GAN-based pencil drawing learning system for art education on large-scale image datasets with learning analytics

Yuxi Jin, Ping Li, Wenxiao Wang, Suiyun Zhang, Di Lin, Chengjiu Yin

Research output: Journal article publicationJournal articleAcademic researchpeer-review

7 Citations (Scopus)

Abstract

We design a generative adversarial network (GAN)-based pencil drawing learning system for art education on large image datasets to help students study how to draw pencil drawings for images and scenes. The system generates a pencil drawing result for a natural image based on GAN. The GAN network is trained on pencil drawing big datasets containing image pairs of natural images and their corresponding pencil drawings. Using the pencil drawing learning system, students can paint pencil drawings whenever they want and for whatever they like by uploading an image of the content they want to draw and getting a pencil drawing example of the uploaded image from the system. With the returned pencil drawing, students will see the pencil drawing effect of natural scenes clearly and realize how to draw the pencil drawing for the natural scene. Besides, with students using the pencil drawing learning system, it will be convenient for teachers assigning homework to students. Teachers can know the learning demands of students by evaluating the hand-in homework and update the content correspondingly. We have conducted two user studies for evaluating the practicality of the system, and the result of the two user studies demonstrated the applicability and practicality of the system.

Original languageEnglish
JournalInteractive Learning Environments
DOIs
Publication statusAccepted/In press - 1 Jan 2019

Keywords

  • art education
  • GAN
  • learning analytic
  • pencil drawing big data
  • Pencil drawing learning system

ASJC Scopus subject areas

  • Education
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'GAN-based pencil drawing learning system for art education on large-scale image datasets with learning analytics'. Together they form a unique fingerprint.

Cite this