Jong-Weon Lee

A Multiple-Level 3D-LEGO Game in Augmented Reality for Improving Spatial Ability

Inspired by the real LEGO game, an Augmented Reality 3D LEGO game is introduced. With multiple levels, the game provides a tool to improve spatial ability for a wide range of ages. Through the game, users can practice many spatial skills such as analyzing a 3D models structure, figuring out what to do to make a primitive geometry become a component of a 3D model, assembling components to create a complex model. The users mainly use their hands controlling physical makers to play the game. A user study was also carried out to evaluate the game and to compare it with the real LEGO game. The game is believed to be a useful and interesting tool to enhance not only humans spatial ability but also humans creation in 3D reconstruction.

Interface for in-situ Authoring of Augmented Reality Contents on a Mobile Device Environment

This paper introduces a difference between mobile Augmented Reality (AR) authoring and desktop AR authoring, and suggests an interface system that can be applied to in-situ authoring of AR contents on a mobile device. The mobile devices have enabled users to use the AR system anytime and anywhere. It is now necessary to create user`s individualized context information using mobile devices on the spot. To author AR contents easily with mobile devices, we need to maximize the convenience of mobile systems, which have yet limitation. To do so, this paper suggests new interaction approaches that manage augmented contents using visual cues and other simple attribute settings. In addition, to solve the problem that users have to hold their mobile devices to track markers while authoring contents, this system enables users to author contents in environment based on captured images. This interface system also can make cooperation environment for more than one users to author contents. This paper verifies the usefulness of the proposed interface by user tests. The results of an analyzing users` comments show that the proposed interface is suitable for in-situ mobile authoring system.

Face representation method using pixel-to-vertex map (PVM) for 3d model based face recognition

3D model based approach for face recognition has been spotlighted as a robust solution under variant conditions of pose and illumination. Since a generative 3D face model consists of a large number of vertices, a 3D model based face recognition system is generally inefficient in computation time. In this paper, we propose a novel 3D face representation algorithm to reduce the number of vertices and optimize its computation time. Finally, we evaluate the performance of proposed algorithm with the Korean face database collected using a stereo-camera based 3D face capturing device.

Comparative Analysis of Graphic Contents Rendering Techniques in a Multi-view System through Agent-Mediator Based Communication

One of the major issues in mixed reality multi-agent systems is synchronization of display, which can adversely affect system performance and hinder user interaction. Real time response from the system cannot be achieved because of the aforementioned issues. If the content displayed on agents is complex and cannot be feasibly rendered on a single agent, then a better strategy is to divide the contents among multiple agents. In this way, only a fraction of the entire contents is rendered by each agent. In this paper, two alternative techniques for multi-agent based content management are proposed, namely, full contents on agents (FCOA) and partial contents on agents (PCOA). In FCOA, each agent in the multi-agent system renders all the contents and only a specific part of the contents is displayed depending upon the usage scenario. In PCOA the agents receive partial contents from the mediator. A comparative study has been presented in this paper to identify the pros and cons of each method.

Computer Assisted English Learning System with Gestures for Young Children

Kids use the computer assisted language learning systems to learn English. The contents of the system are well designed and kids enjoy them. From Cognitive Psychology we found gestures played useful role in learning so we developed the language learning system utilizing gestures. The system provides similar contents as the existing system but tries to enforce users to follow gestures related to given words. We compared the proposed system with an existing one in terms of memorizing test scores. The average improvement achieved using the proposed system was little better than one achieved using the existing system.

User-Personality Classification Based on the Non-Verbal Cues from Spoken Conversations

Abstract Technology that detects user personality based on user speech signals must be researched to enhance the function of interaction between a user and virtual agent that takes place through a speech interface. In this study, personality patterns were automatically classified as either extroverted or introverted. Personality patterns were recognized based on non-verbal cues such as the rate, energy, pitch, and silent intervals of speech with patterns of their change. Through experimentation, a maximum pattern classification accuracy of 86.3% was achieved. Using the same data, another pattern classification test was manually carried out by people to see how well the automatic pattern classification of personal traits performed. The results in the second manual test showed an accuracy of 86.6%. This proves that the automatic pattern classification of personal traits can achieve results comparable to the level of performance accomplished by humans. The Silent Intervals feature of the automatic pattern cl...

Efficient image splicing detection algorithm based on markov features

Image splicing is one of the most common methods for digital image tampering. In this paper, an efficient Markov features based algorithm is proposed for image splicing detection. The proposed algorithm first extracts two types of Markov features, coefficient-wise Markov features and block-wise Markov features in the discrete cosine transform (DCT) domain. The former are obtained by exploiting correlations between consecutive coefficients and the latter are computed by exploiting coefficient correlations between adjacent blocks. Then, a feature vector is obtained by combining these two Markov features and it is fed into support vector machine (SVM) for the classification of authentic and spliced images. The experimental results show that the proposed method not only achieves much higher detection accuracy but also reduces the total running time significantly in comparison with state-of-the-art methods.

A Study on Sound Reproduction for Adaptive Mixed-Reality Space

Advertisements and campaigns on multiscreen with digital monitors are recently becoming very common in public places. However current virtual reality technology has limits in the feeling of physical space which is an important factor for feeling of real space. We present a study on adaptive audio reproduction for physical and spatial immersion with mixed reality technology. Especially we tried to adjust the distortion of audio signal spectrum that can occur at users dynamic locations. As a result, we need the differentiated adjustment audio signal in frequency as well as loudness according to a distance between a user and a speaker.

A Quick Algorithm for Snapping 3D Objects in Augmented Reality

This paper describes a quick algorithm for snapping a moving object (being moved by a user) to existing objects in Augmented Reality (AR) environment. Because in AR, human-computer interactions are in the real time mode, the algorithm should be fast enough not to affect the scene rendering but still assure accuracy. It is currently designed to deal with primitive geometries such as cubes, cones, cylinders, spheres. And it should work well even after these geometries are transformed with scaling, rotating, moving operations. The main idea of the algorithm is that for each kind of geometry, some “hot spots” are defined. Each hot spot is a sphere with a certain radius. If the center point of the moving object is within a hot spot of any existing geometry it will be snapped to this geometry at that hot spot. This algorithm is already employed in an AR modeling system to evaluate its efficiency.

Morphable Model to Interpolate Difference between Number of Pixels and Number of Vertices

The images, which were acquired from various systems such as CCTV and Robot, include many human faces. Because of a rapid increase in visual data, we cannot process these manually; rather we need to do these automatically. Furthermore, companies require automatic security systems to protect their new technology. There are various options available to us, including face recognition, iris recognition and fingerprint recognition. Face recognition is preferable since it does not require direct contact. However, the standard 2-Dimensional method is limited, so Morphable Models may be recommended as an alternative. The original morphable model, made by MPI, contains a large quantity of data such as texture and geometry data. This paper presents a Geometrix-based morphable model designed to reduce this data capacity.