Transactions on Computational Science XXVI

We propose an image-based virtual try-on system for garments in order to reproduce the appearance of try-on during online shopping. Given whole-body images of a fashion model and a customer, we cut out a garment image from the fashion model image and reshape it so that it fits to the body shape of the customer. The reshaping function is estimated automatically from the body contours of the fashion model and the customer. The fitting result is refined further by automatic color correction with reference to the facial regions and a method of retouching parts that protrude from the rear of the garment image. We verified the effectiveness of our system through a user test.

The creation of building models has high importance, due to the demand for detailed buildings in virtual worlds, games, movies and geo information systems. Due to the high complexity of such models, especially in the urban context, their creation is often very demanding in resources. Procedural methods have been introduced to lessen these costs, and allow to specify a building (or a class of buildings) by a higher level approach, and leave the geometry generation to the system. While these systems allow to specify buildings in immense detail, roofs still pose a problem. Fully automatic roof generation algorithms might not yield desired results (especially for reconstruction purposes), and complete manual specification can get very tedious due to complex geometric configurations. We present a new method for an abstract building specification, that allows to specify complex buildings from simpler parts with an emphasis on assisting the blending of roofs.

Non-rigid 3D shape correspondence is a fundamental and challenging problem. Isometric correspondence is an important topic because of its wide applications. But it is a NP hard problem if detecting the mapping directly. In this paper, we propose a novel approach to find the correspondence between two (nearly) isometric shapes. Our method is based on the geodesic structure of the shape and minimum cost flow. Firstly, several pre-computed base vertices are initialized for embedding the shapes into Euclidian space, which is constructed by the geodesic distances. Then we select a serials of sample point sets with FPS. After that, we construct some network flows separately with the level point sets of the two shapes and another two virtual points, source point and sink point. The arcs of the network flow are the edges between each point on two shapes. And the \(L_2\) distances in the k dimensional Euclidian embedding space are taken as the arc costs and a capacity value is added on each point in the above network flow. At last we solve the correspondence problem as some minimum cost max flow problems (MCFP) with shortest path faster algorithm (SPFA), and combine the results of these MCFP as the last correspondence result. Experiments show that our method is accurate and efficient for isometric, nearly isometric and partially shapes.

NeuroFeedback Training (NFT) can be used to enhance cognitive abilities in healthy adults. In this paper, we propose and implement a neurofeedback system which integrates an individual theta/beta based neurofeedback algorithm in a “Shooting” game. The system includes an algorithm of calculation of an Individual Alpha Peak Frequency (IAPF), Individual Alpha Band Width (IABW) and individual theta/beta ratio. Use of the individual theta/beta ratio makes the neurofeeback training more effective. We study the effectiveness of the proposed neurofeedback system with five subjects taking 6 NFT sessions each. As the neurofeedback protocol based on the power of individual theta/beta ratio training is used, each neurofeedback training session includes an IAPF, IABW and individual theta/beta ratio calculation. Subjects play the “Shooting” game to train cognitive abilities. The feedback on the player’s brain state is given by the color of the shooter’s target. If the target turns from “blue” to “red”, the player is in the “desired” brain state and is able to shoot. IAPF and IABW parameters calculated before and after NFT sessions are used for neurofeedback efficiency analysis. Our hypothesis is that after the neurofeedback training by playing the “Shooting” game, the individual alpha peak frequency increases. The results show that all subjects overall have a higher individual alpha peak frequency values right after the training or the next day.

In shape analysis, scaling factors have a great influence on the results of non-rigid shape retrieval and correspondence. In order to eliminate the effects of scale ambiguity, a method with scale-invariant property is required for shape analysis. Previous mapping method only focus on the isometric conditions. In this paper, a Scale-invariant Heat Kernel Mapping (SIHKM) method is introduced, which bases on the heat diffusion process on shapes. It is capable of handling various types of 3D shapes with different kinds of scaling transformations. SIHKM is the extension of the Heat Kernel and related to the heat diffusion behavior on shapes. With SIHKM, we will obtain the intrinsic information from the scaled shapes while without regard to the impact of their scaling. SIHKM method maintains the heat kernel between two corresponding points on the shape with scaling deformations. These deformations include scaling transformation only, isometric deformation and scaling, and local scaling on shapes. The proof of the theory and experiments are given in this work. All experiments are performed on the TOSCA dataset and the results show that our proposed method achieves good robustness and effectiveness for scaled shape analysis.

The HeritageTogether project has developed a web platform through which members of the public can upload their own photographs of heritage assets to be processed into 3D models using an automated Structure-from-Motion work flow. The web platform is part of a larger project which aims to capture, create and archive digital heritage assets in conjunction with local communities in Wales, UK, with a focus on megalithic monuments. The 3D models are displayed online using a lightbox style gallery and a virtual museum, while the large amounts of additional data produced are stored in an online archive. Each representation provides a different perspective and context to the data, allowing users to explore the data in a multitude of ways. HeritageTogether is a digital community and community-built archive and museum of heritage data, developed to inspire local communities to learn more about their heritage and to help to preserve it.

In recent years, the mass growth of online social networks has introduced a completely new platform of analyzing human behavior. Human interactions via online social networks leave big trails of behavioral footprints, which have been investigated by many researchers for the purpose of targeted advertising and business. However, analysis of such online interactions is rarely seen for user identification. The main objective of this paper is to analyze individuals’ online interactions as biometric information. In this paper, we investigated how online interactions retain behavioral characteristics of users and how consistent they are over time. For this purpose, we proposed a novel method of identifying users from online interactions in Twitter. Identification performance has been evaluated on a database of 50 Twitter users over five different time periods. We obtained very promising results from experimentation, which demonstrate the potential of online interactions in aiding the authentication process of social network users’.

In surveillance system, the video data has received a great deal of attention, instead of Mocap data, there has enough no work on recognizing of human through this data. Most Surveillance system monitors the behavior, activities, or other changing information in surrounding real life; usually it is used to recognize people to the purpose of security issues in society. This paper aims to propose a novel approach of human identification, which based on sensor data acquired by an optical system. Three joints of the human body, such as the hip, knee, and ankle joint have been selected by the amount of gait movement in this algorithm. By extracting suitable 3D static and dynamic joints feature from data. The Parametric Bezier Curve(PBC) technique applies on the extracted features in order to derive the strong correlation between joint movements. The curve control points are used to construct the triangles of each walking pose. After that centroid of triangle method apply on constructed triangle to compute a 3D center value. Selecting a triangle which has minimum distance between original pose triangle and recursive triangle center value. We then employed the geometric function to compute the area of each walking pose triangle(gait signature). Furthermore, we optimized the gait signature by using statistical moment on computed areas. After an accurate analysis the signature and found that is has a unique relationship among the 3D human gaits, and use this signature as to classify the human identification. The experiments demonstrated on IGS-90 and Vicon motion capture system data that is proved that proposed method is more accurate and reliable results.

This study seeks to identify the effects gameplay has on leadership behaviors and establish how video games can be use as a didactic tool for leadership development. The leadership behaviors, present in both multiplayer online battle arena games (MOBA) and the real world, are identified. A self-report questionnaire that categorizes respondents’ game roles (carry, support, ganker) and real-world leadership styles (autocratic, democratic, laissez-faire) was conducted. Through contingency leadership theory, this study found that the continuous practice of specific game roles in MOBAs facilitates development of real-world leadership styles. Effects of gameplay on leadership behaviors were estimated using propensity score matching and doubly robust estimation. The empirical analyzes revealed that game players who predominantly play a specific role in games exhibit stronger real-world behaviors of the corresponding leadership style. This study concludes that playing video games helps improve leadership skills and leadership style development.

Face recognition is biometric pattern recognition, which is more acceptable and convenient for users compared with other biometric recognition traits. Among many problems in face recognition system, pose problem is considered as one of the major problem still unsolved in satisfactory level. This paper proposes a novel pose tolerant face recognition approach which includes feature extraction, pose transformation learning and recognition stages. In the first stage, 2DPCA is used as robust feature extraction technique. The linear regression is used as efficient and accurate transformation learning technique to create frontal face image from different posed face images in the second stage. In the last stage, Mahalanobis distance is used for recognition. Experiments on FERET and FEI face databases demonstrated the higher performance in comparison with traditional systems.