InkML

Abstract: Learning disabilities affect an increasing number of students. Among these disabilities, dysgraphia has a nonindifferent role since it undermines the writing communication abilities of the students, with side effects on their self-esteem and a great risk of reduced school performance and more difficult relationships with classmates. It is the opinion of many people that the right way to prevent students from losing the writing gesture and allow for the acquisition of the correct writing automatism is through supporting exercises and activities. With these aims in mind we have designed and developed a client-server web-based software system, usable through modern devices such as tablets and smartphones using cutting edge Javascript libraries and framework and sophisticated algorithms for multiple hand gesture recognition, namely the Dynamic Time Warping algorithm that has been modified to recognize composite gesture. The software tool offers the users the possibility to execute sets of different exercises types, organized in levels, from simple connect the dots to complete writing a word, and the writing is compared with a reference trace done by an expert. The software tool offers immediate feedback on the basis of objective parameters, as well as a comprehensive collection of data stored both in JSON and INKML format, useful for identifying, studying and rehabilitating dysgraphic handwriting.

Abstract: Annotated datasets of handwriting are a prerequisite for the design and training of handwriting recognition algorithms. In this paper, we briefly describe an XML representation for annotation of online handwriting data that uses the emerging digital ink markup language (InkML) standard from W3C for the representation of handwriting data. We then describe a tool based on the proposed representation that can be used for annotation of digital ink. Ease and speed of annotation are emphasized in the design of the tool. Together, the representation and the tool attempt to address the requirements of creation of annotated datasets of handwritten data in different scripts around the worldwide.

Abstract: This paper introduces our efforts to create UPX, an XML-based successor to the venerable UNIPEN format for the representation of annotated datasets of online handwriting data. In the first part of the paper, shortcomings of the UNIPEN format are discussed and the goals of UPX are outlined. Prior work related to UPX in the form of the recently proposed hwDataset representation is presented. The second part of the paper summarizes the status of the UPX effort, in particular, experiments to map UNIPEN elements to hwDataset and InkML and identify potential issues with migrating existing UNIPEN data to UPX. This is work in progress, and we invite participation from the handwriting recognition research community and industry to make UPX a reality.

Abstract: Experiments on cognitive processes require a detailed analysis of the contribution of many participants. In the case of cognitive processes in writing, these experiments require special software tools to collect gestures performed with a pen or a stylus, and recorded with special hardware. These tools produce different kinds of data files in binary and proprietary formats that need to be managed on a workstation file system for further processing with generic tools, such as spreadsheets and statistical analysis software. The lack of common formats and open repositories hinders the possibility of distributing the workload among researchers within the research group, of re-processing the collected data with software developed by other research groups, and of sharing results with the rest of the cognitive processes research community. This paper describes the development of HandSpy, a collaborative environment for managing experiments in the cognitive processes in writing. This environment was designed to cover all the stages of the experiment, from the definition of tasks to be performed by participants, to the synthesis of results. Collaboration in HandSpy is enabled by a rich web interface. To decouple the environment from existing hardware devices for collecting written production, namely digitizing tablets and smart pens, HandSpy is based on the InkML standard, an XML data format for representing digital ink. This design choice shaped many of the features in HandSpy, such as the use of an XML database for managing application data and the use of XML transformations. XML transformations convert between persistent data representations used for storage and transient data representations required by the widgets on the user interface. Despite being a system independent from a specific collecting device, for the system validation, a framework for data collection was created. This framework has also been highlighted in the paper due to the important role it took in a data collection process, of a scientific project to study the cognitive processes involved in writing.