• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권3호
• /
• pp.1700-1721
• /
• 2017

The problem of blocking artifacts is very common in block-based image and video compression, especially at very low bit rates. In this paper, we propose a post-processing method for JPEG-coded image deblocking via sparse representation and adaptive residual threshold. This method includes three steps. First, we obtain the dictionary by online dictionary learning and the compressed images. The dictionary is then modified by the histogram of oriented gradient (HOG) feature descriptor and K-means cluster. Second, an adaptive residual threshold for orthogonal matching pursuit (OMP) is proposed and used for sparse coding by combining blind image blocking assessment. At last, to take advantage of human visual system (HVS), the edge regions of the obtained deblocked image can be further modified by the edge regions of the compressed image. The experimental results show that our proposed method can keep the image more texture and edge information while reducing the image blocking artifacts.

• 복식
• /
• 제65권1호
• /
• pp.150-163
• /
• 2015

Due to desire for more variation from male consumers within the men's fashion market in Korea, there has been an ongoing development of departmentalization of fashion styles. The Generation-X man, in particular, is the most active member of our current day society, and will be the principal agent in the senior market from here on forth. Thus, this study categorized their preferred fashion styles, and will seek to analyze the behaviors related to the pursuit of clothing of the Generation-X man. The qualitative investigations of the Q-method as well as the quantitative investigation of the SPSS 12.0 were used in conjunction as the method of study. Additionally, images and types resulting from the preceding first-year study entitled "The Type and Characteristics of the Modern Men's Fashion Images" were utilized as part of the surveys. As a result of the Q-method, which was used to derive the preferred fashion styles of the Generation-X man, they were classified into three categories: the classic suit preferring 'conservative class type', the polished, comfortable style preferring 'modern sophisticated type', and the adventure and variety seeking 'uninhibited individualistic style'. After analyzing the factors which influence clothing preference behaviors of these men, a total of seven causes were drawn from the results, including: conservative indifference to fashion, others conscious pursuit of fashion, the aim to show off brand name products, high involvement in the aspect of design, pursuit of TPO, pursuit of self-image, and conformity to fashion. The elements that revealed differences in the behaviors in pursuing clothing within the preferred fashion style types of the Generation-X man included the conservative indifference to fashion, and others conscious pursuit of fashion, which therefore shows that rather than enjoying the fashion lifestyle, these men possess a more conservative disposition instead.

• 대한전자공학회논문지SP
• /
• 제39권2호
• /
• pp.11-21
• /
• 2002

비디오 데이터 부호화를 위한 여러 가지 방법들 중 matching pursuit을 이용한 비디오 부호화 방법은 저속 채널상에서 뛰어난 효율을 보이고 있으나, 기존의 블록 기반 변환 부호화 방법에 비하여 연산량이 월등히 많기 때문에 비디오 부호화에 적용하는 데는 어려운 점이 있다 본 논문에서는 matching pursuit의 전체 계산량 중 가장 큰 비중을 차지하는 내적 연산량을 줄이기 위해 matching pursuit의 내적연산에 사용되는 1차원 사전(Dictionary)을 구성하는 각각의 기본 신호들의 절대값이 대칭성을 가진다는 특성과, 크게 화질에 영향을 주지는 않지만 연산량을 줄이는 데는 도움을 줄 수 있도록 변형된 사전을 사용할 수 있다는 것, 그리고 주파수 특성을 이용하여 2차원 사전이 미리 분류될 수 있다는 사실을 이용한다. 실험결과에 나타난 바와 같이 제안하는 방법은 큰 화질 열화 없이, Neff가 제안한 사전의 분리성(Separability)을 이용한 기존의 고속 방법보다 내적 연산량에 소요되는 곱셈량을 약 1/8로 감소시키는 효과를 가져온다.

• 패션비즈니스
• /
• 제11권4호
• /
• pp.1-17
• /
• 2007

The purpose of this study was to provide for the useful fundamental data to enterprise which produces the natural-dyed clothing products by investigating with the holding conditions and pursuit of wearing images. The subjects were females aged 20 to 59, a questionnaire was developed by the researcher and distributed to 237 females. A sample of 223 females responded to the questionnaire. Data analyses were processed by SPSS WIN 10.0 Program; Frequency count and percentage, $X^2-test$, ANOVA and Duncan's multiple range test were used for statistical analysis. The results of this study were as follows: First, there were significant differences in holding items, period and private ownership according to age, any academic background and a monthly income. Second, the result by classification of the pursuit of wearing images could be identified four factors: factor 1) sexual and feminine image, factor 2) simple and common image, factor 3) comfortable and natural image and factor 4) dynamic image.

• 한국실내디자인학회논문집
• /
• 제16호
• /
• pp.175-181
• /
• 1998

The purpose of this study was to analyze the characteristics of expression and formal principle of universalism in Architectural Composition. Theorical category is to find universal system with the connection between idea of society and tradition in compositional frame the results were as follows : First it is the pursuit of divine. Through Middle Age and Renaissance universalism of principles in Architectural Composition is appeared a numerical order and human proportion with applying of cosmology. Second it is the pursuit of schema. With the simplicity of formal image it represented to the geometrical form for its clearness. Third it is the pursuit of typology. As to play a role of decisive factor in formal construction type represented the model with abstraction of shape.

• 한국위성정보통신학회논문지
• /
• 제8권4호
• /
• pp.130-134
• /
• 2013

본 논문에서는 3D 방송의 기본적인 원리를 설명하고 3D 방송을 CS 기술을 적용하여 데이터 용량을 줄이는 방식을 제안한다. 샘플링 이론과 CS 기술의 차이점을 설명하고 개념과 동작원리를 설명한다. 최근 제안된 CS 센싱의 복원 알고리즘인 AMP(Approximate Message Passing)와 CoSaMP(Compressive Sampling Matched Pursuit)를 소개하고 이를 이용하여 이미지 데이터를 압축 복원하여 비교한다. 두 알고리즘의 계산시간을 비교하여 낮은 복잡도를 갖는 알고리즘을 판단한다.

• 한국위성정보통신학회논문지
• /
• 제10권3호
• /
• pp.57-61
• /
• 2015

본 논문에서는 3D 방송의 기본적인 원리를 설명하고 실감영상 CS 기술을 적용하여 데이터 용량을 줄이는 방식을 제안한다. 샘플링 이론과 CS 기술의 차이점을 설명하고 개념과 동작원리를 설명한다. 압축 센싱의 복원 알고리즘인 SS-CoSaMP(Single-Space Compressive Sampling Matched Pursuit) 와 AMP(Approximate Message Passing)를 소개하고 이를 이용하여 이미지 데이터를 압축 복원하여 비교한다. 계산시간을 비교하여 낮은 복잡도를 갖는 알고리즘을 판단한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -1
• /
• pp.278-281
• /
• 2000

Matching pursuit algorithm is a signal expansion technique whose efficiency for motion compensated residual image has already been demonstrated in the MPEG-4 framework. However, one of the practical concerns related to applying matching pursuit algorithm to real-time scalable video coding is its massive computation required for finding dictionary elements. In this respective, this paper proposes a fast algorithm, which is composed of three sub-methods. The first method utilizes the property of symmetry in 1-D dictionary element and the second uses mathematical elimination of inner product calculation in advance, and the last one uses frequency property of 2-D dictionary. Experimental results show that our algorithm needs about 30% computational load compared to the conventional fast algorithm using separable property of 2-D gabor dictionary with negligible quality degradation.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1343-1358
• /
• 2020

In the stagewise arithmetic orthogonal matching pursuit algorithm, the weak threshold used in sparsity estimation is determined via maximum iterations. Different maximum iterations correspond to different thresholds and affect the performance of the algorithm. To solve this problem, we propose an improved variable weak threshold based on the stagewise arithmetic orthogonal matching pursuit algorithm. Our proposed algorithm uses the residual error value to control the weak threshold. When the residual value decreases, the threshold value continuously increases, so that the atoms contained in the atomic set are closer to the real sparsity value, making it possible to improve the reconstruction accuracy. In addition, we improved the generalized Jaccard coefficient in order to replace the inner product method that is used in the stagewise arithmetic orthogonal matching pursuit algorithm. Our proposed algorithm uses the covariance to replace the joint expectation for two variables based on the generalized Jaccard coefficient. The improved generalized Jaccard coefficient can be used to generate a more accurate calculation of the correlation between the measurement matrixes. In addition, the residual is more accurate, which can reduce the possibility of selecting the wrong atoms. We demonstrate using simulations that the proposed algorithm produces a better reconstruction result in the reconstruction of a one-dimensional signal and two-dimensional image signal.

• 통상정보연구
• /
• 제8권4호
• /
• pp.323-341
• /
• 2006

IThis research meets with empirical results in pursuit of aim as below mentioned. Firstly, it gets a line on two-way effects which have an effect on both (the country image and corporate image) by using the corporate image for the study of the country image. After making an analysis of the empirical test, found out that the corporate image has influence upon the country image significantly. Also found out that the country image has an effect on the corporate image powerfully. Therefore, it effects an inspection of evidence that the country image and corporate image have significantly positive concern, each other. Secondly, it is offering the way to use the culture marketing as grasping the mediating effects, which culture difference has influence upon the country image and the corporate image. The mediating effects show that the country image has influence on the corporate image more as culture difference is bigger.