ReDraw: Machine Learning-Based Prototyping of Graphical User Interfaces for Mobile Apps

Team Members: Kevin Moran, Carlos Bernal-Cárdenas, Michael Curcio, Richard Bonett, & Denys Poshyvanyk

College of William & Mary --- SEMERU



This project was created by the Software Engineering Maintenance and Evolution Research Unit (SEMERU) at the College of William & Mary, under the supervision of Dr. Denys Poshyvanyk.  The major goal of the ReDraw project is to leverage recent advances in machine learning and computer vision in order to automate the practice of mobile application prototyping.  

Video Demonstration



We are working to make ReDraw Open Source!

The code for ReDraw will be coming soon in two phases. First, in April 2019 we will open source the original version of the ReDraw evaluated in the TSE paper. Second, we will open source an improved version of ReDraw this summer that uses TensorFlow as a back-end as opposed to Matlab.



ReDraw Workflow Overview

ReDraw Workflow Overview (Click for more detail)

Description coming soon...

Tools used for ReDraw Implementation

We provide the tools we used in our implementation of the GUI-Component Detection, Data Mining & Dynamic Analysis, CNN Classifier, and App Assembler.

Tools used to implement GUI-Component Detection:

  • Coming Soon!

Tools used for Data mining and dynamic analysis:

  • Coming Soon!

tools used to Implement the CNN classifier:

  • Coming Soon!

tools used to Implement the Application Assembler:

  • Coming Soon!

Using ReDraw

We are working to launch a live web-version of ReDraw. Check back soon for more details.

ReDraw Documentation

When we release the web-application we will also release documentation which will be available here.

ReDraw Study Results


Download the ReDraw Dataset

The initial ReDraw Screen and GUI-Component Dataset is now available for Download! We have permanently archived the ReDraw dataset on Zenodo to provide a DOI that will be accessible for the foreseeable future.