Hochang Lee, Sanghyun Seo, Seungtaek Ryoo, Keejoo Ahn, Kyunghyun Yoon
Multimedia Tools and Applications
May 2013, Volume 64, Issue 2, pp 277-292
Increasing the level of detail (LOD) in brushstrokes within areas of interest improved the realism of painterly rendering. Using a modified quad-tree, we segmented an image into areas with similar levels of saliency; each of these segments was then used to control the brush strokes during rendering. We could also simulate real oil painting steps based on saliency information. Our method runs in a reasonable fine and produces results that are visually appealing and competitive with previous techniques.
Hochang Lee, Taemin Lee, Kyunghyun Yoon
Advances in Visual Computing Lecture Notes in Computer Science
Volume 7431, 2012, pp 513-522
Existing color reproduction algorithms achieve image enhancement or visualization by correcting tone and hue. Although these algorithms are good at incorporating a natural feel in an image, they do not accurately represent intended colors that are contrasted. This limitation is particularly evident in the case of impressionist paintings that have a color contrast based on the style of the painter and the conventions of impressionism. In this study, we propose a novel color reproduction algorithm for impressionism, primarily focusing on paintings by Vincent van Gogh. First, the color value that is most obvious to the user is extracted. Based on this color, the color of the main object is transferred. Then, the color contrast information of a sample painting is extracted based on the color harmony theory. Finally, the color of other regions is transferred. Using our proposed algorithm, a more artistic result that matches the contrast style of the artist is generated. This work should be extended further to enhance the simulation of stroke color by a painterly rendering algorithm.
Gyeongrok Lee, Hochang Lee, Taemin Lee, Kyunghyun Yoon
Luminance quantization, which maps the luminance values of an image to discrete levels, is widely used for image abstraction and the expression of a cartoonlike effect. Existing luminance quantization techniques use each pixel’s luminance value separately, leading to a noisy image. Additionally, they do not take the shape of the imaged object into consideration. Thus, they suffer limitations in terms of cartoonlike shade representation. We propose a new luminance quantization algorithm that takes into account the shape of the image. We extract the silhouette from the image, compute edge-distance values, and incorporate this information intothe process of luminance quantization. We integrate the luminance values of neighboring pixels using an anisotropic filter, using gradient information for this filtering. As a result, ourquantized image is superior to that given by existing techniques.
Sanghyun Seo, Seungtaek Ryoo, Kyunghyun Yoon
ACM Transactions on Embedded Computing Systems (TECS) - Special issue on embedded systems for interactive multimedia services (ES-IMS)
Volume 12 Issue 2, February 2013, Article No. 22
In this article, we propose the rendering framework for painting-like image generation and general system architecture for mobile device. Especially, we focused on a color division method for generating neo- impressionist images. The French painter, George Seurat, introduced pointillism under the theory that the individual pigments of colors on the canvas are reconstructed on the human retina. Pointillism is a painting technique in which many small brush strokes are combined to form a picture and determines the color of brush strokes based on the optical mixing of juxtaposed colors. In order to express countless separate dots, we form hierarchical points using Wang Tiles contained points. Also palette will be constructed using neo-impressionist colors. Based on this palette, we propose color division algorithm that distributes hierarchical point’s color to pointillist colors using probability function. Finally, hierarchical points set that applied proposed color division rule is converted into brush strokes that possesses properties such as shape and direction. This rendering algorithm is performed in our proposed system. Our scheme is able to produce a painting with artistic style and be applied to the various platform having the different computing performance and display resolution. This system also can be extended to various imaging devices (IPTV, camera, smart phone, digital photo frame and so on).
Hochang Lee, Sanghyun Seo, Kyunghyun Yoon
Computers & Graphics
Volume 35, Issue 1, February 2011, Pages 81–91
Texture transfer re-renders a target image with high-frequency information (texture) taken fromparts of a reference image that is matched locally to the target image using characteristics such as color. In this paper, we add a directional factor based on the ﬂow of the target image, creating a stroke-like effect that follows edgesmore accurately. In addition, we propose amethod to clearly express object boundaries by considering the effect of the medium on edges in the reference image. We also show how to select an appropriateweight for this directional factor fromthe reference image.We demonstrate the suitability of this improved formof texture transfer for expressing various artistic styles, and compare our resultswith those from previous texture-transfer algorithms. We ﬁnd that our algorithm can be adapted to texture synthesis as well.
Hochang Lee,Sanghyun Seo,Seungtaek Ryoo,Kyunghyun Yoon
A texture transfer algorithm modiﬁes the target image replacing the high frequency information with the example source image. Previ- ous texture transfer techniques normally use such factors as color distance and standard deviation for selecting the best texture from the candidate sets. These factors are useful for expressing a texture effect of the example source in the target image, but are less than optimal for considering the object shape of the target image. In this paper, we propose a novel texture transfer algorithm to ex- press the directional effect based on the ﬂow of the target image. For this, we use a directional factor that considers the gradient di- rection of the target image. We add an additional energy term that respects the image gradient to the previous fast texture transfer al- gorithm. Additionally, we propose a method for estimating the di- rectional factor weight value from the target image. We have tested our algorithm with various target images. Our algorithm can ex- press a result image with the feature of the example source texture and the ﬂow of the target image.
Myounghun Han, Dongwann Kang, Kyunghyun Yoon
Journal of Real-Time Image Processing September 2013
According to the growth of mobile technology, people experience high-performance mobile devices. In this environment, processing in real-time is required for mobile application. For colored paper mosaic application on mobile devices, the problem regarding speed must be solved while maintaining high-quality. In this paper, we propose an accelerated method that generates tiles based on their position. We locate tiles by considering the edges of the image and the shapes of neighbor tiles. The shape of the tiles is determined based on the position of each tile. In addition, we display the generation process of a result for our method be seemed real-time method. In here, we pro- pose an ordering method that is similar to the ordering method of humans by considering color, edge, distance and direction.
Dongwann Kang, Sanghyun Seo, Seungtaek Ryoo, Kyunghyun Yoon
Multimedia Tools and Applications
March 2013, Volume 63, Issue 1, pp 145-159
With the growing use of mobile devices such as smartphones, tablet PCs, and digital cameras, photography has become an integral part of everyday life. In particular, mobile devices with cameras allow us to easily capture and modify photographs that can be shared via social networks. In this paper, we introduce a mobile device application for converting photographs into photomosaic images. In general, high-quality photomosaics require large databases.However,mobile devices have limited resources; hence it is difficult for such devices to support photomosaics. We propose a method that produces a photomosaic effect using a database that consists of rotatable images. We also propose a solution to the performance issue basedonabestmatchsearch.
Dongwann Kang, Yongjin Ohn, Myunghun Han, Kyunghyun Yoon
Computer Animation and Virtual Worlds, 7 JUN 2012
Volume 23, Issue 3-4, pages 191–202, May-August 2012
Although the creation static mosaic-like images from non-mosaic input has been studied, satisfactory methods to maintain and evaluate the temporal coherence of tiles for mosaic animations have remained elusive. Here, we describe a method that successfully generates mosaic animations from videos by applying a temporally and spatially coherent tile-arrangement technique. We arrange tiles on the basis of the feature lines extracted from video input. We then animate the tiles along the motion of the video, add and delete tiles to preserve the tile density, and smooth tile color via frames. Finally, we propose indices to evaluate the temporal coherence of video-based animations, and show that our animations are temporally coherent.
Dongwann Kang, Yonnjin Ohn, Myounghun Han, Kyunghyun Yoon
In mosaic art, tiles of unique color, material, and shape are arranged on a plane to form patterns and shapes. Although previous research has been carried out on creating static mosaic-like images from non-mosaic input, mosaic animation requires a method to maintain the temporal coherence of tiles. Here we introduce a method that creates mosaic animations from videos by applying a temporally and spatially coherent tile-arrangement technique. We extract coherent feature lines from video input using video segmentation, and arrange tiles based on the feature lines. We then animate tiles along the motion of video, add and delete tiles to preserve the tile density, and smooth tile color via frames.