Yoon-Chul Choy

Geometric structure analysis of document images: a knowledge-based approach

This paper presents a knowledge-based method for sophisticated geometric structure analysis of technical journal pages. The proposed knowledge base encodes geometric characteristics that are not only common in technical journals but also publication-specific in the form of rules. The method takes the hybrid of top-down and bottom-up techniques and consists of two phases: region segmentation and identification. Generally, the result of the segmentation process does not have a one-to-one matching with composite layout components. Therefore, the proposed method identifies non-text objects, such as images, drawings, and tables, as well as text objects, by splitting or grouping segmented regions into composite layout components. Experimental results with 372 images scanned from the IEEE Transactions on Pattern Analysis and Machine Intelligence show that the proposed method has performed geometric structure analysis successfully on more than 99 percent of the test images.

An efficient algorithm to compute differences between structured documents

SGML/XML are having a profound impact on data modeling and processing. We present an efficient algorithm to compute differences between old and new versions of an SGML/XML document. The difference between the two versions can be considered to be an edit script that transforms one document tree into another. The proposed algorithm is based on a hybridization of bottom-up and top-down methods: The matching relationships between nodes in the two versions are produced in a bottom-up manner and then the top-down breadth-first search computes an edit script. Faster matching is achieved because the algorithm does not need to investigate the possible existence of matchings for all nodes. Furthermore, it can detect structurally meaningful changes such as the movement and copy of a subtree as well as simple changes to the node itself like insertion, deletion, and update.

Logical structure analysis and generation for structured documents: a syntactic approach

This paper presents a syntactic method for sophisticated logical structure analysis that transforms document images with multiple pages and hierarchical structure into an electronic document based on SGML/XML. To produce a logical structure more accurately and quickly than previous works of which the basic units are text lines, the proposed parsing method takes text regions with hierarchical structure as input. Furthermore, we define a document model that is able to describe geometric characteristics and logical structure information of documents efficiently and present its automated creation method. Experimental results with 372 images scanned from the IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) show that the method has performed logical structure analysis successfully and generated a document model automatically. Particularly, the method generates SGML/XML documents as the result of structural analysis, so that it enhances the reusability of documents and independence of platform.

Standardization of eBook documents in the Korean industry

An electronic book (eBook) has quite a few advantages over a paper-based book. However, several technical problems have not been solved until now in spite of the growing interest in eBooks, eBook industries are using different document formats with the result of difficulty in exchanging and sharing eBook contents and reinvestment in developing the related software. The US and Japan have realized the importance of a standard document format for eBooks, so they have developed the Open eBook Publication Structure (OEB PS) and JepaX, respectively, with the support from government agencies and related industries. Recently, the Electronic Book of Korea (EBK) has established a working group and developed a standard format based on the eXtensible Markup Language (XML) for eBooks. The goals of the standard include the explicit exchange of eBook contents reflecting the characteristics of the Korean publishing environment, simplicity in creation and exchangeability with the related formats. The standard supports the logical structure of various document classes as well as advanced style control such as vertical writing and multi-column editing based on XSL.

A dynamic message filtering technique for 3D cyberspaces

This paper discusses the scalability problem of distributed virtual environment (DVE) centered on area of interest (AOI) model and dead reckoning (DR) algorithm. Previous models improving scalability of virtual environment are analyzed and compared, and a new adaptive message-filtering algorithm based on DR is proposed. The proposed model can be utilized for distributed interactive simulation (DIS) and various network applications such as multi-player games and virtual communities. The most distinguished characteristic of the proposed model is the introduction of flexible threshold mechanism (FTM). It is inefficient that in static dead reckoning (SDR) algorithm, moving avatar straightly and frequently rotating one are uniformly considered. The proposed model overcomes the weak point of established DR caused by a fixed threshold and a strong dependency on rotational behavior of moving avatars. This paper defines a new criterion for update message filtering, named as update lifetime (UL), which is a valid duration time of entity state update. The advantage of dynamic approaches proposed in this paper is the ability of keeping the balance between fidelity and performance in filtering. In experimental results, it was shown that intelligent DR lowered the increment rate of update message traffic over the increase of behavioral complexity of avatar without any significant loss of accuracy.

Automated vectorization of cartographic maps by a knowledge- based system

Abstract Developing an automated vectorizing system as an input method for a geographic information system (GIS) is of extreme importance due to the fact that an input process takes a lot of time and cost in constructing a GIS. Most vectorizing systems require users to set the parameters as appropriately as possible for a particular map image, but it is quite difficult for a novice to adjust the parameters appropriately. This paper proposes a knowledge-based system for automated vectorization, allowing an appropriate choice of the parameters. Since thinning of the input image to produce a skeleton of unit width is a prerequisite for the automated vectorization among several steps, the performance of representative thinning algorithms is systematically evaluated in various map images, and appropriate rules for the maps are devised. Each rule in the knowledge base is characterized by the type of map, and by the resolution, line width, slope and protrusions. Experimental results with various map images show that the proposed system is superior in terms of performance and convenience of use.

A sketch interface to empower novices to create 3D animations

Realistic character animation requires elaborate rigging built on top of high quality 3D models. Sophisticated anatomically based rigs are often the choice of visual effect studios where life-like animation of CG characters is the primary objective. However, rigging a character with a muscular-skeletal system is very involving and time-consuming process, even for professionals. Although, there have been recent research efforts to automate either all or some parts of the rigging process, the complexity of anatomically based rigging nonetheless opens up new research challenges. We propose a new method to automate anatomically based rigging that transfers an existing rig of one character to another. The method is based on a data interpolation in the surface and volume domain, where various rigging elements can be transferred between different models. As it only requires a small number of corresponding input feature points, users can produce highly detailed rigs for a variety of desired character with ease. Copyright

A layered scripting language technique for avatar behavior representation and control

The paper proposes a layered scripting language technique for representation and control of avatar behavior for simpler avatar control in various domain environments. We suggest three layered architecture which is consisted of task-level behavior, high-level motion, and primitive motion script language. These layers brides gap between application domain and implementation environments, so that end user can control the avatar through easy and simple task-level scripting language without concerning low-level animation and the script can be applied various implementations regardless of application domain types. Our goal is to support flexible and extensible representation and control of avatar behavior by layered approach separating application domains and implementation tools.

Sketch-n-Stretch: Sketching Animations Using Cutouts

Sketch-n-Stretch lets novices quickly and easily create 2D animations. The system has a seamless two-layer drawing interface that supports cutouts using a whiteboard metaphor. Cutout animations serve as building blocks to help users construct sophisticated animations. While manipulating cutout animations, users can draw and write text to create effects-such as articulated figures, multiple motions, and image objects-that have been difficult with previous sketching approaches. An intuitive timeline interface employs visually integrated motion cues and supports several traditional animation effects. Novices positively evaluated Sketch-n-Stretchs effectiveness in creating object motions, compared to an existing sketching tool. They also used its advanced features to animate complete stories. This video demonstrates the Sketch-n-Stretch tool for making sketch-based animations.

A structured documents retrieval method supporting attribute-based structure information

There are many studies on retrieval methods for structured documents but most of the studies are for those whose structure information is expressed by elements. But when elements are used to describe a document structure, the structure becomes static and difficult to expand. So describing a document structure using attributes is used in many standards. But most of the existing systems support mainly element-based structured documents and do not consider attribute-based ones. Hence they do not support attribute-based structured documents well. So, we propose a new indexing method that supports attribute-based structured documents. In our index scheme, element-based structure information and attribute-based structure information are seamlessly integrated to describe a general document structure. Also, we consider possible searching methods under the proposed index, and implement each method. And then, we experiment each method using the document actually being used in business, then analyze the results.