Sketched symbol recognition using Zernike moments

Hse, Heloise Hwawen; Newton, A.R.

doi:10.1109/icpr.2004.1334128

Cited by 84 publications

(77 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These include Rubine's [31] single stroke gesture recognition algorithm (used by SILK and Freeform) and Apte's [1] multi-stroke algorithms. Hse has developed the multi-stroke recognition approach into HHReco, a reusable Java toolkit supporting sketching which incorporates a range of trainable and customizable recognisers [17]. While these toolkits are all immensely useful, they still require significant programming to incorporate into other applications.…”

Section: Related Workmentioning

confidence: 99%

“…MaramaSketch uses the open source HHReco toolkit to support multi-stroke text and graphical shape recognition [17]. HHReco provides an incrementally re-trainable set of positive and negative examples that can be augmented incrementally during MaramaSketch usage or via custom training sets developed before use.…”

Section: Design and Implementationmentioning

confidence: 99%

“…We chose to use a multi-stroke, trainingbased shape and text recognition algorithm [17] for MaramaSketch. This was primarily to allow individual users to describe their own examples of each available shape type for MaramaSketch to increase the accuracy of its recognition.…”

Section: Example Usagementioning

confidence: 99%

See 2 more Smart Citations

Supporting Generic Sketching-Based Input of Diagrams in a Domain-Specific Visual Language Meta-Tool

Grundy

Hosking

2007

29th International Conference on Software Engineering (ICSE'07)

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Design and Implementationmentioning

confidence: 99%

See 1 more Smart Citation

Supporting Generic Sketching-Based Input of Diagrams in a Domain-Specific Visual Language Meta-Tool

Grundy

Hosking

2007

29th International Conference on Software Engineering (ICSE'07)

View full text Add to dashboard Cite

show abstract

“…Graphics recognition applications include the conversion of hand-drawn flow charts, block diagrams and graphs into machine interpretations and printed graphics using on-line recognition of curve based graphic symbols [3,7].…”

Section: Introductionmentioning

confidence: 99%

VizDraw: A Platform to Convert Online Hand-Drawn Graphics into Computer Graphics

Mishra

Eichel

Fieguth

et al. 2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. With the adoption of tablet-based data entry devices, there is considerable interest in methods for converting hand-drawn sketches of flow charts, graphs and block diagram into accurate machine interpretations, a conversion process with many applications in engineering, presentations, and simulations. However, the recognition of hand-drawn graphics is a great challenge due to the visual similarity of many system components. This is complicated due to the significant differences in drawing styles between users. The proposed method, VizDraw, establishes an architecture that utilizes a number of pattern recognition tools to convert hand-drawn diagrams into computer graphics by segmenting the original diagram into individual components. This method generates hypothesis graphs for each component, evaluates the hypotheses using forward and backward dynamic programming, and finally utilizes a rule-based floor planning routine for component and symbol placement. VizDraw is invariant to scaling, rotation, translation and style of drawing. The preliminary results show how VizDraw is used for engineering drawings, simulation, and incorporation into computer aided design (CAD) models.

show abstract

“…Several of these have been developed and applied to recognising geometric shapes drawn with multiple strokes [19,2], which allows for richer sketched element recognition. From this work a number of sketch recognition engines have been developed which provide support for training multi-stroke recognisers in a number of domains [20,36].…”

Section: Introductionmentioning

confidence: 99%

SUMLOW: early design‐stage sketching of UML diagrams on an E‐whiteboard

2007

View full text Add to dashboard Cite

SummaryMost visual diagramming tools provide point-and-click construction of computer-drawn diagram elements using a conventional desktop computer and mouse. SUMLOW is a Unified Modelling Language (UML) diagramming tool that uses an E-whiteboard and sketching-based user interface to support collaborative software design. SUMLOW allows designers to sketch UML constructs, mixing different UML diagram elements, diagram annotations and hand-drawn text.A key novelty of the tool is the preservation of hand-drawn diagrams and support for manipulation of these sketches using pen-based actions. Sketched diagrams can be automatically "formalized" into computer-recognised and drawn UML diagrams and then exported to a 3rd party CASE tool for further extension and use. We describe the motivation for SUMLOW, illustrate use of the tool to sketch various UML diagram types, describe its key architecture abstractions and implementation approaches, and report on two evaluations of the toolset. We hope our experiences will be useful for others developing sketching-based design tools or those looking to leverage pen-based interfaces in software applications.

show abstract

Sketched symbol recognition using Zernike moments

Cited by 84 publications

References 15 publications

Supporting Generic Sketching-Based Input of Diagrams in a Domain-Specific Visual Language Meta-Tool

Supporting Generic Sketching-Based Input of Diagrams in a Domain-Specific Visual Language Meta-Tool

VizDraw: A Platform to Convert Online Hand-Drawn Graphics into Computer Graphics

SUMLOW: early design‐stage sketching of UML diagrams on an E‐whiteboard

Contact Info

Product

Resources

About