• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.368-391
• /
• 2018

Face recognition (FR) with a single sample per person (SSPP) is common in real-world face recognition applications. In this scenario, it is hard to predict intra-class variations of query samples by gallery samples due to the lack of sufficient training samples. Inspired by the fact that similar faces have similar intra-class variations, we propose a virtual sample generating algorithm called k nearest neighbors based virtual sample generating (kNNVSG) to enrich intra-class variation information for training samples. Furthermore, in order to use the intra-class variation information of the virtual samples generated by kNNVSG algorithm, we propose image set based multimanifold discriminant learning (ISMMDL) algorithm. For ISMMDL algorithm, it learns a projection matrix for each manifold modeled by the local patches of the images of each class, which aims to minimize the margins of intra-manifold and maximize the margins of inter-manifold simultaneously in low-dimensional feature space. Finally, by comprehensively using kNNVSG and ISMMDL algorithms, we propose k nearest neighbor virtual image set based multimanifold discriminant learning (kNNMMDL) approach for single sample face recognition (SSFR) tasks. Experimental results on AR, Multi-PIE and LFW face datasets demonstrate that our approach has promising abilities for SSFR with expression, illumination and disguise variations.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• Journal of Distribution Science
• /
• v.19 no.9
• /
• pp.41-52
• /
• 2021

Purpose: Virtual reality is a unique technology to distribute data and demonstrates user's understanding towards complex products. The objective of this research is to investigate the impact of virtual reality on real world purchase intention of automotive cutting tools in Thailand's exhibitions. Hence, the research framework was constructed by telepresence, perception narrative, authenticity, trustworthiness, functional value, aesthetics, and purchase intention. Research design, data and methodology: Samples were collected from 500 visitors who participated in the selected top two metalworking exhibitions. Mix sampling approach is applied by using non-probability sampling methods of purposive or judgmental sampling, quota sampling, and convenience sampling method, respectively to reach target samples. Confirmatory Factor Analysis (CFA) and Structural Equation Model (SEM) were used to analyze and confirm goodness-of-fit of the model and hypothesis testing. Results: The results indicate that authenticity, functional value, and trustworthiness induced higher experiential value towards purchase intention. Those variables are stimulated by telepresence and perception narrative towards VR experience. Conclusions: Consumer's purchase intention towards VR experience on engineering cutting tools rely on consumer's sense of authenticity, trustworthiness, and functional value. Hence, marketing practitioners in automotive companies are encouraged to develop VR which focusing on significant factors to enhance consumers purchase intention.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.7
• /
• pp.3172-3193
• /
• 2018

Recently, several studies have shown that linear representation based approaches are very effective and efficient for image classification. One of these linear-representation-based approaches is the Collaborative representation (CR) method. The existing algorithms based on CR have two major problems that degrade their classification performance. First problem arises due to the limited number of available training samples. The large variations, caused by illumintion and expression changes, among query and training samples leads to poor classification performance. Second problem occurs when an image is partially noised (contiguous occlusion), as some part of the given image become corrupt the classification performance also degrades. We aim to extend the collaborative representation framework under limited training samples face recognition problem. Our proposed solution will generate virtual samples and intra-class variations from training data to model the variations effectively between query and training samples. For robust classification, the image patches have been utilized to compute representation to address partial occlusion as it leads to more accurate classification results. The proposed method computes representation based on local regions in the images as opposed to CR, which computes representation based on global solution involving entire images. Furthermore, the proposed solution also integrates the locality structure into CR, using Euclidian distance between the query and training samples. Intuitively, if the query sample can be represented by selecting its nearest neighbours, lie on a same linear subspace then the resulting representation will be more discriminate and accurately classify the query sample. Hence our proposed framework model the limited sample face recognition problem into sufficient training samples problem using virtual samples and intra-class variations, generated from training samples that will result in improved classification accuracy as evident from experimental results. Moreover, it compute representation based on local image patches for robust classification and is expected to greatly increase the classification performance for face recognition task.

• Journal of Information Technology Applications and Management
• /
• v.10 no.3
• /
• pp.121-142
• /
• 2003

Most of companies related to the area of B2B electronic commerce are making their efforts to innovate their existing business process into new designed process based on the concept of virtual enterprise. Virtual enterprise can take on many forms and definitions. Nevertheless, the rationale for this business model is clear cooperate to compete, the virtual organization advocates collaboration, partnerships, alliance and similar ideas. This studyintends to suggest an empirical clue to test several hypotheses related to the influence of environmental. organizational, and technological factor to the successful implementation of virtual enterprise in automobile industry. This research surveyed 91 corporations in Korean automobile part industry. Among those samples 86 data of corporate general managers turned out to be statistically valid. This study performed the factor analysis, Cronbach-alpha test. Pearson correlation analysis for testing the validity and the reliability of this research. The results of factor analysis and reliability test indicate that thirty issues to be surveyed are to be grouped into nine factors. The result of multiple regression shows that the influencing factors of eight independent variables on a dependent variable are cooperation between partners, information intensity, IT compatibility, IS maturity. The partners in the strategic alliance will have to trust each other in carrying out their designated roles and responsibilities. and supplying the correct information critical for creating value in virtual business environment.

• Journal of the Korean Society of Costume
• /
• v.65 no.1
• /
• pp.104-117
• /
• 2015

Recently, the fashion industry has been integrating with The IT industry in order to develop in various ways. This study looks into ways to utilize the 3D CAD system, which would reduce time and cost while producing samples, and strengthen the communication between the brand and its cooperators by deploying knit designs using Knit CAD system's 3D virtual clothing program. The research method was reference, Internet resources 3D fashion CAD system and 3D Knit CAD system. Based on the data, simulation of the complete design of 4 deployed knit designs was done by using 3D virtual clothing program of the Knit CAD system utilizing knit design elements. One of each design element among the virtual clothing designs was chosen to produce real clothing, and the experts did verification on the appearance assessment of 3D virtual clothing knit designs of the Knit CAD system. As a result, 3D virtual clothing knit design of the Knit CAD system proved itself as an efficient system in terms of time and cost.

• Fashion & Textile Research Journal
• /
• v.23 no.2
• /
• pp.247-260
• /
• 2021

While it is an important element of clothing construction, research has so far been very limited on the similarities between virtual and real clothing in terms of the type of neckline. The purpose of this study is to verify the similarity, accuracy of virtualization, and actuality of neckline, which all play an important role in individual impressions and image formation, and require considerable modification when fitting real samples. A total of 5 neckline models were selected through the analysis of dress composition textbooks. The selected designs were then planned and manufactured in muslin. The specimen clothes were then tested on a female model in her 20s. 2 kinds of virtual bodies were created in order to compare the real and the virtual dressing. The first virtual body was made through an Artec 3D Eva scan of the model, and the other was made by entering the model's measurements in a CLO 3D program. A visual image of the front, side, and back image of both the real and virtual dressing were subsequently collected. The collected images were then evaluated by 20 professional fashion workers who checked the similarity between the real and the virtual versions. The current study found that the similarity between the actual and virtual wearing of the five neckline designs with reality appeared higher with the virtual wearing image using the 3D-scanned body. The results of this study could provide further information on the selection of appropriate avatars to clothing companies that check the fit of clothing by utilizing 3D virtualized programs.

• Fashion & Textile Research Journal
• /
• v.13 no.3
• /
• pp.390-397
• /
• 2011

This study investigates the influences of shopping enjoyment and risk reduction on customers' attitude and the behavioral intention in the Internet shopping mall using a moving virtual model. For this study, we produced a moving virtual model to present a fashion product. The virtual model walks for about one minute on the stage. After respondents viewed it, they completed a questionnaire. The questionnaire consists of online shopping enjoyment, risk reduction, customers' attitude and behavioral intention. Respondents are limited to females aged in their 20s and 30s, who have experienced Internet shopping and are highly interested in fashion products. 411 samples were used for the final analysis. Cronbach's alpha, factor analysis, and multiple regression analysis were conducted. The results are as follows. Online shopping enjoyment and risk reduction influenced the behavioral intention directly as well as through the attitude. However, the size of the influence indicated that online shopping enjoyment is larger than risk reduction. Therefore, Internet malls should utilize the moving virtual model to provide customers with enjoyment and risk reduction, which will increase customers' favorable attitudes and the behavioral intention such as purchase intention and word of mouth.

• Journal of Distribution Science
• /
• v.19 no.7
• /
• pp.113-121
• /
• 2021

Purpose: Technology induces the virtual distribution channel to exist, especially for booking a room online. This situation, indeed, provides an alternative for the customers to book based on their budget through digital platforms. One platform offering competitive prices is virtual hotel operators, such as Airbnb, OYO, RedDoorz, and Airy Rooms. Preferably, after using their platform, the user should be satisfied and loyal. Hence, this investigation aims to prove some associations. The first is between e-satisfaction and e-loyalty. The second is between website quality and e-satisfaction. The final is between website quality and e-loyalty. Research design, data, and methodology: This study is quantitatively designed with the sample of 350 users of the virtual hotel operator applications in Bandar Lampung: Airbnb, OYO, RedDoorz, and Airy, as the samples. Therefore, by denoting this sample size, the structural equation model based on covariance is utilized to examine the three hypotheses proposed. Also, to get the responses, this study uses a survey through a questionnaire. Result: This investigation demonstrates the positive relationship between e-satisfaction and e-loyalty. Additionally, website quality positively associates with e-satisfaction and e-loyalty. Conclusion: The virtual hotel operators must have the superiority on their website-based application to update the information based on the room availability and price, ensure online transaction safety, and facilitate its utilization to maintain long-term satisfaction and loyalty virtually.

• Fashion & Textile Research Journal
• /
• v.16 no.6
• /
• pp.961-970
• /
• 2014

Several retailers such as Target and Kohle's and their vendors have piloting the 3D clothing simulation programs to produce garment samples. However, few studies have verified the virtual fit information and 3d visualization process for pants, and no study compared the commercial 3D virtual programs. This study is designed to analyze similarity of fit and appearance between real pants with 3D virtual pants based on three 3D virtual programs (Optitex, CLO 3D, and i-Designer), three lower body types (slim, normal, and thick waist type), and fit status. We selected a representative model for each lower body type, produced their custom pants according to Lee and Nam's method(2007), and took photos of front, side and back view for visual analysis. Then, we virtually tried each model's custom pants on her parametric avatar developed by manually inputting their body measurements using the three 3D virtual program. Thirty fit experts compared the real fit to virtual fit. This study found that 'Optitex' and 'i-Designer' can visualize more effectively than 'CLO 3D' in many fit locations. Regarding the body types, 3D virtual program can visualize pants fit for 'thick waist body type' more preciously than the other body types. With respect to fit status, it does not affect much on the similarity overall.