I'm currently working in a Lolipop LBP cascade detector using OpenCV. The training is correctly done and the cascade classifier detects the sticks of the Lolipops correctly but with some minor errors.

enter image description here

Is there any way to obtain a "level of trust" or an index of how many features had been detected during the cascade detection process?


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.