ContourCNN: Convolutional neural network for contour data classification

Ahmad Droby, Jihad El-Sana

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper proposes a novel Convolutional Neural Network model for contour data analysis (ContourCNN) and shape classification. A contour is a circular sequence of points representing a closed shape. For handling the cyclical property of the contour representation, we employ circular convolution layers. Contours are often represented sparsely. To address information sparsity, we introduce priority pooling layers that select features based on their magnitudes. Priority pooling layers pool features with low magnitudes while leaving the rest unchanged. We evaluated the proposed model using letters and digits shapes extracted from the EMNIST dataset and obtained a high classification accuracy.

Original languageEnglish
Title of host publicationInternational Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665412629
DOIs
StatePublished - 7 Oct 2021
Event2021 IEEE International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021 - Mauritius, Mauritius
Duration: 7 Oct 20218 Oct 2021

Publication series

NameInternational Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021

Conference

Conference2021 IEEE International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2021
Country/TerritoryMauritius
CityMauritius
Period7/10/218/10/21

Keywords

  • CNN
  • Circular data
  • Classification
  • Contour
  • Convolutional neural netwrok
  • Priority pool

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems and Management
  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Mechanical Engineering
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'ContourCNN: Convolutional neural network for contour data classification'. Together they form a unique fingerprint.

Cite this