"McSig" is a multimodal teaching and learning environ-ment for visually-impaired students to learn character shapes, handwriting signatures collaboratively with their teachers. It combines haptic audio output realize the teacher's pen input in parallel non-visual modalities. McSig intended children how handwrite characters (and from that signatures), something very difficult without visual feedback. We conducted an evaluation eight pretest assess current skills set of training phase using...

We present McSig, a multimodal system for teaching blind children cursive handwriting so that they can create personal signature. For people is very difficult to learn as it near-zero feedback activity needed only occasionally, yet in important situations; example, make an attractive and repeatable signature legal contracts. McSig aids the of signatures by translating digital ink from teacher's stylus gestures into three non-visual forms: (1) audio pan pitch represents x y movement stylus;...

Digital ink features drive recognition engines. Intuitively, we understand that particular are of more value for some problems than others. Likewise, inclusion poor may be detrimental to success. Many different have been proposed recognition, and most work well the context they employed. However given a new problem it is not clear which already defined will useful. We assembled categorized comprehensive feature library use this with attribute selection algorithms choose best specified...

The Penan people of Malaysian Borneo were traditionally nomads the rainforest. They would leave messages in jungle for each other by shaping natural objects into language tokens and arranging these symbols specific ways -- much like words a sentence. With settlement, is being lost as it not used younger generation. We report here, tangible system designed to help preserve their unique object writing language. key features are that: its tangibles made real objects; works wild; new can be...

We present our toolkit to automatically evaluate recognition algorithms. There are few published comparative evaluations of sketch algorithms and those that exist do not provide benchmarking or direct comparisons because standardised data an evaluation platform is available. By unifying collection, labelling in one tool, fair, flexible comprehensive possible. Currently we have 6 existing recognizers integrated into this tool. With initial these observed the context from which training taken...

Repositories of digital ink sketches would be invaluable for testing and evaluation sketch recognition software. However, there is no existing tool flexible data collection management building repositories hand drawn diagrams. We present a the efficient collection, analysis data. A resultant dataset records each stroke accompanied by participant diagram information, labels measurements various features. This enables effective construction large database to aid development techniques.

Abstract Although many approaches to digital ink recognition have been proposed, most lack the flexibility and adaptability provide acceptable rates across a variety of problem spaces. This project uses systematic approach data mining analysis build gesture recognizer for sketched diagrams. A wide range algorithms was tested, those with best performance were chosen further tuning analysis. Our resulting recognizer, RATA.Gesture, is an ensemble four algorithms. We evaluated it against popular...

Touch and stylus sensitive computer displays are widely available. Yet, the development of gesture sets to support these interaction methods continues be difficult. We present RATA, a tool for designers software developers create recognizers novel custom sets. Guided by RATA wizard, developer: defines their set; collects example gestures; labels them with an auto labeller; generates recognizer model file – no coding or expert knowledge is required. Incorporating into program requires just...

While many approaches to digital ink recognition have been proposed, most lack flexibility and adaptability provide acceptable rates across a variety of problem spaces. Time expert knowledge are required build accurate recognizers for new domain. This project uses selected algorithms from data mining toolkit large feature library, compose tailored software component (Rata.SSR) that enables single stroke recognizer generation few example diagrams. We evaluated Rata.SSR against four popular...

We present an innovative drawing tool that can detect tangible instruments on a capacitive multi-touch tablet. There are three core components to the system: hardware, recognizer used identify tangibles, and application. Our include ruler, protractor set square. Users apply these familiar physical construct digital ink drawings tablet in intuitive engaging manner. The user evaluation shows tools easy use have high rate of recognition touch screen.

We introduce Tangeo, a drawing system that combines tangible tools, such as rulers, protractors and set squares with table-top environment. Geometric on computers is often constrained to abstract widget tools metaphoric, indirect input methods mouse keyboard. Tangeo allows users construct geometric drawings in more direct manner by manipulating virtual data familiar physical objects finger. User evaluations yielded high rate of user satisfaction indicated the effective at enhancing drawing.

Grouping of strokes into semantically meaningful diagram elements is a difficult problem. Yet such grouping needed if truly natural sketching to be supported in intelligent sketch tools. Using machine learning approach, we propose number new paired-stroke features for and evaluate the suitability range algorithms. Our evaluation shows algorithms produce promising results that are statistically better than existing grouper.

Labeled ink stroke data is essential to the development and evaluation of sketch recognizers. Manually labeling strokes a tedious, time-consuming, error prone task; very few tools are available facilitate this. We propose new intuitive method automatic for single primitives. This involves building recognizer from partially labeled dataset. then used identify automatically label remaining data, therefore reducing amount manual required by researchers. An comparing against our auto shows that...

Sketch recognition is the interpretation of hand-drawn diagrams, and seeks to understand users' intent while allowing them draw unconstrained diagrams. Research in sketch has been on-going for approximately half a century, experienced iterative advances due difficulty problem. As pen- touch-capable devices such as smartphones, tablets, touch-driven monitors, large touchscreen have become ubiquitous, emergent technologies virtual augmented reality-driven computing are becoming more advanced,...

Little is known about the usability and cognitive load experienced by students using online asynchronous discussion tools in higher education. Given that use of both generic chat specialised learning technology forum continue to increase, it important for educators designers/developers understand user experience these tools. This research evaluates a text-based tool, Discord, Ed Discussion, from perspective complement findings educational literature. We have identified issues plague such...

Passive stylus systems offer a simple and cost-effective solution for digital input, compatible with wide range of surfaces devices. This study reviews the domain passive tracking on surfaces, topic previously underexplored in existing literature. We answer four key research questions: what type exist this domain, methods do they use styli, how accurate are they, their limitations? A systematic literature review resulted 24 papers describing systems. Their primarily fall into categories:...

Physical drawing tools, such as rulers, afford immediate visual and proprioceptive feedback to the user: even before a line is added drawing. Such immediacy not available in standard digital software. We introduce TUI-Geometry, application that senses tangible tools on an interactive tabletop provides user with intelligent beautification. A evaluation comparing TUI-Geometry passive showed users preferred were able draw significantly more accurately it -- thus we provide foundation for...

Digital ink affords numerous opportunities to broaden the use of computer supported learning in science, technology, engineering and mathematics (STEM) education. This review recent literature on digital tools demonstrates that they offer significant potential, although there are relatively few studies intelligent tools, it is notable span STEM disciplines. In this review, we identify major challenges for applications education, discuss primary areas use, feedback mechanisms interaction methods.

An early step in bottom-up diagram recognition systems is grouping ink strokes into shapes. This paper gives an overview of the key literature on automatic techniques sketch recognition. In addition, we identify major challenges identifiable shapes, discuss common solutions to these based current research, and highlight areas for future work.