• 대한전자공학회논문지SP
• /
• 제44권1호
• /
• pp.10-16
• /
• 2007

본 논문에서는 색상의 공간적인 상관관계와 질감 모멘트를 이용한 내용기반 영상 검색 기법을 제안한다. 이를 위해, 색상의 공간적인 상관관계를 표현하는 새로운 색상 기술자를 제안하고, 또한 제안된 색상 기술자와 국부적인 푸리에 변환에 기반한 질감 특성을 결합한 영상 검색 방법을 제안한다. 일반적으로 색상의 공간적인 상관관계를 표현하기 위해서 컬러 코렐로그램(color correlogram)이 사용되고 있다. 하지만 컬러 코렐로그램은 중심화소에 따른 이웃한 화소들의 색상 분포를 확률적으로 잘 나타내는 장점이 있지만, 색상의 구조적인 정보를 표현하지 못하는 단점이 있다. 그러므로 본 논문에서는 색상의 분포와 구조적인 정보를 표시할 수 있는 새로운 색상 기술자를 제안한다. 제안하는 새로운 색상 기술자는 중심 화소와 이웃 화소들과의 색상 거리를 계산한 후 최소 거리의 색상과 최대 거리의 색상을 추출한 후 최소-최대 색상 쌍이 이루는 각에 대한 각각의 빈도수를 계산한다. 그런 다음, 각각의 이루는 각에 대해서 최소 거리 색상에 대한 최대 거리 색상들의 평균값과 분산값으로 구성된 새로운 기술자(min-max color correlation descriptor, MMCCD)를 생성한다. 제안한 색상 기술자를 이용하여 검색한 결과는 기존 방법들과 비교했을 경우 정확률에서 최소 5.2%에서 최대 13.21% 향상된 검색 결과를 확인할 수 있었다. 또한, 국부적인 푸리에 변환에 기반한 질감 기술자를 새로운 색상 기술자와 결합하여 특징 벡터의 크기를 절반으로 줄이면서도 새로운 색상 기술자만을 사용할 경우와 비교하여 향상된 검색 결과를 확인할 수 있었다.

• 한국디자인학회:학술대회논문집
• /
• 한국디자인학회 2002년도 봄 학술발표회 논문집
• /
• pp.110-111
• /
• 2002

• 방송공학회논문지
• /
• 제18권3호
• /
• pp.372-379
• /
• 2013

본 논문에서는 LBP와 HSV 컬러 히스토그램을 이용한 내용 기반 영상 검색 방법을 제안한다. 영상 검색 시스템에서는 텍스트가 아닌 사용자가 원하는 특정한 객체를 포함하는 영상을 질의로 입력하여 원하는 영상을 검색한다. 대부분의 연구에서는 색상, 질감, 모양 등과 같은 전역 특징 값을 이용하여 영상을 검색한다. 이러한 전역 특징 값들은 하늘이나 바닥과 같은 배경이 큰 부분을 차지하는 영상에서는 특징 값의 대부분이 배경에서 추출되어 영상 검색의 성능 저하를 초래한다. 이러한 문제를 해결하기 위해, 컬러를 이용하여 영상의 배경을 고속으로 검출하고 배경의 영향을 줄여 관심 객체의 특징을 강조한다. 제안된 방법에서는 특징 값으로 HSV 컬러 히스토그램과 Local Binary Patterns을 사용한다. 또한, 색의 경계 부분의 패턴을 추출하기 위해 양자화 된 Hue 채널에서 Local Binary Patterns을 추출한다. 제안된 알고리즘의 성능 검증하기 위해, Corel 1000 database를 이용하여 실험한 결과 82% 이상의 높은 검색 정확도를 나타내었다.

• 반도체디스플레이기술학회지
• /
• 제12권4호
• /
• pp.33-38
• /
• 2013

Image retrieval is one of the most exciting and fastest growing research fields in the area of multimedia technology. As the amount of digital contents continues to grow users are experiencing increasing difficulty in finding specific images in their image libraries. This paper proposes an efficient image descriptor which uses a local color and texture in the non-overlapped block images. To evaluate the performance of the proposed method, we assessed the retrieval efficiency in terms of ANMRR with common image dataset. The experimental trials revealed that the proposed algorithm exhibited a significant improvement in ANMRR, compared to Dominant Color Descriptor and Edge Histogram Descriptor.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권2호
• /
• pp.116-120
• /
• 2006

This paper discusses an approach for detecting a new edge in color images. The color image is to be represented by a vector field, and the color image edges are detected as differences in the local vector statistics. This method is based on the calculation for the vector angle between two adjacent pixels. Unlike Euclidean distance in RGB space, the vector angle distinguishes the differences in chromaticity, independent of luminance or intensity. The proposed approach can easily accommodate concepts, such as variable template edge detection, as well as the latest developments in vector order statistics for color image processing. In this paper, it is used not a conventional fixed template operator but a variable template operator The variable template is implemented and experimental results for digital color images are included.

• 한국통신학회논문지
• /
• 제21권4호
• /
• pp.848-854
• /
• 1996

Many image display devices allow only a limited number of colors to be simultaneously displayed. in disphaying of natural color image using color palette, it is necessary to construct an optimal color palette and the optimal mapping of each pixed of the original image to a color from the palette. In this paper, we proposed the clustering algorithm using local region block centered one color cluster in the prequantized 3-D histogram. Cluster pairs which have the least distortion error are merged by considering distortion measure. The clustering process is continued until to obtain the desired number of colors. The same as the clustering process, original color value. The proposed algorithm incroporated with a spatial activity weighting value which is reflected sensitivity of HVS quantization errors in smoothing region. This method produces high quality display images and considerably reduces computation time.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 IWAIT
• /
• pp.59-62
• /
• 2009

In general, as a dynamic range of digital still camera is narrower than a real scene‘s, it is hard to represent the shadow region of scene. Thus, multi-scaled retinex algorithm is used to improve detail and local contrast of the shadow region in an image by dividing the image by its local average images through Gaussian filtering. However, if the chromatic distribution of the original image is not uniform and dominated by a certain chromaticity, the chromaticity of the local average image depends on the dominant chromaticity of original image, thereby the colors of the resulting image are shifted to a complement color to the dominant chromaticity. In this paper, a modified multi-scaled retinex method to reduce the influence of the dominant chromaticity is proposed. In multi-scaled retinex process, the local average images obtained by Gaussian filtering are divided by the average chromaticity values of the original image in order to reduce the influence of dominant chromaticity. Next, the chromaticity of illuminant is estimated in highlight region and the local average images are corrected by the estimated chromaticity of illuminant. In experiment, results show that the proposed method improved the local contrast and detail without color distortion.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2004년도 추계학술발표논문집(상)
• /
• pp.891-894
• /
• 2004

This paper proposes an improved image segmentation algorithm by the watershed algorithm based on the local adaptive threshold on local minima search and the fixing threshold on label allocation. The previous watershed algorithm generates the problem of over-segmentation. The over-segmentation makes the boundary in the inaccuracy region by occurring around the object. In order to solve those problems we quantize the input color image by the vector quantization, remove noise and find the gradient image. We sorted local minima applying the local adaptive threshold on local minima search of the input color image. The simulation results show that the proposed algorithm controls over-segmentation and makes the fine boundary around segmented region applying the fixing threshold based on sorted local minima on label allocation.

• 한국조경학회지
• /
• 제34권5호
• /
• pp.24-31
• /
• 2006

The tourism sites and attractions of South Korea in many ways have little specialties in their image due to the local development plan's uniformed way of designing and improving landscape. The lack of specialties in tourist sites and attractions have caused displeasure from the local residents, as the sites don't characterize the locals as attractively and appealingly as is the potential. There have been no research or studies on the scenic effect on tourism or resort development thus producing an urgent call for local authorities to develop planned landscapes of local sites. This study compares Bugok Onchon (hot spring), whose image hardly differentiates itself from the others, with Kinosaki Onsen (hot spring). Bugok Hot Spring, which is the case study of this report, has recorded a steady decline of visitors due to a result of uniformed development planning. In the case of Kinosaki Hot Spring, scenery development, however, has made a breakthrough in tourist increase despite its no-so-easily-accessible location. The study assumes that scenery effects changes in promoting local tourism, thus analyzing and comparing the two hot springs to unearth critical factors in tourist site development, as well as viewing the present state of Bugok Hot Spring for further study. Furthermore, the study provides tourist site developers with a guideline of the two comparative Hot Spring cases. Investigations and analyses are mainly focused on colors, which are important factors in making underlying images of tourist sites, and the comparison of Bugok Hot Spring with Kinosaki Hot Suing. Bugok Hot Spring shows the influences of accent colors as well as a variety of color combinations and similarities of color tones. Kinosaki Hot Spring shows a combination of naturally-generated colors its own scenic beauty by trimming the landscape. Through the comparative study of the two hot springs, Bugok (boulevard) uncovers a typical case of Korean local landscape planning, even with the well-known tourist attraction 'Bugok-Hawaii', and calls upon a new, serious landscape-improvement plan to increase visitors.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.5197-5218
• /
• 2019

Large-scale retrieval algorithm is problem for visual analyses applications, along its research track. In this paper, we propose a high-efficiency region division-based image retrieve approaches, which fuse low-level local color histogram feature and texture feature. A novel image region division is proposed to roughly mimic the location distribution of image color and deal with the color histogram failing to describe spatial information. Furthermore, for optimizing our region division retrieval method, an image descriptor combining local color histogram and Gabor texture features with reduced feature dimensions are developed. Moreover, we propose an extended Canberra distance method for images similarity measure to increase the fault-tolerant ability of the whole large-scale image retrieval. Extensive experimental results on several benchmark image retrieval databases validate the superiority of the proposed approaches over many recently proposed color-histogram-based and texture-feature-based algorithms.