Preprocessing from Cascade Classifier for Decision Trees [closed]

asked 2016-11-22 14:37:42 -0500

DerrickB gravatar image

updated 2016-11-22 14:39:44 -0500

Hello OpenCV Community,

i want to compare/ test the performance of Decision Trees and Cascade Classifiers for Person Detection. My Problem is that the cv::CascadeClassifier does the Preprocessing like Sliding Window etc. automatically in its Methods but the cv::DTree dont.

Is there a solution to extract the methods from the CC and use it for the DTrees also, or does the cv::DTree has something comparable?

I hope the question is understandable.

Thank you for your Advice,

Kind regards,

Derrick

edit retag flag offensive reopen merge delete

Closed for the following reason question is off-topic or not relevant by DerrickB
close date 2016-11-27 09:42:16.819857

Comments

  • what kind of features do you plan to use ?
  • you'll have to train it, too
  • did you ever look at the src code ? it's already using (some kind of) decision tree under the hood
berak gravatar imageberak ( 2016-11-23 03:45:51 -0500 )edit

I used LBP and Haar Features for the Cascade Classifier. ( I prefer LBP because of the training time)

For DTree i dont know how to use/ select feature. I train it with 24x48 px positive and negative Images.

My Problem is: I cant put whole Input Pictures in the DTree Prediciton, i need to cut it by myself in the trained Image size (24x48). In "detectmultiscale" of CC i can put the whole image in. (e.g. 270x480)

@berak

DerrickB gravatar imageDerrickB ( 2016-11-23 06:33:52 -0500 )edit

@berak Can you tell me how i use features (LBP/ HAAR) with the DTrees?

Does it make any sense to use DTrees for Object Detection (without recognition)?

DerrickB gravatar imageDerrickB ( 2016-11-26 08:47:34 -0500 )edit