Classifier Design

The design and development of a classifier based solely on simple image features will be presented.

• Justification for Using Simple Features
• Feature Selection Process
  • Concept Exploration Dataset
    • Concept Exploration Observations
    • Connected Components
  • Feature Metrics Design
    • White Speckle
    • Broken-Chars Zone
    • Size Information
  • Preliminary Set of Rules
• Determining Threshold Values
  • Training Dataset
  • Conclusions from Training Test
    • White Speckle
    • Reference Point
    • Broken Chars Zone
    • Size Information
• Final Set of Rules
• Summary