I implemented a generalized likelihood ratio test (GLRT) detector/identifier. The result of the identification step results in a score for each of the objects to be identified in an ordered list. The ratio values are log of a ratio number.

Is there a way to compute an estimate of the probability/confidence of similarity in that estimate ?

  • $\begingroup$ well, the values should be monotonous with confidence. The conversion from log-likelihoods (or ratios thereof) to likelihoods depends on the distribition of error. $\endgroup$ Jul 28 at 19:42
  • $\begingroup$ Can you write down the closed-form expression of the GLRT? $\endgroup$
    – Maxtron
    Jul 30 at 4:25

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.