Dongwann Kang

A study on stackable mosaic generation for mobile devices

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 based on a best match search.

Efficient paper mosaic rendering on mobile devices based on position-based tiling

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 propose an ordering method that is similar to the ordering method of humans by considering color, edge, distance and direction.

A photomosaic image generation method using photo annotation in a social network environment

With the growing use of social networking services, various applications have been developed to utilize their vast capabilities. Photomosaic techniques, which combine many images to create a new rendering of an input image, can benefit from the capabilities of social networks. In this study, we propose a method that generates a photomosaic image by considering social network context. Our algorithm creates a photomosaic that incorporates photos posted by other users in the users network . We enable the matching function to easily select photos from the albums of users who are connected to the owner of the input image, by computing the closeness of those connections. Moreover, our technique allows the photos in the albums of friends who are annotated in the source image to be matched more effectively.

Generation of coherent mosaic animations: enhancement and evaluation of temporal coherence

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. Copyright

An artistic photographic collage on a mobile device

Computer graphics and image processing technologies for editing photographs taken by a user, and for photographic entertainment, have increased in recent years. One of these techniques, non-photorealistic rendering (NPR), is the focus of this study. In this study, we propose a method for applying David Hockneys photographic collage filtering on mobile devices by using several well-known computer graphics and image processing techniques. This process involves taking a sequence of images and extracting feature points, and using these feature points to deform an image. Finally, we obtain a photographic collage using the David Hockney style by generating a patchwork.

Animation for ancient tile mosaics

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.

Detail-Adaptive Toon Shading Using Saliency

This paper proposes a toon shading technique that can depict morphological features of an object precisely. We have applied two algorithms to conventional toon shading technique. The first is to express the shape of important areas by increasing and decreasing local contrast proportional to the degree of visual importance of an area by using virtual local lights while maintaining cartoon effect. The second algorithm is to depict details by adjusting the shading levels according to the visual importance of an area by using 2D toon texture. Saliency was used in this paper as a measure to determine visual importance of each area. Adjustments of shading levels and local contrasts based on saliency create cartoon images that are properly revealing details of significant areas regardless of an object’s surface orientation and the location of a light.

Study on predicting sentiment from images using categorical and sentimental keyword-based image retrieval

Visual stimuli are the most sensitive stimulus to affect human sentiments. Many researches have attempted to find the relationship between visual elements in images and sentimental elements using statistical approaches. In many cases, the range of sentiment that affects humans varies with image categories, such as landscapes, portraits, sports, and still life. Therefore, to enhance the performance of sentiment prediction, an individual prediction model must be established for each image category. However, collecting much ground truth sentiment data is one of the obstacles encountered by studies on this field. In this paper, we propose an approach that acquires a training data set for category classification and predicting sentiments from images. Using this approach, we collect a training data set and establish a predictor for sentiments from images. First, we estimate the image category from a given image, and then we predict the sentiment as coordinates on the arousal–valence space using the predictor of an estimated category. We show that the performance of our approach approximates performance using ground truth data. Based on our experiments, we argue that our approach, which utilizes big data on the web as the training set for predicting content sentiment, is useful for practical purposes.

Interactive Painterly Rendering for Mobile Devices

Painterly rendering is among the most popular non-photorealistic rendering techniques and has been employed in many applications. Research on painterly rendering mainly focuses on automatically generating artistic results. In this study, we aim to develop an entertaining and interactive application for painterly rendering with touchscreen mobile devices. The proposed application provides user interaction for added enjoyment and ensures high-quality painterly results. We provide a method for finding the appropriate position of the brush stroke around the points touched by the user and for generating and rendering the brush stroke. With the proposed method, users can quickly generate high-quality painterly results.

Directional texture transfer for video

Texture transfer is a method that copies the texture of a reference image to a target image. This technique has an advantage in that various styles can be expressed according to the reference image, in a single framework. However, in this technique, it is not easy to control the effect of each style. In addition, when this technique is extended to processing video images, maintaining temporal coherence is very difficult. In this paper, we propose an algorithm that transfers the texture of a reference image to a target video while retaining the directionality of the target video. The algorithm maintains the temporal coherency of the transferred texture, and controls the style of the texture transfer.