• 방송공학회논문지
• /
• 제10권3호
• /
• pp.383-391
• /
• 2005

본 논문은 블록DCT(Discrete Cosine Transform) 기반의 영상 압축 과정에서 발생하는 블록효과(block artifact)를 제거하기 위해 ALM(Alvarez, Lions, and Morel) 확산 모델에 기반을 둔 새로운 이방성 확산(anisotropic diffusion)을 제안한다. 등방성 확산은 평탄 영역에 나타나는 블록 경계를 제거하는 역할을 하는 반면, 이방성 확산은 윤곽선 영역이나 텍스쳐 영역을 보존하는 역할을 하기 때문에, 제안된 확산 모델은 블록 효과를 제거하면서 윤곽선(edge)을 보존하기 위해 등방성 확산(isotropic diffusion)과 이방성 확산의 비율을 제어하는 확산비율 조절 매개 변수(RCP : rate control parameter)가 제안 되었다. 또한, 텍스쳐 영역의 과도한 평탄화를 막기 위해 속도 매개 변수(SAP : speed control parameter)를 고안하였으며, 이는 텍스쳐 영역의 확산 속도를 감소시기는 역할을 한다.

• 한국토양비료학회지
• /
• 제45권2호
• /
• pp.306-311
• /
• 2012

1. 우리나라 남부를 17개 지역으로 구분하여 최근 30년간의 기상자료 분석에 의한 5월~10월의 일평균 PET는 $2.75mm\;day^{-1}$ 이었다. 2. 노지재배 고추의 우리나라 남부 17개 지역별, 3개 토성 및 16개 순별, 총 816경우의 재배여건에 적합한 물 절약형 적정 관개간격 및 1회관개량을 산정하였다.

• 한국재료학회지
• /
• 제23권1호
• /
• pp.41-46
• /
• 2013

The microstructural evolution of AA1050/AA6061 complex aluminum alloy, which is fabricated using an accumulative roll-bonding (ARB) process, with the proceeding of ARB, was investigated by electron back scatter diffraction (EBSD) analysis. The specimen after one cycle exhibited a deformed structure in which the grains were elongated to the rolling direction for all regions in the thickness direction. With the proceeding of the ARB, the grain became finer; the average grain size of the as received material was $45{\mu}m$; however, it became $6.3{\mu}m$ after one cycle, $1.5{\mu}m$ after three cycles, and $0.95{\mu}m$ after five cycles. The deviation of the grain size distribution of the ARB processed specimens decreased with increasing number of ARB cycles. The volume fraction of the high angle grain boundary also increased with the number of ARB cycles; it was 43.7% after one cycle, 62.7% after three cycles, and 65.6% after five cycles. On the other hand, the texture development was different depending on the regions and the materials. A shear texture component {001}<110> mainly developed in the surface region, while the rolling texture components {011}<211> and {112}<111> developed in the other regions. The difference of the texture between AA1050 and AA6061 was most obvious in the surface region; {001}<110> component mainly developed in AA1050 and {111}<110> component in AA6061.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.436-442
• /
• 2017

A novel method of Skin lesion segmentation based on the combination of Texture and Neural Network is proposed in this paper. This paper combines the textures of different pixels in the skin images in order to increase the performance of lesion segmentation. For segmenting skin lesions, a two-step process is done. First, automatic border detection is performed to separate the lesion from the background skin. This begins by identifying the features that represent the lesion border clearly by the process of Texture analysis. In the second step, the obtained features are given as input towards the Recurrent Echo state neural networks in order to obtain the segmented skin lesion region. The proposed algorithm is trained and tested for 862 skin lesion images in order to evaluate the accuracy of segmentation. Overall accuracy of the proposed method is compared with existing algorithms. An average accuracy of 98.8% for segmenting skin lesion images has been obtained.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1996년도 Proceedings International Workshop on New Video Media Technology
• /
• pp.29-34
• /
• 1996

This paper proposes a new concept in video called Graphical Video. Graphical Video is a content-based and scalable video representation. A video consists of several elements such as moving images, still images, graphics, characters and charts. All of these elements can be represented graphically except moving images. It is desirable to transform these moving images graphical elements so that they can be treated in the same way as other graphical elements. To achieve this, we propose a new graphical representation of moving images using spatio-temporal clusters, which consist of texture and contours. The texture is described by three-dimensional fractal coefficients, while the contours are described by polygons. We propose a method that gives domain pool location and size as a means to describe cluster texture within or near a region of clusters. Results of an experiment on texture quality confirm that the method provides sufficiently high SNR as compared to that in the original three-dimensional fractal approximation.

• 대한전자공학회논문지
• /
• 제24권5호
• /
• pp.914-922
• /
• 1987

An image coding technique based on a segmentation, which utilizes a simplified description of regions composing an image, is investigated in this paper. The proposed coding technique consists of 3 stages: segmentation, contour coding. In this paper, emphasis was given to texture coding in order to improve a quality of an image. Split-and-merge method was employed for a segmentation. In the texture coding, a linear predictive coding(LPC), along with approximation technique based on a two-dimensional polynomial function was used to encode texture components. Depending on a size of region and a mean square error between an original and a reconstructed image, appropriate texture coding techniques were determined. A computer simulation on natural images indicates that an acceptable image quality at a compression ratio as high as 15-25 could be obtained. In comparison with a discrete cosine transform coding technique, which is the most typical coding technique in the first-generation coding, the proposed scheme leads to a better quality at compression ratio higher than 15-20.

• 대한전자공학회논문지SP
• /
• 제41권5호
• /
• pp.165-173
• /
• 2004

수리형태학을 이용한 영상분할의 분할 성능은 우수하지만 너무 많은 영역으로 분할되는 경향이 있는데, 후처리 과정을 사용하지 않고 이러한 문제를 해결하기 위해서는 마커 추출에 사용되는 구조요소의 크기를 증가시켜야 한다. 그러나 구조요소의 크기가 너무 크면 영역의 경계를 제대로 분리해낼 수 없기 때문에 본 논문에서는 영상분할의 성능 개선을 위해 수리형태학적 구조요소를 선택적으로 적용하였다. 이를 위해 평균국부분산과 영상의 기울기를 이용하여 입력 영상을 질감 영역, 에지 영역, 단순 영역으로 분류하였다. 그리고 각 영역별로 구조요소의 크기를 선택적으로 적용하여 영상이 과분할 되는 원인을 제거하였다. 실험 결과, 화소의 밝기 값이 비슷한 영역에 대해서도 영상이 잘 분할됨을 확인하였고 기존의 방법보다 질감 영역 및 에지영역을 정확하게 찾아냄을 확인할 수 있었다.

• 한국정밀공학회지
• /
• 제21권10호
• /
• pp.162-169
• /
• 2004

High temperature uniaxial compression tests in the alpha single phase region were carried out on the Ti -43mo1%Al intermetallic compound, in order to obtain oriented lamellar microstructure. The compression deformation temperatures and strain rates are from 1573k to 1623k and 1.0x10$^{-4}$ s to 5.0x10$^{-3}$ s, respectively. Fully lamellar microstructure was observed after the uniaxial compression deformation in a single phase region followed by cooling to room temperature. Lamellar colony diameter depended on strain rates and test temperatures. The diameter varied between 8601m and 300fm. Stress-strain curve showed a work softening and the size of lamellar colony diameter varied depending on peak stresses. This shows the occurrence of dynamic recrystallization. Texture measurements after the uniaxial compression deformation, showed the development of fiber during dynamic recrystallization. It is seen that the area for the maximum pole density existed in 35 degrees away from the compression plane. The texture sharpens with a decrease in strain rate

• 한국멀티미디어학회논문지
• /
• 제5권5호
• /
• pp.505-514
• /
• 2002

본 논문에서는 내용기반 영상 분류를 위한 방법론으로써 신경망을 이용한 방법을 제안한다. 분류 대상 영상은 인터넷상의 다양한 영상들 중에서 전경과 배경의 구분이 있는 객체 영상이다. 전처리 과정에서 영역 분할을 이용하여 영상 내에서 배경을 제거하고 객체 영역을 추출한다. 분류를 위한 특징은 웨이블릿 변환 후 푸출된 형태 특징과 질감특징을 이용한다 추출된 특징 값들을 이용하여 영상들에 대한 학습패턴을 생성하고 신경망 분류기를 구성 한다. 신경망의 학습 알고리즘은 역전파 알고리즘을 사용한다. 가장 효과적인 질감특징을 선 택 하기 위한 실험에서는 대각 모멘트가 가장 높은 분류률을 보여 주었다. 배경을 제거 하고 대각 모멘트를 특징으로 사용하여 실험하였을 때, 30종류에서 각 10개씩 총 300개의 학습 데이터와300개의 테스트 데이터에 대하여 각각 72.3%와 67%의 정분류률을 보였다.

• 한국멀티미디어학회논문지
• /
• 제20권1호
• /
• pp.43-50
• /
• 2017

According to living environment, the number of deaths due to thyroid diseases increased. In this paper, we proposed an algorithm for recognizing a thyroid detection using texture analysis based on shape, gray level co-occurrence matrix and gray level run length matrix. First of all, we segmented the region of interest (ROI) using active contour model algorithm. Then, we applied a total of 18 features (5 first order descriptors, 10 Gray level co-occurrence matrix features(GLCM), 2 Gray level run length matrix features and shape feature) to each thyroid region of interest. The extracted features are used as statistical analysis. Our results show that first order statistics (Skewness, Entropy, Energy, Smoothness), GLCM (Correlation, Contrast, Energy, Entropy, Difference variance, Difference Entropy, Homogeneity, Maximum Probability, Sum average, Sum entropy), GLRLM features and shape feature helped to distinguish thyroid benign and malignant. This algorithm will be helpful to diagnose of thyroid nodule on ultrasound images.