7.2

Theory of Parameter Estimation for Recognition

In this section, correctness, instability and optimality are proposed for evaluating parameter estimates. Their relationships to non-parametric pattern recognition are discussed and non-parametric methods for computing correct and optimal estimates are presented. Prior to these, necessary notations for optimization-based object recognition are introduced.

• 7.2.1 Optimization-Based Object Recognition
• 7.2.2 Criteria for Parameter Estimation
  • Correctness
  • Instability
  • Optimality
• 7.2.3 Linear Classification Function
• 7.2.4 A Non-parametric Learning Algorithm
• 7.2.5 Reducing Search Space