Abstract

This paper presents an approach for the recognition of multi-domain hand-drawn diagrams, which exploits Sketch Grammars (SkGs) to model the symbols’ shape and the abstract syntax of diagrammatic notations. The recognition systems automatically generated from SkGs process the input sketches according to the following phases: the user’ strokes are first segmented and interpreted as primitive shapes, then by exploiting the domain context they are clustered into symbols of the domain and, finally, an interpretation of whole diagram is given. The main contribution of this paper is an efficient model of parsing suitable for both interactive and non-interactive sketch-based interfaces, configurable to different domains, and able to exploit contextual information for improving recognition accuracy and solving interpretation ambiguities. The proposed approach was evaluated in the domain of UML class diagrams obtaining good results in terms of recognition accuracy and usability.

Highlights

  • Hand-drawn sketches allow users to quickly draw new technical solutions and effectively communicate them to a variety of audiences

  • This paper presents a sketch recognition system for multi-domain hand-drawn diagrams based on grammar formalisms and parsing technologies [18,19]

  • The sketch recognition systems described in [45,46] use variants of visual language grammars to provide contextual information in order to face the inherent ambiguity of sketched drawings

Read more

Summary

Introduction

Hand-drawn sketches allow users to quickly draw new technical solutions and effectively communicate them to a variety of audiences. This paper presents a sketch recognition system for multi-domain hand-drawn diagrams based on grammar formalisms and parsing technologies [18,19]. Grammars to hierarchically define both the symbols’ shapes and the abstract syntax of diagrammatic notations, and to automatically generate efficient LR-based parsers [20] The latter are on the top layer of the sketch recognition strategy, while the bottom layer consists of a domain-independent primitive shape recognizer. Sketch Grammars allow users to construct recognizers of any diagrammatic or iconic domain These recognizers do not constrain users to a specific drawing style, since the symbols of the diagrams can be drawn with a varying number of strokes and without a particular direction or order.

Sketch Recognition Challenges
Related Work
Stroke-Based Sketch Recognition Methods
Sketch Description Languages
Overview of Our Approach
Preliminary Definitions
Sketch Grammars
The Sketch Recognition System
The Primitive Shape Recognizer
The Symbol Recognizer
The Language Recognizer
Offline Sketch Recognition
Recognition Accuracy Evaluation and Usability Study
Experiment Setup
Results and Discussion
How difficult is it for you find the solution to the proposed problem?
Conclusions and Future Work

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.