Extracting Decision Models from Digitally Drawn or Hand-drawn DMN Images

Date

2025-01-07

Contributor

Advisor

Department

Instructor

Depositor

Speaker

Researcher

Consultant

Interviewer

Narrator

Transcriber

Annotator

Journal Title

Journal ISSN

Volume Title

Publisher

Volume

Number/Issue

Starting Page

5668

Ending Page

Alternative Title

Abstract

Decision Model and Notation (DMN) models are used to model and automate operational decisions. Frequently, these DMN models are distributed as images within documents, either as screenshots or as pictures of hand-drawn models. This distribution method can results in the loss of the original source format. Re-using these images then entails the manual process of remodelling or redrawing them, a task that is both time-consuming and complex. In this study, deep learning techniques are employed to extract DMN models from both digitally drawn and hand-drawn DMN images. A substantial dataset was collected and annotated to train and test the diverse range of models. Subsequently, the work's outcome has been integrated into a DMN Computer Vision Tool application which can be used to reconstruct DMN source files based on hand-drawn sketches and digital images.

Description

Keywords

Business Process Technology, computer vision, deep learning, dmn

Citation

Extent

10

Format

Geographic Location

Time Period

Related To

Proceedings of the 58th Hawaii International Conference on System Sciences

Related To (URI)

Table of Contents

Rights

Attribution-NonCommercial-NoDerivatives 4.0 International

Rights Holder

Local Contexts

Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.