NAME
opencv_traincascade
SYNOPSIS
opencv_traincascade [options]
DESCRIPTION
traincascade application.
OPTIONS
opencv_traincascade supports the following options:
BASIC OPTIONS
-data cascade_dir_name
-vec vec_file_name
-bg background_file_name "-numPos " number_of_positive_samples The
default is 2000.
-numNeg number_of_negative_samples The default is 1000.
-num Stagesnumber_of_stages The default is 20.
-precalcValBufSize precalculated_vals_buffer_size_in_Mb The default is
256.
-precalcIdxBufSize precalculated_idxs_buffer_size_in_Mb The default is
256.
-baseFormatSave
CASCADE OPTIONS
-stageType The default is BOOST.
-featureType Set feauture type . You can select HAAR or LBP. The
default is HAAR.
-w sampleWidth The default is 24.
-h sampleHeight The default is 24.
BOOST OPTIONS
-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.
-minHitRate min_hit_rate The default is 0.995.
-maxFalseAlarmRate max_false_alarm_rate The default is 0.5.
-weightTrimRate weight_trim_rate The default is 0.95.
-maxDepth max_depth_of_weak_tree The default is 1.
-maxWeakCount max_weak_tree_count The default is 100.
HAARFEATURE OPTIONS
-mode <BASIC(default)|CORE|ALL The type of the applied haarFeature
mode. You can choose between BASIC, ORE and ALL. The default is BASIC.
EXAMPLES
TODO
SEE ALSO
opencv_haartraing(1), opencv_performance(1)
More information and examples can be found in the OpenCV documentation.
AUTHORS
This manual page was written by Nobuhiro Iwamatsu <iwamatsu@debian.org>
for the Debian project (but may be used by others).