• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.11
• /
• pp.529-536
• /
• 2015

When rendering both three-dimensional objects and photo images together, the non-photorealistic rendering results are in visual discord since the two contents have their own independent color distributions. This paper proposes a non-photorealistic rendering technique which renders both three-dimensional objects and photo images such as cartoons and sketches. The proposed technique computes the color distribution property of the photo images and reduces the number of colors of both photo images and 3D objects. NPR is performed based on the reduced colormaps and edge features. To enhance the natural scene presentation, the image region segmentation process is preferred when extracting and applying colormaps. However, the image segmentation technique needs a lot of computational operations. It takes a long time for non-photorealistic rendering for large size frames. To speed up the time-consuming segmentation procedure, we use GPGPU for the parallel computing using the GPU. As a result, we significantly improve the execution speed of the algorithm.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.12
• /
• pp.9-14
• /
• 2015

In this paper, we present an color quantization method by complementing the disadvantage of K-means color quantization that is one of the well-known color quantization. We named the proposed method "octree-means" color quantization. K-means color quantization does not use all of the clusters because it initializes the centroid of clusters with random value. The proposed method complements this disadvantage by using the octree color quantization which is fast and uses the distribution of colors in image. We compare the proposed method to six well-known color quantization methods on ten test images to evaluate the performance. The experimental results show 68.29 percent of mean square error(MSE) and processing time increased by 14.34 percent compared with K-means color quantization. Therefore, the proposed method improved the K-means color quantization and perform an effective color quantization.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2534-2536
• /
• 2003

Color는 다른 물체로부터 하나의 물체를 특정짓기 위한 효과적이고 강인한 실마리이므로 color clustering이 많은 주목을 받고 있다. 그러나 불규칙한 조명변화에 의한 color 변이 때문에 color segmentation은 매우 어렵다. 이 논문은 B-spline 곡선을 이용한, HSI color space에서의 intensity 정보를 포함한 신뢰할 수 있는 color modeling 방법을 제안한다. 이것은 비록 HS 평균임에도 불구하고 단색 물체의 color 분포가 조명이 변함에따라 변한다는 사실에 기반한다. 이 접근법을 사용하면 피부색을 가진 영역의 color clustering이 불규칙한 조명변화에 적응될 수 있다.

• Journal of Korea Multimedia Society
• /
• v.8 no.4
• /
• pp.473-481
• /
• 2005

In this paper, we propose an image segmentation method preserving object's boundaries by using the number of quantized colors and merging regions using adaptive threshold values. First of all, the proposed method quantizes an original image by a vector quantization and the number of quantized colors is determined differently using PSNR each image. We obtain initial regions from the quantized image, merge initial regions in CIE Lab color space and RGB color space step by step and segment the image into semantic regions. In each merging step, we use color distance between adjacent regions as similarity-measure. Threshold values for region-merging are determined adaptively according to the global mean of the color difference between the original image and its split-regions and the mean of those variations. Also, if the segmented image of RGB color space doesn't split into semantic objects, we merge the image again in the CIE Lab color space as post-processing. Whether the post-processing is done is determined by using the color distance between initial regions of the image and the segmented image of RGB color space. Experiment results show that the proposed method splits an original image into main objects and boundaries of the segmented image are preserved. Also, the proposed method provides better results for objective measure than the conventional method.

• Journal of IKEEE
• /
• v.13 no.4
• /
• pp.1-7
• /
• 2009

A video segmentation algorithm, which can extract objects even with non-stationary backgrounds, is proposed in this work. The proposed algorithm is composed of three steps. First, we perform an initial segmentation interactively to build the probability density functions of colors per each macro block via kernel density estimation. Then, for each subsequent frame, we construct a coherence strip, which is likely to contain the object contour, by exploiting spatio-temporal correlations. Finally, we perform the segmentation by minimizing an energy function composed of color, coherence, and smoothness terms. Experimental results on various test sequences show that the proposed algorithm provides accurate segmentation results.

• Journal of information and communication convergence engineering
• /
• v.13 no.3
• /
• pp.205-214
• /
• 2015

In this paper, we propose a new approach to learning a discriminative model for figure/ground segmentation by incorporating the bag-of-features and conditional random field (CRF) techniques. We advocate the use of image patches instead of superpixels as the basic processing unit. The latter has a homogeneous appearance and adheres to object boundaries, while an image patch often contains more discriminative information (e.g., local image structure) to distinguish its categories. We use pixel-level sparse coding to represent an image patch. With the proposed feature representation, the unary classifier achieves a considerable binary segmentation performance. Further, we integrate unary and pairwise potentials into the CRF model to refine the segmentation results. The pairwise potentials include color and texture potentials with neighborhood interactions, and an edge potential. High segmentation accuracy is demonstrated on three benchmark datasets: the Weizmann horse dataset, the VOC2006 cow dataset, and the MSRC multiclass dataset. Extensive experiments show that the proposed approach performs favorably against the state-of-the-art approaches.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.1
• /
• pp.223-229
• /
• 2018

This paper proposes a robust technique of image segmentation, which can be obtained if the topological persistence of each connected component is used as the feature vector for the graph-based image segmentation. The topological persistence of the components, which are obtained from the super-level set of the image, is computed from the morse function which is associated with the gray-level or color value of each pixel of the image. The procedure for the components to be born and be merged with the other components is presented in terms of zero-dimensional homology group. Extensive experiments are conducted with a variety of images to show the more correct image segmentation can be obtained by merging the components of small persistence into the adjacent components of large persistence.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.7
• /
• pp.2345-2358
• /
• 2022

This paper presents a method to generate stained-glass animation from video inputs. The method initially segments an input video volume into several regions considered as fragments of glass by mean-shift segmentation. However, the segmentation predominantly results in over-segmentation, causing several tiny segments in a highly textured area. In practice, assembling significantly tiny or large glass fragments is avoided to ensure architectural stability in stained glass manufacturing. Therefore, we use low-frequency components in the segmentation to prevent over-segmentation and subdivide segmented regions that are oversized. The subdividing must be coherent between adjacent frames to prevent temporal artefacts, such as flickering and the shower door effect. To temporally subdivide regions coherently, we obtain a panoramic image from the segmented regions in input frames, subdivide it using a weighted Voronoi diagram, and thereafter project the subdivided regions onto the input frames. To render stained glass fragment for each coherent region, we determine the optimal match glass fragment for the region from a dataset consisting of real stained-glass fragment images and transfer its color and texture to the region. Finally, applying lead came at the boundary of the regions in each frame yields temporally coherent stained-glass animation.

• Journal of Biomedical Engineering Research
• /
• v.42 no.5
• /
• pp.201-210
• /
• 2021

In Korean medicine, tongue diagnosis is one of the important diagnostic methods for diagnosing abnormalities in the body. Representative features that are used in the tongue diagnosis include color, shape, texture, cracks, and tooth marks. When diagnosing a patient through these features, the diagnosis criteria may be different for each oriental medical doctor, and even the same person may have different diagnosis results depending on time and work environment. In order to overcome this problem, recent studies to automate and standardize tongue diagnosis using machine learning are continuing and the basic process of such a machine learning-based tongue diagnosis system is tongue segmentation. In this paper, image data is augmented based on the main tongue features, and backbones of various famous deep learning architecture models are used for automatic tongue segmentation. The experimental results show that the proposed augmentation technique improves the accuracy of tongue segmentation, and that automatic tongue segmentation can be performed with a high accuracy of 99.12%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.3
• /
• pp.67-73
• /
• 2012

Local color transfer is the process of assigning a given color to a local region in a target image. The local region that contains the given color has to be segmented. Conventionally, the segmentation of the corresponding local region in a target image is based on the color distance. The region which is the closest in color distance is separated. However, since the close range of color distance separating a given color from target image is ambiguous and uncertain, color distortion is often generated around a separated local region. Therefore, this paper addresses the problem of segmentation in a local color transfer. To prevent color distortion, a modified color influence map is proposed with color categories. First, the target image is roughly segmented using a color category map, which groups similar colors in color space. It restricts the color transfer to a specific color category according to a given color. Second, modified color influence map assigning different weight to lightness and chroma, respectively, is used instead of Euclidian color distance. Then, by combining a modified color influence map and color category map filtered with anisotropic diffusion, a local region that contains a given color can be segmented more strictly than conventional method.