opencv_traincascade - transcascade application

       This  manual  page was written by NobuhiroIwamatsu <iwamatsu@debian.org> for the Debian project (but may
       be used by others).

OpenCV                                              May 2010                              OPENCV_TRAINCASCADE(1)

-datacascade_dir_name-vecvec_file_name-bgbackground_file_name-numPosnumber_of_positive_samples
              The default is 2000.

       -numNegnumber_of_negative_samples
              The default is 1000.

       -numStagesnumber_of_stages
              The default is 20.

       -precalcValBufSizeprecalculated_vals_buffer_size_in_Mb
              The default is 256.

       -precalcIdxBufSizeprecalculated_idxs_buffer_size_in_Mb
              The default is 256.

       -baseFormatSave

-bt{DAB|RAB|LB|GAB}
              The  type  of the applied boosting algorithm. You can choose between Discrete AdaBoost (DAB), Real
              AdaBoost (RAB), LogitBoost (LB) and Gentle AdaBoost (GAB). The default is GAB.

       -minHitRatemin_hit_rate
              The default is 0.995.

       -maxFalseAlarmRatemax_false_alarm_rate
              The default is 0.5.

       -weightTrimRateweight_trim_rate
              The default is 0.95.

       -maxDepthmax_depth_of_weak_tree
              The default is 1.

       -maxWeakCountmax_weak_tree_count
              The default is 100.

-stageType
              The default is BOOST.

       -featureType
              Set feature type . You can select HAAR or LBP.  The default is HAAR.

       -wsampleWidth
              The default is 24.

       -hsampleHeight
              The default is 24.

traincascadeapplication.

       TODO

-mode<BASIC|CORE|ALL>
              The type of the applied haarFeature mode. You can choose between BASIC, ORE and ALL.  The  default
              is BASIC.

       opencv_traincascade - transcascade application

opencv_traincascade supports the following options:

opencv_haartraing(1), opencv_performance(1)

       More information and examples can be found in the OpenCV documentation.

opencv_traincascade[options]