Application of Agents to the Recognition of Mathematical Expressions from Noisy Images

Daniel Ogwok, Elizabeth M. Ehlers

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

Abstract

Research in image and pattern recognition has been going on for a long time. State of art solutions have been presented, and this has only got better with the introduction of convolutional neural networks. These networks have proven to work well, especially with high dimensional data. Mathematical expressions are written and used on a daily basis; however, it becomes a challenge when they have to be digitalized from images, especially when there is noise in the image. Noise presents an additional layer of difficulty in recognition of the expressions. This paper presents a system that uses agents that implement various segmentation and machine learning methods to recognize mathematical expressions from noisy images taken in a classroom setting.

Original languageEnglish
Title of host publicationCIIS 2021 - 2021 4th International Conference on Computational Intelligence and Intelligent Systems
PublisherAssociation for Computing Machinery
Pages7-12
Number of pages6
ISBN (Electronic)9781450385930
DOIs
Publication statusPublished - 20 Nov 2021
Event4th International Conference on Computational Intelligence and Intelligent Systems, CIIS 2021 - Virtual, Online, Japan
Duration: 20 Nov 202122 Nov 2021

Publication series

NameACM International Conference Proceeding Series

Conference

Conference4th International Conference on Computational Intelligence and Intelligent Systems, CIIS 2021
Country/TerritoryJapan
CityVirtual, Online
Period20/11/2122/11/21

Keywords

  • Agents
  • Connected Components Labelling
  • Convolutional Neural Networks
  • Image Recognition
  • K-Nearest Neighbours
  • Support Vector Machines

ASJC Scopus subject areas

  • Software
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Application of Agents to the Recognition of Mathematical Expressions from Noisy Images'. Together they form a unique fingerprint.

Cite this