture mapping)은 실감 있는 영상을 만들기 위해 3차원 그래픽스 칩에서 사용되는 기술이다. 이 방식 중 이중선형 필터링 모드(bilinear filtering mode)에서는 1개의 픽셀(pixel)을 처리하기 위해 4개의 텍셀(texture element: texel)에 접근이 요구된다. 본 논문에서는 텍스처의 접근패턴을 분석하여 동시에 4개의 텍셀을 접근할 수 있는 고성능 텍스처 캐시의 구조를 제시하였다. 3차원 게임인 퀘이크3(Quake 3)와 언리얼 토너먼트 2004(Unreal Tournament 2004)의 텍스처 접근 추출파일을 이용한 시뮬레이션 결과로 성능평가를 하였으며, 제시한 텍스처 캐시의 구조는 물리적인 크기가 8KBytes 이하인 경우 콜은 성능을 갖게 됨을 분석하였다.

• 전자공학회논문지B
• /
• 제31B권12호
• /
• pp.51-58
• /
• 1994

Mathematical morphology based on set theory is easy to be implemented in parallel and can be applied to various fields in image analysis. Particularly mophological pattern spectrum can detect critical scales in an image object and quantify various aspects of the shape-size content. In this paper, texture classification using pattern spectrum based on morphological subband decomposition is porposed. The low-low band extracts pattern spectrum features, and the high-low, low-high, and high-high bands extrack the structural information. This approach has the advantages of efficient information extraction, less time-consuming, high accuacy, less computation, and parallel implementation.

• 반도체디스플레이기술학회지
• /
• 제8권3호
• /
• pp.39-44
• /
• 2009

Local Binary Pattern (LBP) is becoming a popular tool for various machine vision applications such as face recognition, classification and background subtraction. In this paper, we propose a new extension of LBP, called the Diagonal LBP (DLBP), to handle the image-based gender classification problem arise in interactive display systems. Instead of comparing neighbor pixels with the center pixel, DLBP generates codes by comparing a neighbor pixel with the diagonal pixel (the neighbor pixel in the opposite side). It can reduce by half the code length of LBP and consequently, can improve the computation complexity. The Support Vector Machine is utilized as the gender classifier, and the texture profile based on DLBP is adopted as the feature vector. Experimental results revealed that our approach based on the diagonal LPB is very efficient and can be utilized in various real-time pattern classification applications.

• 반도체디스플레이기술학회지
• /
• 제8권2호
• /
• pp.23-29
• /
• 2009

To increase the data capacity of one-dimensional symbology, 2D barcodes have been proposed a decade ago. In this paper, a new 2D barcode detection algorithm based on Local Binary Pattern is presented. To locate 2D barcode symbols, a texture analysis scheme based on the Local Binary Pattern is adopted, and a gray-scale projection with sub-pixel operation is utilized to separate the symbol precisely from the input image. Finally, the segmented symbol is normalized using the inverse perspective transformation for the decoding process. The proposed method ensures high performances under various lighting/printing conditions and strong perspective deformations. Experiments show that our method is very robust and efficient in detecting the symbol area for the various types of 2D barcodes.

• 복식
• /
• 제18권
• /
• pp.269-281
• /
• 1992

The purposes of this study were to 1) classify the contents of clothing image preferences, 2) find out the relationship among personal values, preferences for clothing image and clothing design, and 3) investigate the relationship between clothing image preferences and clothing design preferences, Questionnaire was comprised of three section. The clothing image preference measure was included 36 bipolar adjectives of 7-point scales. Clothing design preferences measure was included the items of patterns, colors, and textures. 'Survey of Personal Values' by Eung-Un Hwang and Kyung -hye Lee was used for measurement of 6 values : practical mindedness ; achievement ; variety ; decisiveness; orderliness; and goal orientation. Samples were 288 college women. The data were analyzed using pearson's correlation coefficient and factor analysis. The results of the study were the following. 1. Four segments of clothing image preferences derived by factor analysis : F. 1 'progressive-conservative' ; F.2. 'casual-formal'; F.3 'plain-splendid'; F.4 'masculine-feminine'. 2. In relation between personal values and clothing image preferences, 1) achievement was positively related to the preference of progressive image 2) variety was positively related to the preferences of progressive and masculine image, and 3) goal orientation was negatively related to the preferences of the progressive and masculine image, and positively related to plain image. 3. In relation between personal values and clothing design preferences, 1) practical mindedness was positively related to the preference of black, 2) achievement was positively related to the preferences of blue and such realistic pattern as floral, 3) variety was positively related to the preferences of geometric or abstract patterns and thick or transparent texture, and 4) orderliness was negatively related to the preferences of abstract pattern. 4. In relation between clothing image preferences and clothing design preferences, 1) progressive image was positively related to abstract pattern, red, blue, and black, 2) casual image was positively related to geometric pattern, green, blue, and negatively related to red and soft rexture, 3) plain image was negatively related to lustered and transparent texture, abstract pattern, red, and black, and 4) masculine image was negatively related to lustered, thin, soft, and transparent texture, floral and dotted patterns, red, orange, and yellow.

• 한국통신학회논문지
• /
• 제32권5C호
• /
• pp.496-512
• /
• 2007

본 논문에서는 엔트로피 복호화 과정을 부분적으로 수행하여 특징 벡터를 구성하는 새로운 JPEG-2000 압축 영상 검색 시스템을 제안한다. 제안하는 방법은 JPEG-2000 엔트로피 부호화 과정을 통해 발생하는 다양한 문맥 정보를 이용한다. 엔트로피 부호화 기술은 주위 인접한 웨이블릿 계수들의 부호 및 중요 상태 계수의 구조적인 패턴을 분석하여 세 가지의 부호화 패스 및 네 가지의 부호화 기술을 통해 총 19가지의 문맥 정보를 발생한다. 문맥 정보는 산술 부호화 과정에서 부호화 하는 심벌의 확률을 예측하기 위한 모델을 제공한다. 그리고 문맥 정보는 영상의 국부적인 특징을 서술 할 수 있기 때문에 다양한 패턴 특성을 나타내는 질감 영상을 효율적으로 정의할 수 있다. 또한 제안하는 알고리즘은 JPEG-2000 압축 영상에서 복호화 과정을 부분적으로 수행하기 때문에 영상 검색을 수행하기 위한 검색 시간에서 뛰어난 성능을 나타낼 수 있다. 실험을 위해 MIT VisTex 질감 영상을 이용하여 다양한 왜곡 영상 및 유사 영상 데이터베이스를 구성하였으며 기존 검색 알고리즘을 구현하여 제안하는 검색 시스템과 비교 및 평가한다. 본 논문에서 제안하는 알고리즘이 기존 검색 방법보다 검색 성능에서 뛰어날 뿐만 아니라 검색 시간에서도 많은 이득을 얻을 수 있다.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.402-410
• /
• 2017

For many years, researchers in face description area have been representing and recognizing faces based on different methods that include subspace discriminant analysis, statistical learning and non-statistics based approach etc. But still automatic face recognition remains an interesting but challenging problem. This paper presents a novel and efficient face image representation method based on Optimized Local Ternary Pattern (OLTP) texture features. The face image is divided into several regions from which the OLTP texture feature distributions are extracted and concatenated into a feature vector that can act as face descriptor. The recognition is performed using nearest neighbor classification method with Chi-square distance as a similarity measure. Extensive experimental results on Yale B, ORL and AR face databases show that OLTP consistently performs much better than other well recognized texture models for face recognition.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.8-12
• /
• 1999

Since the advent of high resolution satellite image, possibilities of applying various human interpretation mechanism to these images have increased. Also many studies about these possibilities in many fields such as computer vision, pattern recognition, artificial intellegence and remote sensing have been done. In this field of these studies, texture is defined as a kind of quantity related to spatial distribution of brightness and tone and also plays an important role for interpretation of images. Especially, methods of obtaining texture by statistical model have been studied intensively. Among these methods, texture measurement method based on cooccurrence matrix is highly estimated because it is easy to calculate texture features compared with other methods. In addition, these results in high classification accuracy when this is applied to satellite images and aerial photos. But in the existing studies using cooccurrence matrix, features have been chosen arbitrarily without considering feature variation. And not enough studies have been implemented for appropriate resolution selection in which cooccurrence matrix can extract texture. Therefore, this study reviews the concept of cooccurrence matrix as a texture measurement method, evaluates usefulness of several features obtained from cooccurrence matrix, and proposes appropriate resolution by investigating variance trend of several features.

• 한국생활과학회지
• /
• 제20권2호
• /
• pp.413-426
• /
• 2011

This research was designed to compare the subjective evaluation of texture image and preference according to fiber blending ratio of men's suit fabrics. 110 subjects evaluated the texture image and preference of various fabrics. For statistical analysis, factor analysis, MDS, pearson correlation and ANOVA were used. The results were as follows: Sensory image factors of suit fabrics were 'smoothness', 'bulkiness', 'stiffness', 'elasticity', 'moistness' and 'weight sensation'. Sensibility image factors were 'classic', 'practical', 'characteristic' and 'sophisticated'. 'Bulkiness' and 'elasticity' sensory images showed high correlations with sensibility images. Fabrics with high wool blending ratio showed as 'classic' and 'sophisticated', 'bulkiness' and 'elasticity' texture images and fabrics with low wool blending ratio showed texture images of 'characteristic', 'surface character', 'stiffness', 'moistness' and 'weight sensation'. Wool fiber blending ratio affected on the purchase preference and tactile preference. Using regression analysis, it was shown that sensibility images had more of an effect on preference than sensory images. The thickness and pattern type showed positive effects and fiber blending ratio showed negative effects on the preference.