Guest editorial

With the rapid development of computer and network technologies in recent years, research and applications in computer-aided design (CAD), computer animation, digital entertainment and digital art have been receiving increasing attention from researchers across the world. The aim of this special issue of ComSIS is to further promote the development of those areas to benefit their applications in various fields.

This special issue is a collection of 19 papers selected from the 426 submissions to the 6th Conference on Intelligent CAD and Digital Entertainment (CIDE 2009) held in Taian, Shandong, China, from 15 to 17 August 2009. All the papers included in this special issue have gone through a rigorous peer-review and revision process for their originality and quality.

This issue of ComSIS takes the topic of advances in computer animation and digital entertainment as a center. Many of the papers covered mostly theoretical research and various application domains, such as intelligent CAD, computer graphics, computer animation, and motion capture animation.

In photometric stereo, the existence of specularities hampers recovery of the normal map. To deal with this common reflective phenomenon, in the paper “An extended photometric stereo algorithm for recovering specular object shape and its reflectance properties”, Zuoyong Zheng, Lizhuang Ma, Zhong Li and Zhihua Chen introduce a novel representation for specular reflection with a set of specular basis functions with different roughness values. This representation is suitable for any intensively or weakly specular object, and is introduced into the photometric stereo algorithm to recover both the surface shape and its reflectance properties. The reconstructed shapes and re-rendered images validate the proposed algorithm.

The paper “Extracting PCB components based on color distribution of highlight areas” by Zhou Zeng, Lizhuang Ma and ZuoYong Zheng investigates methodologies for locating and identifying the components on a printed circuit board (PCB) used for surface mount device inspection. The proposed scheme consists of two stages: solder joint extraction and protective coating extraction. Solder joints are extracted by first detecting all the highlight areas, and then recognizing and removing the invalid highlight areas. The sequence of color distribution as a new clue has been applied to clustering solder joints. Each protective coating is extracted by the positions of the clustered solder joints.

How to enhance interoperability between stakeholders and improve efficiency of supply chain management is the key issue that needs to be addressed in automobile industry. Yong Zhang, Shijun Liu, Lei Wu, Yuchang Jiao, Xiangxu Meng propose a methodology that provides a guide on how to establish interoperability between enterprises through a federated approach in “Service-oriented enterprise interoperability in automobile supply chain management”. An interoperability service platform is designed and delivered in the form of software as a service (SaaS). This paper introduces the specifications of the service platform and proposes an interactive framework which is used to establish interoperability between the service platform and other on-premise applications.

Spherical mobile robot (SMR) has been studied analytically and experimentally in the paper “Modeling and simulation of a Spherical Mobile Robot” by Shengju Sang, Jichao Zhao, Hao Wu, Shoujun Chen and Qi An. A novel design with an internal propulsion mechanism and mathematical models of the robot’s dynamics and kinematics is introduced.

Based on feature point and core extraction by the multi-dimensional scaling (MDS) transformation, Xiaopeng Sun, J. Pan and Xiaopeng Wei present a novel skeleton extraction algorithm in their paper“3D Mesh Skeleton Extraction Using Prominent Segmentation”.

The paper “A Dynamic Alignment Algorithm for Imperfect Speech and Transcript” by Ye Tao, Xueqing Li and Bian Wu presents a novel alignment approach for imperfect speech and the corresponding transcription. It starts with multi-stage sentence boundary detection in audio, followed by a dynamic programming based search, to find the optimal alignment and detect the mismatches at sentence level.

Multi-video summarization is a great theoretical and technical challenge due to the wider diversity of topics in multi-video than single-video as well as the multi-modality nature of multi-video over multi-document. Dongming Jiang, Jian Shao and Lu Yao in their paper “Multi-video summarization using complex graph clustering and mining” propose an approach to analyze both visual and textual features across a set of videos and to create a so-called circular storyboard composed of topic-representative keyframes and keywords.

Xiaopeng Wei, Boxiang Xiao and Qiang Zhang present a retrieval method for human Mocap (motion capture) data based on biomimetic pattern recognition in their paper “A retrieval method for human Mocap data based on biomimetic pattern recognition”. BVH rotation channels are extracted as features of motion for both the retrieval instance and the motion data. Several hyper sausage neurons are constructed according to the retrieval instance, and the trained domain covered by these hyper sausage neurons can be considered as the distribution range of a same kind of motions.

The paper “Generative 3D Images in a visual evolutionary computing system” by Hong Liu presents a novel computer-aided design system which uses a computational approach to producing 3D images for stimulating the creativity of designers.

Dimensionality reduction is an important preprocessing step in high-dimensional data analysis without losing much intrinsic information. Zhao Zhang and Ning Ye in their paper “Effective semi-supervised nonlinear dimensionality reduction for wood defects recognition” consider the problem of kernel based semi-supervised nonlinear dimensionality reduction, which is called KNDR. It can project the data onto a set of ‘useful’ features and preserve the structure of labeled and unlabeled data as well as the constraints defined in the embedded spaces, under which the projections of the data can be effectively partitioned from each other.

Multi-feature index tree (MFI-Tree), a new indexing structure, is proposed to index multiple high-dimensional features of video data for video retrieval through example in the paper “MFI-Tree: An effective multi-feature index structure for weighted query application” by Yunfeng He and Junqing Yu. The MFI-Tree employs a tree structure which is beneficial for the browsing application, and retrieves the last level cluster nodes in retrieval application to improve performance. Aggressive decided distance for kNN (ADD-kNN) search algorithm is designed because it can effectively reduce the distance to prune the search space.

According to the different requests of the Web and the heterogeneity of Web servers, Zhang Lin, Li Xiao-Ping and Su Yuan in their paper “A Content-based dynamic load-balancing algorithm for heterogeneous Web server cluster” present a content-based load-balancing algorithm. The mechanism of this algorithm is that a corresponding request is allocated to the server with the lowest load according to the degree of effects on the server and a combination of load state of the server. Furthermore, the algorithm applies a method of random distributing base-probability to assign each request to an appropriate server in terms of their weight.

Increased attention has been given to blind source separation in signal processing, which aims to recover independent sources from their linear instantaneous mixtures without resorting to any prior knowledge. In the paper “Blind separation using second order statistics for non-stationary signals”, Jun Du, Ju Liu, Shengju Sang and Jun Wang propose a new simple BSS technique that exploits second order statistics for non-stationary sources. They use the algebraic structure of the signal model and the subspace structures in order to efficiently recover sources with interference of noise.

Jianfeng Liu, Zhigeng Pan and Xiangcheng Li in their paper “An Accelerometer-Based Gesture Recognition Algorithm and its Application for 3D Interaction” propose an accelerometer-based gesture recognition algorithm. Raw data output by accelerometer should be quantized, and then trained and recognized by discrete Hidden Markov Model. Based on this, they treat gesture as a method of human-computer interaction and use it in 3D interaction subsystem in VR system named VDOM by following steps: establish Gesture-Semantic Map, train standard gestures, finally do recognition.

As a video coding standard, H.264 achieves high compress rate while keeping good fidelity. Haitao Wei, Junqing Yu, and Jiang Li in their paper “The design and evaluation of hierarchical multi-level parallelisms for H.264 encoder on multi-core architecture” propose a hierarchical multi-level parallelisms (HMLP) framework for the H.264 encoder which integrates four level parallelisms – frame-level, slice-level, macroblock-level and data-level – into one implementation. According to the analysis of coding performance on each level parallelism, they propose a method to combine different parallel levels to attain a good compromise between high speedup and low bit-rate.

Ding Ying, Li Wen-Hui, Fan Jing-Tao and Yang Hua-Min present a novel method to robustly and efficiently detect moving objects, even under complex backgrounds, such as those consisting of illumination changes, long shadows, etc. in “Robust moving object detection under complex background”. They integrate the local binary pattern texture measure to extend the moving object detection work for light illumination changing, then introduce HSI color space measure for removing shadows for the background subtraction. Moreover, a novel fuzzy approach using the Choquet integral improves detection accuracy.

Since classification error accumulation in hierarchical methods impacts classification accurracy, in the paper “A novel hierarchical speech emotion recognition method based on improved DDAGSVM”, Qi-Rong Mao and Yong-Zhao Zhan propose a novel hierarchical method based on improved decision directed acyclic graph SVM for speech emotion recognition. The improved DDAGSVM is constructed according to the confusion degrees of emotion pairs. In addition, a geodesic distance-based testing algorithm is proposed for the improved DDAGSVM to give the differently distinguished test samples many decision chances.

Diagnosis strategy is a testing sequence of fault detection and isolation. For the distribution of electronic equipment, Wang Hongxia, Ye Xiaohui and Wang Liang in their paper “Research on optimizing the fault diagnosis strategy of complex electronic equipments” put forward a feasible engineering maintenance method based on the questions of test point selection and diagnosis strategy.

Xiaopeng Wei, Xiaoyong Fang, Qiang Zhang and Dongsheng Zhou propose a new method for matching two 3D point sets of identical cardinality with global similarity but local non-rigid deformations and distribution errors in their paper “3D point pattern matching based on spatial geometric flexibility”. To establish one-to-one identification, they introduce a forward 3D point pattern matching (PPM) method based on spatial geometric flexibility, which considers a non-rigid deformation between the two point-sets.

I would like to give my great thanks to the reviewers for their helpful comments and all of the authors for their contributions, efforts and enthusiasm. Thanks are also due to the ComSIS Consortium, and especially to the Editor-in-Chief of ComSIS, Mirjana Ivanović and other staff in the Editorial Office for their advice and help in making this special issue possible.

Guest Editor
Prof. Qiang Zhang
Key Laboratory of Advanced Design
and Intelligent Computing (Dalian University)
Ministry of Education
Dalian 116622, China
zhangq@dlu.edu.cn