Skip to main content

About this book

This journal subline serves as a forum for stimulating and disseminating innovative research ideas, theories, emerging technologies, empirical investigations, state-of-the-art methods, and tools in all different genres of edutainment, such as game-based learning and serious games, interactive storytelling, virtual learning environments, VR-based education, and related fields. It covers aspects from educational and game theories, human-computer interaction, computer graphics, artificial intelligence, and systems design.

The 19 papers presented in the 14th issue were organized in topical sections named: 3D modeling and visualization; image; e-learning and games; and miscellaneous.

Table of Contents


3D Modeling and Visualization


Application of Visualization in Clothing Thermal Computational Design

Computational design provides a scientific and quantitative way for designers to conduct clothing functional design. In this study, the authors describe the application of 2D/3D visualization in the clothing thermal computational design process. The computational 2D visualization is employed to compare the key parameters between target cases and select appreciate case design. The computational 3D visualization can provide more detail supplementary information to demonstrate the final effects of the selected case design.
Mingliang Cao, Lu Jin, Yi Li, Zhigeng Pan

The 3D Human Body Modeling for Virtual Fitting Based on the Key Characteristic Parameters

With the development of Internet and e-commerce in recent years, it has become an urgent need for e-commerce users to buy satisfactory clothes through virtual fitting. Therefore, it is of great significance to research and develop a virtual fitting system that can help users create 3D human models to express their personality quickly and effectively by simply entering key characteristic parameters. By using computer simulation and 3D modeling technology, we focus on analyzing and selecting key parts and characteristic parameters that affect the effect of dressing, and study how to create the contour of human body’s key parts by leveraging these key characteristic parameters. And then, the contour is used to create 3D human surface model, based on which personalized 3D human body model for virtual fitting can be quickly and effectively created through users’ modification of key characteristic parameters.
Meiliang Wang, Yang Shen

Hierarchical-Layout Treemap for Context-Based Visualization

In order to represent hierarchical information more efficiently and aesthetically on mobile devices, many researchers have adopted the space-filling method—Treemap. In this article, a novel dynamic hierarchical-layout algorithm is proposed to visualize hierarchical information on mobile devices. This layout algorithm tries to represent the hierarchical data set with more balanced aspect ratio for the rectangles which is closely related to the aesthetics of treemap. Furthermore, a focus+context fisheye distortion algorithm is introduced to help users understand details by increasing the size of the interested items while decreasing the others. Experimental results show that the proposed method can provide a suitable resolution for visualizing hierarchical information with high efficiency and give focus+context views on mobile devices in real time.
Jingtao Wang, Yinwen Shen, Dingke Kong, Jing Hua

3D Indoor Environment Modeling and Detection of Moving Object and Scene Understanding

Obtaining large-scale outdoor city environment is a mature technique, supporting many applications, such as search, navigation, etc. The indoor environment with same complexity often contains high density duplicate objects (e.g. table, chair, display, etc.). In this paper, special structure of indoor environment was applied to accelerate home video camera to conduct 3D collection and identification of indoor environment. There are two stages of this method: (i) Learning stage, gain three-dimensional model of objects which occurs frequently and variation pattern with only few scanning capture, (ii) identification stage, determine the objects which had been seen before but in different gestures and positions from the single scanning of a new field, which greatly accelerate identification process.
In addition, under indoor environment, detection of moving objects, such as lighting change, is also arduous task. Basic histons and histons roughness index (HRI) related to it have been reported by literature. It has impressive achievement for the segmentation of still image. We expand histons definition to 3D histons and consider the combined mode of the whole color plane, but not to consider single color plane. Besides, bring fuzziness into 3D HRI measurement. Move the object in accordance with the concept of rough set theory, change background gradually or set dynamic background as background, and pixel labeled at the same time won’t let the objects that move slowly bring into background model.
Common home video camera was used to obtain typical area of a university construction, including classroom and laboratory, to prove result of the method we adopted, by qualitative and quantitative analysis, was satisfying.
Bin Shao, Zhimin Yan

A Watermarking Algorithm for 3D Point Cloud Models Using Ring Distribution

A robust watermarking algorithm for 3D point cloud models based on feature vertices is proposed in this paper. Vertices with mean curvature less than zero are selected as feature vertices for watermark embedding. These feature vertices lying in the deeper surface can guarantee better imperceptibility for the watermarking information. The invariant space is established to resist geometric attacks by using the rest vertices, in which the 3D model are divided several ball rings according to the number of watermark bits. Scheme to embed watermarking information is to modify the radial distances of the feature vertices within the different ball rings. Experimental results show the proposed algorithm is robust against geometric attacks. It outperforms other methods in terms of imperceptibility and robustness.
Jing Liu, Yajie Yang, Douli Ma, Yinghui Wang, Zhigeng Pan



A Novel Algorithm Related with Customers Based on Image Gradient Orientation

Based on the study of image gradient orientation and relevant technique about customers, this paper has proposed a algorithm related with customers based on image gradient orientation (CS-IGO-LDA). Face images are vulnerable to illumination changes, resulting in most of the traditional subspace learning algorithms which rely on image representation information are robust. In order to alleviate this problem, we represent the original samples by using image gradient orientation rather than the pixel intensity. And, in order to better describe the differences between different categories, we use methods related with customers to extract sample feature vector of each individual. The proposed CS-IGO-LDA method has made full use of the advantage of image gradient orientation and methods related with customers in face recognition. Experiments in face databases of Yale, JAFFE and XM2VTS have proved the validity of the new algorithm in face recognition and face verification.
Xiaofen Li, Defa Zhang

Automatic Recognition of Pavement Crack via Convolutional Neural Network

Conventional visual and manual road crack detection method is labor-consuming, non-precise, dangerous, costly and also it can affect transportation. With crack being the main distress in the actual pavement surface, digital image processing has been widely applied to cracking recognition recently. This paper presents the preprocessing method, segmentation method, the locating method, and a novel convolutional neural network based pavement cracking recognition method in the area of image processing. This paper trains and tests aforementioned 5-layer convolutional neural network on the pavement crack dataset. The experimental result shows that this 5-layer convolutional neural network performs better than that classical conventional machine learning method. Actual pavement images are used to verify the performance of this method, and the results show that the surface crack could be identified correctly and automatically. The convolutional neural network can learn the features of crack well and sort these aircraft with a high classification accuracy.
Shangbing Gao, Zheng Jie, Zhigeng Pan, Fangzhe Qin, Rui Li

Image Zooming Model Based on Image Decomposition

According to the different morphological characteristics between cartoons and textures in images, an image zooming model was proposed which based on image decomposition. The model decomposed the image into cartoons and textures by decomposition model; it analyzed the features of isotropic model and anisotropic model, the cartoon part was zoomed by isotropic model and the texture part was zoomed by anisotropic model. The using of shock filter eliminated the weak edge due to image zooming. At last, it achieved the amplification by combining the two zoomed parts. Simulation experiment results showed the model was good enough to zoom the image, strengthen the edge and guarantee the smoothness of the image. The model had better visual effects and the value of Peak Signal-to-Noise Ratio (PSNR) and Root-mean-square error (RMSE) was better than Bi-cubic and anisotropic model.
Yongguo Zheng, Songhe Gao

Salient Object Detection Based on the Fusion of Foreground Coarse Extraction and Background Prior

In order to obtain more refined salient object detection results, firstly, the coarse salient regions are extracted from the bottom-up, the coarse saliency map contains local map, frequency prior map and global color distribution map, which are more in accord with the rules of biological psychology. Then, an algorithm is proposed to measure the background prior quality by using three indexes, namely, salient expectation, local contrast and global contrast. Finally, the weighted algorithm is designed according to the prior quality to improve the saliency, so that the saliency prior and the saliency detection results are more accurate. Compared with 9 state-of-the-art algorithms on the 2 benchmark datasets of ECSSD and MSRA 10k, the proposed algorithm highlights salient regions, reduces noise, and is more in line with human visual perception, and reflects the excellence.
Lingkang Gu, Zhigeng Pan

E-learning and Games


EasyCouplet: Automatic Generation of Chinese Traditional Couplets

In order to inherit and develop the Couplet culture, one of the most famous language culture in China, this paper implements a creation system of couplets. In this paper, a noval way to generate the customized couplet is discussed from the name-embedded couplet. The 2-gram word graph technology is used to generate the first sentence which contained the given word. Then, combined with language model which based on statistical method, grammar model and mutual information model, improved Viterbi Algorithm based on HMM is used to decode the second sentence. It turned out that the system can realize the automatic generation of the name embedded couplet. According to the contents involved in the given couplet, the system can generate pictures to match the couplet. This system is aimed for Spring Festival couplets and Birthday couplets, both are name-embedded couplet that generated with the name of people. Users can choose the templates and relative special elements freely to create a satisfactory multimedia couplet picture.
Zhigeng Pan, Shicheng Zhang, Yanhua Guo

Design and Implementation on Digital Display System of Tang Dynasty Women Costumes

As an excellent representation of Chinese traditional culture, the Tang Dynasty dress has unique artistic features, such as unique shape, rich colors and exquisite patterns. With the progress of the times and clothing innovation, Chinese traditional costume elements are less and less reflected in modern society, with the lack of public awareness of Chinese traditional costume culture. Chinese traditional dress is gradually fading away from our daily life. In view of this fact, this paper uses computer simulation technology to build a virtual exhibition system for traditional costumes. Based on interaction design principles, a digital simulation system for women costumes in Tang Dynasty has been designed and implemented, so as to modify the public learning approach to traditional culture, to express and spread the culture meanings of Tang Dynasty costumes through text, images and music, and to realize interaction with users by means of interactive effects.
Desheng Lyu, Meng Guo, Yuchao Sun

Study of Animation Simulation Technology for Earthquake Escape Education

China is an earthquake-prone countries, so it’s important to carry out earthquake escape education which has practical significance. The traditional way of earthquake escaping education is not vivid enough, also lacking the sense of reality or interactivity, so to arouse the learner’s interest proved to be very difficult. Based on the constructivism learning concept, a new educational method for assisting earthquake escaping was proposed based on animation simulation technology. Using virtual reality engine an animation game was developed, in which virtual scenes were created, animation character was modeled, the motion controlling method for virtual characters was constructed, and particle animation was used so as to achieve earthquake effects. The prototype of this demonstration system can run in a browser, which makes it easy to promote. Preliminary tests show that users prefer this new educational method for earthquake escaping to the old ones. Electronic document is a “live” template. The various components of your paper [title, text, heads, etc.] are already defined on the style sheet, as illustrated by the portions given in this document.
Weijian Hu, Yanyan Zheng

Online Game Bot Detection Based on Extreme Learning Machine

Some players of Massively Multiuser Online Role-Playing Games (MMORPG) manipulate game bots to accumulate property quickly in the game world, for getting a high-level experience quickly without spending too much time and energy. It has a great impact on the game experience of human players, and lead to an unfair phenomenon in games. We analyze and screen players in online games to quickly capture game bots, and let game operators do subsequent processing. First, we analyze game log data and arrange user behavior sequences to form a matrix with user information. Second, Extreme Learning Machine (ELM) is used for classification and screening. Some traditional classification methods, i.e. SVM and KNN, are used on the same data to verify the algorithm effect. Empirical study demonstrates that the proposed method is competitive with some traditional methods in terms of accuracy and efficiency.
Xu Huang, Jing Fan, Shaowen Gao, Wenjun Hu

Attention Decrease Detection Based on Video Analysis in E-Learning

E-learning takes the advantages of lower cost and higher benefit. It becomes one of the educational research focus through learning behavior analysis to promote deep learning. In order to help learners overcome possible disadvantages in e-learning environment such as prone inattention and delayed response, one video analysis algorithm is designed to detect attention decrease situation, then feedback in time or warn early. The algorithm uses head posture, gaze, eye closure and mouth opening, facial expression features as attention observation attributes. Next machine learning classifiers are applied to code behavior features. Finally the time sequential statistics of behavior features evaluate the attention level and emotional pleasure degree. Experiments show that the algorithm is effective to find out the inattention cases to give desirable feedback. It may be applicable in adaptive learning and human computer interaction fields.
Liying Wang



Research on the Construction Mechanism of Collaborative Innovation Research Platform of Private Universities

Taking Jilin Animation Institute as an Example
The participation of private universities in collaborative innovation is of great significance to the academic development of scientific research work, the economic development of society and the implementation of the national collaborative innovation strategy. At first, this paper expounds on the connotation of the collaborative innovation research platform and its requested functions, and then illustrates the principles of building the collaborative innovation research platform. Also, it takes Jilin Animation Institute as an example to study the structure, safeguard mechanism and operation mode of its collaborative innovation research platform, providing effective basis for private universities to build the collaborative innovation research platform.
Mingming Zhao, Guangning Sui

A Bibliometric Analysis on the Published Papers in Journal of Technology Enhanced Foreign Language Education (TEFLE) from Year 2006 to 2015

This Paper presents a bibliometric analysis of the papers published in the journal of Technology Enhanced Foreign Language Education (TEFLE), a core professional academic journal in China, during the years from 2006 to 2015. Our result aims to provide a clear view of the evolution of literature in the research field of technology enhanced foreign language learning over the past decade, intending to put forward a preliminary framework for TEFLE to improve its publication quality and at the same time foster better technology enhanced foreign language education in China. Bibliometric indicators of paper amount, author information, total citations, and frequency of keywords have been analyzed with the use of tools of BICOMB and SPSS and methods of co-word and cluster analysis, which indicates that, over the past decade, both of the quality of the published papers and the paper evaluation system has been improved. The statistics also reveal that the authors in TEFLE are mainly from eastern China, a research group that has been formed with more researchers constantly joining in, and a number of papers have been highly cited, bringing further interest in the related disciplines. Currently, the reform of foreign language classroom teaching with technological aids appears the hotspot topic in the related applied field. An effort is made to demonstrate that the research method has shifted to a new way that places equal emphasis on both quantitative and qualitative study in technology enhanced learning (TEL) and technologies have a bigger influence on foreign language learning in China, but in the meantime, there is an imbalance in the distribution of authors from different national geographic areas in TEL research.
Xiu-Yan Zhong

Fuzzy Comprehensive Evaluation for Rural Public Sports Services

Establishing a performance evaluation system for rural public sports services is the basis for setting up a scientific administrative control system for public sports services. Questionnaire survey, Delphi method and mathematical statistics technique were conducted. Based on relevant theories and principles, exploratory factor analysis was adopted, and the performance evaluation system for rural public sports services along with the weights of indicators was determined. This evaluation system consisted of three primary indicators, eight secondary indicators and thirty tertiary indicators. Rural areas of five prefecture-level cities in Zhejiang Province were taken as the research objects. An empirical study was conducted regarding the performance evaluation system for public sports services in rural areas using the fuzzy comprehensive evaluation method. The results showed that the comprehensive score for the performance of public sports services in rural areas of Zhejiang was 70.087, indicating a moderate level, which was intermediate between “satisfactory” and “neutral”. The respondents were satisfied or above with three indicators, namely, public sports organization and administration services provided by the local public sports sector, current number of public sports facilities, and usage of public sports facilities. However, the respondents were most unsatisfied with two indicators, namely, service attitude of rural public sports administrators and development and exploitation and utilization of rural public sports resources.
Qiuhong Han, Shen Qing

Studies on Artistic Style of Chinese Ink Deckle-Edged Paper-Cutting Animation

This article elaborates processes of the production and development of ink deckle-edged paper-cutting animation and summarizes its artistic style. The overall style of ink deckle-edged paper-cutting animation has the unique beauty of artistic conception of Chinese traditional arts, modeling of character is featured on fine and delicate, and has characteristic of shading in Chinese ink painting. Its theme is refined and rich in philosophy. At the same time, this article also explores problems existed and future development of ink deckle-edged paper-cutting animation.
Xiaoli Dong

Usability Study of CAD for Clothing Thermal Computational Design Education

This paper describes a usability study of CAD for teaching and learning clothing thermal computational design (CTCD) for university students of fashion and textiles. The CAD helps students to learn the clothing thermal computational design through computational design simulations (CD-Sims). The pedagogical strategies of employing CAD, and learning process and pedagogical implementation of CD-Sims are discussed. In addition, a user study employing the CD-Sims with CAD indicated that they enhanced students’ learning outcomes on pre-test and post-test clothing thermal computational design scores.
Mingliang Cao, Yi Li, Josephine Csete, Zhigeng Pan


Additional information

Premium Partner

    Image Credits