Using reinforcement learning for image thresholding

Maryam Shokri, Hamid R. Tizhoosh

Research output: Contribution to journalConference articlepeer-review


A reinforcement-learning agent was introduced to find the optimal threshold for digital images. The agent learnt the optimal threshold for an image through interactions with an experienced user, and by integrating objective domain knowledge. Results showed that the proposed approach could integrate human expert knowledge in an objective or subjective way to overcome the shortcomings of existing methods.

Original languageEnglish (US)
Pages (from-to)1231-1234
Number of pages4
JournalCanadian Conference on Electrical and Computer Engineering
StatePublished - 2003
EventCCECE 2003 Canadian Conference on Electrical and Computer Engineering: Toward a Caring and Humane Technology - Montreal, Canada
Duration: May 4 2003May 7 2003


  • Image Processing
  • Image thresholding
  • Reinforcement learning

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering


Dive into the research topics of 'Using reinforcement learning for image thresholding'. Together they form a unique fingerprint.

Cite this