• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.166-179
• /
• 2021

Recently, with the development of technology, computer vision research based on the human visual system has been actively conducted. Saliency maps have been used to highlight areas that are visually interesting within the image, but they can suffer from low performance due to external factors, such as an indistinct background or light source. In this study, existing color, brightness, and contrast feature maps are subjected to multiple shape and orientation filters and then connected to a fully connected layer to determine pixel intensities within the image based on location-based weights. The proposed method demonstrates better performance in separating the background from the area of interest in terms of color and brightness in the presence of external elements and noise. Location-based weight normalization is also effective in removing pixels with high intensity that are outside of the image or in non-interest regions. Our proposed method also demonstrates that multi-filter normalization can be processed faster using parallel processing.

• 한국의류산업학회지
• /
• 제20권3호
• /
• pp.293-303
• /
• 2018

Since 2009, consumers could access a new shopping channel called 'mobile shopping' with the generalization of smartphones. Mobile shopping (based on wireless communication technology), emphasizes convenience differentiated from internet shopping. A recent report introduced fashion products as powerful global drivers for mobile shopping sales. Korea and China have the highest percentage of consumer mobile shopping experiences compared to other countries. This study investigates the effects of cross-over shopping orientation, perception of app attributes, and flow on app loyalty that compared Korean and Chinese consumers. We obtained 652 usable questionnaires from two local college students; subsequently, data were analyzed by using factor analysis, Cronbach's alpha, and regression analysis using SPSS 21.0 Package. The study results showed that the cross-over shopping orientation affected perception of app attributes that included Review/Information, Design, Response and Product. Product only affected Flow, which reflected a high similarity between Korean and Chinese consumers. However, Korean and Chinese consumers showed remarkable differences in the factors related to app loyalty. Therefore, the results indicate that retailers of fashion products have developed strategies to improve mobile sales and increase the app loyalty of cross-over shopping orientation consumers.

• 한국의류산업학회지
• /
• 제22권1호
• /
• pp.25-37
• /
• 2020

This study investigates the clothing purchase behavior of active seniors in their 50s and 60s. Differences of clothing purchase behaviors were examined according to gender and the group classified by shopping orientation. Data were collected from September 2 to September 9, 2019 using a professional internet research panel; subsequently, 246 sets of useful data were analyzed by descriptive statistics, factor analysis, reliability analysis, t-test, chi-squared test, ANOVA and Duncan-test using SPSS 21.0. The results of this study were as follows. First, there were significant differences in clothing purchase behavior of purchase frequency, purchase item, purchase price, and purchase channel according to gender; therefore marketers need plan different merchandising and retailing strategies between man's wear and woman's wear. Second. the result of cluster analysis by shopping orientation showed that active seniors were categorized into four groups including 'active shopping pursuit', 'economic/pleasure pursuit', 'convenience/brand pursuit', and 'passive shopping pursuit'. Third, there were significant differences in demographic variables such as gender and occupation according to four categorized groups. In addition, the significant differences of clothing purchase behaviors were verified according to four groups. 'Active shopping pursuit' group was shown to make the best use of offline channels and online channels in information research and product purchase.

• 한국의상디자인학회지
• /
• 제20권1호
• /
• pp.183-197
• /
• 2018

This study examined outdoor sports wear purchase behaviors among middle-aged male consumers based on outdoor sports wear shopping orientation. Data research was conducted on 300 internet users in their 40s and 50s located all parts of the country. The SPSS 24.0 software program was used to conduct data analyses such as descriptive statistics, frequency analysis, factor analysis, cluster analysis, $x^2-test$, t-test, ANOVA, and Duncan test as a post-hoc analysis. The results of this study were as follows: Firstly, outdoor sports wear shopping orientation was identified with fivefactors : the tendencies of wanting to show off a brand name, conservative purchasing, economical purchasing setting a high value on a salesperson, and impulse purchasing. Secondly, the middle-aged male consumers were classified in to three groups by the cluster analysis: a rational group, an indifferent shopping group, and pursuit brand shopping group. Thirdly, the evaluation criteria of products were significantly different depending on outdoor sports wear shopping orientation subdivision in all factors. Fourthly, in the case of fashion information sources regarding outdoor sportswear, significant differences were found according to shopping orientation subdivision in mass media/store source, personal source/ prior shopping experience. Fifthly, all types of stores were significantly different depending on shopping orientation subdivision except for large discount stores.

• Asia pacific journal of information systems
• /
• 제17권3호
• /
• pp.25-53
• /
• 2007

The Expectation Confirmation Model (ECM) of information systems investigates the continued information systems usage behavior. This paper expands the original post-adoption beliefs and searches the applications in the emerging hedonic information systems. Previous IS researches focused on the organizational environments. However as the information technology (especially internet) evolves, information systems have not only emerged for the organizations but also for the individual users, such as internet portals, internet communities, on-line games etc. These information systems so called Hedonic Information Systems aims to provide self-fulfilling value rather than instrumental value to the users. Researches in other disciplines, including marketing and consumer behavior research, illustrate that the hedonic and utilitarian perspective of goods and services have different influence on the consumer behavior. Goods and services used to be classified into either hedonic or utilitarian aspect but now they may belong to both aspects simultaneously. Moreover consumer's goals or tasks have both hedonic utilitarian aspects. When a consumer makes a decision to purchase or repurchase goods or services, he/she compares the hedonic and utilitarian perspectives of goods to find most suitable ones to satisfy their goals/tasks. Finally, consumer's behavior is determined by the trade-off between what the goods can provide to the consumers and in what extent the goods fulfill consumer's purchase behavior. Consumer also shows that the salience of hedonic perspective is relatively greater when consumer decides which of several items to give up (forfeiture choices) than the time when they decide which item to acquire (acquisition choices). Some researches in MIS discipline have found out that the information systems also have both hedonic and utilitarian perspectives. The decision process of whether to use information systems or not is similar to that of a consumer's decision of purchasing or repurchasing goods or services. However most of researches in MIS tend to focus on the extrinsic motivation variables which only cover the utilitarian perspective of information systems. It is only recent that researches start to investigate the intrinsic motivation variable - Perceived Enjoyment - for the hedonic perspective. Considering the consumer's purchasing decision process, users of information systems evaluate the systems through balancing between intrinsic (hedonic) and extrinsic (utilitarian) variables according to their main tasks or tendencies. This paper proposes a model that is based on the ECM of IS Continuance model modified from Expectation Confirmation Model to fit into the continued usage of information system. It first started from the decision process regarding hedonic and utilitarian perspectives in the consumer behavior literatures. The model deals with continued usage of information systems beyond the mere technology adoption as in most of the previous MIS researches. This research is particularly important to the hedonic information systems, because their business model depends on the frequent usages rather simple adoption at the beginning. Because the basic model only considered the extrinsic motivations (perceived usefulness) to explain the users' behavior and as the information systems can have both hedonic and utilitarian dimensions, it should consider both perspectives. Therefore, this newly proposed model considers intrinsic variable (perceived enjoyment) as well. Since the individual user can have a preference on either aspects that is between the hedonic and utilitarian perspective depending on his/her main tasks or goals, some variables (Hedonic Orientation and Utilitarian Orientation) meaning the extents of users' pursuing from the information system were additionally studied.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제4권3호
• /
• pp.305-323
• /
• 2010

This paper proposes an efficient and yet powerful local descriptor called phase-space partition based descriptor (PPD). This descriptor is designed for the mobile image matching and retrieval. PPD, which is inspired from SIFT, also encodes the salient aspects of the image gradient in the neighborhood around an interest point. However, without employing SIFT's smoothed gradient orientation histogram, we apply the region based gradient statistics in phase space to the construction of a feature representation, which allows to reduce much computation requirements. The feature matching experiments demonstrate that PPD achieves favorable performance close to that of SIFT and faster building and matching. We also present results showing that the use of PPD descriptors in a mobile image retrieval application results in a comparable performance to SIFT.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권9호
• /
• pp.4355-4374
• /
• 2018

Crowd escape event detection has become one of the hottest problems in intelligent surveillance filed. When the 'escape event' occurs, pedestrians will escape in a disordered way with different velocities and directions. Based on these characteristics, this paper proposes a Direction-Collectiveness Model to detect escape event in crowd scenes. First, we extract a set of trajectories from video sequences by using generalized Kanade-Lucas-Tomasi key point tracker (gKLT). Second, a Direction-Collectiveness Model is built based on the randomness of velocity and orientation calculated from the trajectories to express the movement of the crowd. This model can describe the movement of the crowd adequately. To obtain a generalized crowd escape event detector, we adopt an adaptive threshold according to the Direction-Collectiveness index. Experiments conducted on two widely used datasets demonstrate that the proposed model can detect the escape events more effectively from dense crowd.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권8호
• /
• pp.3011-3024
• /
• 2021

Pose estimation of the sensor is important issue in many applications such as robotics, navigation, tracking, and Augmented Reality. This paper proposes visual-inertial integration system appropriate for dynamically moving condition of the sensor. The orientation estimated from Inertial Measurement Unit (IMU) sensor is used to calculate the essential matrix based on the intrinsic parameters of the camera. Using the epipolar geometry, the outliers of the feature point matching are eliminated in the image sequences. The pose of the sensor can be obtained from the feature point matching. The use of IMU sensor can help initially eliminate erroneous point matches in the image of dynamic scene. After the outliers are removed from the feature points, these selected feature points matching relations are used to calculate the precise fundamental matrix. Finally, with the feature point matching relation, the pose of the sensor is estimated. The proposed procedure was implemented and tested, comparing with the existing methods. Experimental results have shown the effectiveness of the technique proposed in this paper.

• 복식문화연구
• /
• 제21권5호
• /
• pp.671-683
• /
• 2013

The purpose of this study was to identify middle-school boys' purchase behavior according to their shoes shopping orientation. A self-administered questionnaire was used to collect from 314 subjects. Factor analysis, Chi-square test, and one-way ANOVA were done using SPSS PC (Ver. 18.0). Most middle-school boys selected shoes that were 255~270mm, possessed on to two pairs of school shoes, searched for information for about five days before purchase, had spent 50,000~150,000 won on one to two pairs of shoes during the previous six months, saw design, comfort, and brand as their selection criteria, chose their shoes by themselves, shoes specialty stores, had favorite brands, preferred athletic shoes made of achromatic canvas, and bought new shoes when their old ones wore out. Factors of shoe shopping orientation were fashion and brand, economy, conformity, and comfort, and students were grouped into an active shopping group, an underdeveloped shopping orientation group, and a value pursuit group. The active shopping group bought more shoes, spent more on shoes, selected their shoes themselves, patronized discount shoe stores or specialty stores, and preferred national brand shoes. The underdeveloped shopping orientation group accepted their friends' opinions when selecting shoes and bought cheaper shoes. The value pursuit group accepted their parents' opinions when selecting shoes, patronized internet shopping malls or traditional markets, and selected cheaper shoes. The shoe shopping orientation of middle-school boys was immature, but they showed strong consumption needs.

• 마케팅과학연구
• /
• 제8권
• /
• pp.61-87
• /
• 2001

인터넷 가상환경에 존재하고있는 온라인 쇼핑몰은 새로운 거래유형을 정착시키기 위한 다양한 노력을 기울이고 있으며 새로운 환경에 걸 맞는 생존모델의 구축에 더할 나위 없는 노력을 경주하고 있다. 이러한 측면에서 온라인 쇼핑몰에게는 고객을 유지해야할 필요를 느끼고 있으며 다양한 마케팅적 접근이 시도 되도 있다 본 연구는 인터넷 쇼핑몰의 구축에 있어서 다양한 구성환경 특성을 바탕으로 고객유지에 영향을 미치는 변수를 찾고자 시도하였다 이러한 발상의 바탕으로 고객이 쇼핑의 행동을 직 접적으로 행하는 데 있어서 핵심적인 효과인 쇼핑가치의 틀을 동원하고자 한다. 즉 인터넷 쇼핑몰의 특성이 쇼핑가치에 영향을 미칠 수 있게 구성된다면 쇼핑가치로 인해서 고객은 유지될 수 있다고 연구의 구성을 설정하였다. 본 연구의 결과에 의해 인터넷 쇼핑몰의 구성에 있어서 도구적 틀을 제시하는데 기여하고자 하며 종국적으로 고객의 유지에 대하여 가치를 판단해 보고자 한다. 따라서 본 연구는 인터넷 쇼핑몰의 감성적 특성(디자인, 원격실재감) 웹인지도 기능적 특성(고객배려, 상품검색, 정보제공, 제품가치, 거래시스템)이 쇼핑가치(쾌 락적 쇼핑가치, 실용적 쇼핑가치)와 고객유지(신뢰, 고객만족, 관계지향)에 어떤 영향을 미치는가를 분석하였다. 분석결과 웹인지도, 고객배려, 정보제공은 기각되었으며 그 외 변수는 채택되었다