In this paper, we propose an effective novel content-aware chroma reconstruction (CACR) method for screen content images (SCIs). After receiving the decoded downsampled YUV image on the client side, our fast chroma-copy approach reconstructs the missing chroma pixels in the flat regions of SCI. Then, for non-flat regions, a non-flat region-based winner-first voting (NRWV) strategy is proposed to identify the chroma subsampling scheme used on the server side prior to compression. Further, an effective adaptive hybrid approach is proposed to reconstruct each missing chroma pixel in the non-flat region by fusing the two reconstructed results, one from our modified NRWV-based chroma subsampling-binding and luma-guided chroma reconstruction scheme, which favors the sharp edges in SCI, as well as the other from the bicubic interpolation scheme, which favors blurred and continuous-tone textures. Further, based on the identified chroma subsampling scheme, a geometry alignment-based error compensation approach is proposed to enhance the reconstructed chroma image. Based on typical test SCIs and JCT-VC screen content videos, comprehensive experiments are carried out in HEVC-16.17 to demonstrate that in terms of quality, visual effect, and quality-bitrate tradeoff of the reconstructed SCIs, our CACR method significantly outperforms the existing state-of-the-art methods.

This study proposes a mobile augmented-reality teaching system focused on historic buildings that enables users to build a deeper understanding of the building structure, features, historical references and era influence while simultaneously exploring the historic site through the interaction effect that combines the virtual and the real. This increases overall interest in architecture and history. In this study, five students will operate the AR system to study how Mackay Culture influenced Tamsui and a satisfaction survey with both the questionnaire survey and an interview will be utilized to determine if participants are receptive to our proposed system and provide feedback on how to make subsequent improvements on our model.

Interaction between the student and the instructor is important for the student to gain knowledge. Also, one of the major tasks on the instructor in e-learning is to reply student e-mails and posted messages. Students usually raise their questions by these two methods in an e-learning environment. In this paper, we introduce a semantic-based automated question answering system that can act like a virtual teacher to respond to student questions online. With the system, not only the instructor can be relieved from the load of answering lots of questions, but also the student can mostly get answers promptly without waiting for the instructor to get online and provide an answer. This would be a big help for both the instructor and the student in e-learning environment. Through the process of raising questions and getting answers, the knowledge base will be enriched for future questions answering. Further, not only the students can get answers for their questions, but also the instructors could know what problems students encounter in learning. These would be big aids to both the teaching and the learning.

Due to the benefit provided by the well-developed infrastructure of the Internet, a growing number of people wish to enroll onto distance learning courses. However, the development of distance learning still faces many challenges, especially in the field of providing appropriate and user-friendly course design tools for the instructor, measuring student learning performance. Moreover, it is hard for an instructor to discern a student's personal needs, such as knowledge level, learning ability, and learning needs. Besides, instructors are required to post all teaching material on the Internet before class starts which may result in the preparation of class material without considering student learning ability. This leads to a slower development of distance learning. We provide a systematic course design tool which is based on the quantitative analysis mechanism we proposed to construct a multidimension and multiadaptive course learning object-oriented model. Furthermore, combining the resource-sharing character of PHP, a course on-demand mechanism can be developed which allows the instructor to provide a different combination of courses for different learning programs.

Martial art actions can be represented via VRML animations or extracted by video tracking. We propose an action retrieval method, which allows users to retrieve similar martial art actions. The mechanism is based on a similarity function that compares animation tracks. A representation of the human skeleton includes head, knee, elbow, wrist, etc and further aggregates important features in martial art actions. Different weights are dynamically calculated according to motion sensitivity of feature points. As a result, the system can automatically retrieve similar martial art actions. The results are tested by a professional kung fu master with good satisfaction.

Because of the interest of 3D images and the popularity of World Wide Web, the number of 3D scene/objects and model database throughout the world is growing both in number and in size. VRML (Virtual Reality Modeling Language) is used to model the 3D object of the Web page, and become as a standard for 3D information. Most content-based retrieval (CBR) techniques such as shape and color comparison among objects are for image and video. The mechanisms are designed based on 2D information. In this paper, we propose a new similarity method, based on 3D information extracted from a VRML object database. The system includes multiple subsystems, which are conducted in two main parts. The first part includes the VRML object parser system and the normalization system. The second part includes the comparison system, database management system and a friendly graphical user interface. The method is the first step of our project, which aims to incorporate feature extraction of virtual reality objects, such as chairs, car, and others in 3D space. House interior designers can use the proposed system. The user can select proper scenes and furniture in order to meet the requirement of potential customers.