1,721,111 research outputs found
Real-Time Analysis of Eye Behaviour for Enhanced E-Learning
No full textThanks to constant price decrease and continuous technological improvements, reliable and easy-to-use eye trackers are now relatively widespread, especially in research laboratories. On the same time, e-learning is becoming almost as common as traditional in-class teaching, offering courses which cover practically any topic. In this paper we consider the application of eye tracking to e-learning, as a way to improve the machine-learner interaction process. What we look at — as well as how we do that — can in fact be used to enhance the learning process, revealing precious information which would otherwise remain hidden
A mobile robot multimedia interaction system based on CPP-TRS methodology and language
No full textThe paper presents a graphical interaction system which allows the user to easily specify the tasks a mobile robot will have to perform
Freehand Interaction with a Paper-Based Input Interface
No full textDepending on their structure, graphical user interfaces may sometimes be not fully comfortable, because they require oculomotor coordination and relatively precise mouse movement. While physical interfaces may be the right choice for purpose-specific appliances, they become less practicable in the case of interfaces for software tools, since each program would need its own physical interface. Moreover, there may be situations in which the input interface is used in dirty environments (such as industrial plants), and needs to be replaced very often. Starting from these premises, this article studies the feasibility of a gesture interaction input approach based on a paper interface, also appraising its efficiency and investigating the user acceptance level. Through a finger, the user can directly operate interface controls either drawn by him or herself or provided in ready-to-use pre-printed sheets. The implemented prototype, based on computer vision, relies on a simple and cheap webcam, and controls consist of sliders, buttons, knobs and trackpads. Experiments have shown that the proposed approach is practicable in terms of both performance and positive reception by users, although some inherent problems of vision-based systems must be taken into account. In addition, users’ opinions have provided feedback about potential application scenarios and possible system improvements. The obtained results can be the starting point for deeper and more focused investigations, driving further research on the topic
New Visualization Modes for Effective Image Presentation
No full textIn this paper we consider the problem of effective browsing of collections of images. In particular, we address those situations where it is necessary to find a limited number of images satisfying certain criteria, as well as the very common case in which the user, not having a clear idea about what to search, needs to explore the entire picture database to identify what he or she simply likes. The approaches we propose try to find good trade-offs between browsing time and quality of the exploration. The article has a twofold purpose: on the one hand, it presents a selection of the new image display methods we have developed in the last years, which differentiate from those considered to date by the Information Visualization community; on the other hand, it illustrates the results obtained through comparative tests performed on a subset of the developed display modes, with the main aim to prove the feasibility of their use as substitutes for the usual "grid" arrangement
E-learning and machine perception: in pursuit of human-like interaction in computer-based teaching systems
No full textMore and more technological advances offer new paradigms for
training, allowing novel forms of teaching and learning to be devised.Unfortunately, however, most e-learning systems are still based on complex procedures and little usable interfaces, which may result in frustrating learning experiences, because of users’ lack of computer skills. To reduce such risk it would be helpful to go beyond the standard interface usability, towards more natural ways of providing input to the machine. In this paper we consider the possibility of exploiting vision and speech as intuitive communication channels, to enhance the quality of the interaction between users and e-learning platforms. Through an analysis of current research in the fields of vision-based
and speech-based perceptive interfaces, we discuss several application scenarios for e-learning, stressing the important role that such natural communication forms could play in improving the interaction process
A Study on Text Entry Methods Based on Eye Gestures
No full textPurpose – In this paper we consider the two main existing text input techniques based on “eye gestures” -- namely EyeWrite and Eye-S -- and compare them to each other and to the traditional “virtual keyboard” approach.
Design/methodology/approach – The study primarily aims to assess user performance at the very beginning of the learning process. However, a partial longitudinal evaluation is also provided. Two kinds of experiments have been implemented involving 14 testers.
Findings – Results show that while the virtual keyboard is faster, EyeWrite and Eye-S are also appreciated and can be viable alternatives (after a proper training period).
Practical implications – Writing methods based on eye gestures deserve special attention, as they require less screen space and need limited tracking precision. This study highlights the fact that gesture-based techniques imply a greater initial effort, and require proper training not only to gain knowledge of eye interaction per se, but also for learning the gesture alphabet. We think that our investigation can drive the designers of gaze-controlled writing techniques based on gestures to put more consideration on the intuitiveness of gestures themselves, as they may greatly influence user performance in the first stages of the learning process.
Originality/value – This is the first study comparing EyeWrite and Eye-S. Moreover, unlike other analyses, our investigation is mainly aimed at assessing user performance with the three text entry methods at the inception of the learning procedure
VISPS, A Visual System for Plan Specification
No full textIn various circumstances, it is possible to arrive at the need to specify sequences of operations that a “machine” has to perform to achieve a purpose. This paper will present VISPS, a visual system originally designed to specify mission plans for the SARA autonomous submarine robot. Although this is the particular setting for which the system had been initially devised, thanks to its flexibility it can be easily configured to adjust to different contexts and situations, even if it is always based on the same simple basic visual mechanism
Browsing Large Collections of Images through Unconventional Visualization Techniques
No full textIn this paper we describe some alternative methods intended for rapid and effective browsing of large collections of images. Specifically, we address the user who, not having a clear idea about what to search, needs to explore the entire image database to identify what he or she likes. The purpose of our approaches is to find techniques characterized by good trade-offs between browsing time and quality of the exploration
Implementing Eye-Based User-Aware E-Learning
No full textWe propose an e-learning scenario where eye tracking is exploited to get valuable data about user behavior. What we look at — as well as how we do that — can in fact be used to improve the learning process, revealing information which would otherwise remain hidden. The prototype system we are developing at the University of Pavia takes into account both the user’s “emotional status” and the way learning activities are carried out, employing these data to adapt content presentation in real-time
Vision-based user interfaces: methods and applications
No full textWithin the class of perceptive user interfaces (i.e. interfaces providing the computer with perceptive capabilities), artificial vision is being exploited more and more as a new input modality, in addition to or in replacement of standard interaction paradigms. The aim of this paper is to provide a global view on the field of vision-based interfaces (VBIs), through the analysis of the methods used for their implementation and the exploration of the practical systems in which they have been em-ployed. The focus will mostly be on techniques and prototypes intended for office and home PC-based use, as we are mainly interested in vision technology applied to ordinary computing environ-ments. After a brief introduction to basic concepts about interfaces and image processing, the attention will be shifted to the four main areas in which VBIs find their maximum expression, namely head tracking, face/facial expression recognition, eye tracking and gesture recognition
- …
