A Manually Captured and Modified Phone Screen Image Dataset for Widget Classification on CNNs

Sung Chul Byun, Seong Soo Han, Chang Sung Jeong

Research output: Contribution to journalArticlepeer-review

Abstract

The applications and user interfaces (UIs) of smart mobile devices are constantly diversifying. For example, deep learning can be an innovative solution to classify widgets in screen images for increasing convenience. To this end, the present research leverages captured images and the ReDraw dataset to write deep learning datasets for image classification purposes. First, as the validation for datasets using ResNet50 and EfficientNet, the experiments show that the dataset composed in this study is helpful for classification according to a widget's functionality. An implementation for widget detection and classification on RetinaNet and EfficientNet is then executed. Finally, the research suggests the Widg-C and Widg-D datasets—a deep learning dataset for identifying the widgets of smart devices—and implementing them for use with representative convolutional neural network models.

Original languageEnglish
Pages (from-to)197-207
Number of pages11
JournalJournal of Information Processing Systems
Volume18
Issue number2
DOIs
Publication statusPublished - 2022 Apr

Bibliographical note

Publisher Copyright:
© 2022. Journal of Information Processing Systems.All Rights Reserved

Keywords

  • Captured image
  • Cnn
  • Deep learning dataset
  • Image classification
  • Object detection
  • Widget

ASJC Scopus subject areas

  • Software
  • Information Systems

Fingerprint

Dive into the research topics of 'A Manually Captured and Modified Phone Screen Image Dataset for Widget Classification on CNNs'. Together they form a unique fingerprint.

Cite this