Outfit Browser – An Image-data-driven User Interface for Self-service Systems in Fashion Stores
TL;DR: In this paper, a visual interface for browsing a fashion product range based on visual preferences is presented, where a selected fashion product is placed in the middle of the screen and similar products in the surrounding environment comparable to terms in a tag cloud.
About: This article is published in Procedia Manufacturing.The article was published on 2015-01-01 and is currently open access. It has received 6 citations till now. The article focuses on the topics: User interface & Service (business).
Citations
More filters
Journal Article•
TL;DR: Face detection based on Adaboost and cascade classifier and face detection which is combined effectively with tracking algorithm based on CamShift is proposed and can operate successfully detection and tracking in scale variation, view variation or occlusion.
Abstract: Face detection based on Adaboost and cascade classifier are studied in this paperHaar-Like features, computing method of integral image,detail definition of micro structural features and their description modes are discussedThe computing methods of four different kinds of rectangle features are also givenMoreover,color histogram is the feature of tracking,and face detection based on Adaboost which is combined effectively with tracking algorithm based on CamShift is proposedTo evaluate the performance of the proposed method,experiments have been conducted on video sequencesExperimental results show this proposed method can operate successfully detection and tracking in scale variation,view variation or occlusion
50 citations
01 Jan 2020
TL;DR: A unified framework for outfit design and advice is proposed using Unified Modelling Language (UML) diagrams and notations, which are globally recognised and can be leveraged by online fashion stores to better serve their customers and can also be implemented as a mobile app to give suitable advice to its end users.
Abstract: The application of technology in the apparel industry has received significant attention from the research community in recent times. Technology is being leveraged to support the various processes in the supply chain of the industry. On the consumer side, choosing the right outfit for occasions can be quite challenging. It is for this reason that researchers have proposed a number of fashion recommender systems in the literature. Although the proposals in literature cover a number of areas, they are yet to touch on recommendation based on weather. It is also important to harmonise all of the proposals into a unified framework that will help guide developers. The aim of this study therefore is to propose a unified framework for outfit design and advice. The framework is developed using Unified Modelling Language (UML) diagrams and notations, which are globally recognised. In addition, a prototype of an aspect of the framework has also been implemented as proof of concept. We believe that this framework can be leveraged by online fashion stores to better serve their customers and can also be implemented as a mobile app to give suitable advice to its end users.
7 citations
TL;DR: In this article , the authors examine how phygital luxury experiences can be generated from mobile-mediated service activities while enabling luxury apparel shoppers to attain status goals and hedonic goals.
Abstract: PurposeThe purpose of this study is to examine how phygital luxury experiences can be generated from mobile-mediated service activities while enabling luxury apparel shoppers to attain status goals and hedonic goals. Phygital luxury experiences are defined in this context as shopping experiences that blend the participative and immersive components of mobile and ubiquitous media with physical luxury servicescapes.Design/methodology/approachThis conceptual research draws on activity theory from the field of human-computer interaction to produce an activity-centric model of phygital luxury experiences. By drawing on activity theory, the authors develop research propositions and build a conceptual model. The conceptual model probes how phygital luxury experiences can be generated from mobile-mediated service activities that enable luxury apparel shoppers to attain status goals and hedonic goals. In turn, service activities are proposed to meld with luxury shopping goals when mobile devices allow luxury apparel shoppers to participate in community-, rules-, and labor-based service activities.FindingsFirst, the conceptual model demonstrates that social validation and personalization are status and hedonic drivers for community-based service activities (e.g. content-sharing and multiplatform storytelling). Second, special privileges and new comforts are status and hedonic drivers for rules-based service activities (e.g. engaging in pseudo-webrooming, pseudo-showrooming, and seamless and on-demand resources). Third, know-how and domination are status and hedonic drivers for labor-based service activities (e.g. adopting self-service technologies and smart or intelligent displays).Originality/valueThis conceptual model contributes to the well-documented need for research on interactive luxury strategies and luxury retail innovation. Overall, these service activities provide luxury brands and shoppers new opportunities for building elite communities, bending store rules, and altering the division of labor within physical stores. At the same time, this model shows that exclusivity and allure of luxury consumption can be reproduced through luxury apparel shoppers’ embodied interactions with salespeople and relevant audiences in connected store environments.
3 citations
10 Nov 2014
TL;DR: In this article, the authors propose to lead consumers back to the touch point where they have most influence: the physical POS, and this can happen best, if brands lead their customers back to their physical POS.
Abstract: Traditional brick-and-mortar business is facing several challenges. “Retail companies that want to survive among other retailers will have to make sure their store is more than just a collection of products” (Floor, 2006). Competition is not only driven by other companies but also exists among different sales channels (Brynjolfsson, Hu, and Rahman, 2009). Online business experiences a continuous growth throughout the last years and it is getting harder to reach consumers through traditional channels. Business that previously took place in physical environments now finds itself faced with a variety of new channels. Recent technology merges the real with the virtual world. Particularly in the times of “always on”, consumers perceive the channels that brands provide as one holistic construct. Firms have to keep up with this rapid development in consumer behavior. Today, companies of the modern service-driven economy still strive to be successful by offering a broad choice of products and services (Zagel and Bodendorf, 2012). However, the consumer’s experience with the brand is not only determined by the actual product itself. It is rather a combination of all single experiences gained at each and every touch point. These consist of so-called experiential features that are either of functional/utilitarian or emotional/hedonic nature (Holbrook, 1999; Gentile, Spiller, and Noci, 2007). By evoking fun, pleasure, and other positive emotions during shopping, companies can not only satisfy, but fascinate their consumers over their brands and products. And this can happen best, if brands lead their customers back to the touch point where they have most influence: the physical POS.
2 citations
TL;DR: In this paper, the authors present a systematic mapping study aiming to identify the best ways to present recommendations to users, and the results point to a tendency towards self-explanatory and interactive interfaces.
Abstract: Recommender systems use information about the user to generate a set of personalized items as a suggestion and are applied in contexts where it exists an overload of content available to the user. The way these recommendations are viewed is now the focus of recent studies based on the need to improve the user experience with recommender systems. This paper presents a Systematic Mapping Study aiming to identify the best ways to present recommendations to users. A total of 434 papers were identified, of which 27 were selected for further analysis. The results point to a tendency towards self-explanatory and interactive interfaces.
2 citations
Additional excerpts
...Os autores Piazza et al. (2015) propõe em seu trabalho uma visualização para um Sistema de Recomendação de roupas....
[...]
References
More filters
TL;DR: There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.
Abstract: This paper describes a computational approach to edge detection. The success of the approach depends on the definition of a comprehensive set of goals for the computation of edge points. These goals must be precise enough to delimit the desired behavior of the detector while making minimal assumptions about the form of the solution. We define detection and localization criteria for a class of edges, and present mathematical forms for these criteria as functionals on the operator impulse response. A third criterion is then added to ensure that the detector has only one response to a single edge. We use the criteria in numerical optimization to derive detectors for several common image features, including step edges. On specializing the analysis to step edges, we find that there is a natural uncertainty principle between detection and localization performance, which are the two main goals. With this principle we derive a single operator shape which is optimal at any scale. The optimal detector has a simple approximate implementation in which edges are marked at maxima in gradient magnitude of a Gaussian-smoothed image. We extend this simple detector using operators of several widths to cope with different signal-to-noise ratios in the image. We present a general method, called feature synthesis, for the fine-to-coarse integration of information from operators at different scales. Finally we show that step edge detector performance improves considerably as the operator point spread function is extended along the edge.
28,073 citations
"Outfit Browser – An Image-data-driv..." refers methods in this paper
...Then it is converted into a binary image having only edges of the product by applying theCanny Edge Detection algorithm [11]....
[...]
TL;DR: In this paper, the authors developed and tested a theoretical extension of the TAM model that explains perceived usefulness and usage intentions in terms of social influence and cognitive instrumental processes, which was tested using longitudinal data collected regarding four different systems at four organizations (N = 156), two involving voluntary usage and two involving mandatory usage.
Abstract: The present research develops and tests a theoretical extension of the Technology Acceptance Model (TAM) that explains perceived usefulness and usage intentions in terms of social influence and cognitive instrumental processes. The extended model, referred to as TAM2, was tested using longitudinal data collected regarding four different systems at four organizations ( N = 156), two involving voluntary usage and two involving mandatory usage. Model constructs were measured at three points in time at each organization: preimplementation, one month postimplementation, and three months postimplementation. The extended model was strongly supported for all four organizations at all three points of measurement, accounting for 40%--60% of the variance in usefulness perceptions and 34%--52% of the variance in usage intentions. Both social influence processes (subjective norm, voluntariness, and image) and cognitive instrumental processes (job relevance, output quality, result demonstrability, and perceived ease of use) significantly influenced user acceptance. These findings advance theory and contribute to the foundation for future research aimed at improving our understanding of user adoption behavior.
16,513 citations
TL;DR: In this article, an attitudinal model is developed and empirically tested integrating constructs from technology acceptance research and constructs derived from models of web behavior, and two distinct categories of the interactive shopping environment support the differential importance of immersive, hedonic aspects of the new media as well as the more traditional utilitarian motivations.
2,888 citations
"Outfit Browser – An Image-data-driv..." refers background in this paper
...756 [7] Given that I have access to the system, I predict that I would use it....
[...]
TL;DR: In this paper, a simple equation to compute correlated color temperature (CCT) from CIE 1931 chromaticity coordinates x and y is given, which is useful in designing sources to simulate CIE colorimetric illuminants.
Abstract: A simple equation to compute correlated color temperature (CCT) from CIE 1931 chromaticity coordinates x and y is given. Over the range of interest in color science, the errors are negligible. It was derived from the fact that the isotemperature lines for CCTs of principle interest nearly converge toward a point on the chromaticity diagram and the assumption that CCT may be represented by a third-order polynomial function of the reciprocal of the slope of the line from that point to the chromaticity of the light. the equation is useful in designing sources to simulate CIE colorimetric illuminants.
1,320 citations
"Outfit Browser – An Image-data-driv..." refers methods in this paper
...In this research the proposed approach from McCamyis implemented [12]....
[...]
TL;DR: In this article, a theoretical extension of the Technology Acceptance Model TAM that explains perceived usefulness and usage intentions in terms of social influence and cogni cation is presented. But this model is not applicable to the context of mobile devices.
Abstract: The present research develops and tests a theoretical extension of the Technology Acceptance Model TAM that explains perceived usefulness and usage intentions in terms of social influence and cogni...
1,016 citations