Rechercher une page de manuel

Chercher une autre page de manuel:


Langue: en

Version: 257781 (debian - 07/07/09)

Section: 1 (Commandes utilisateur)


opencv-performance - evaluate the performance of the classifier


opencv-performance [options]


opencv-performance evaluates the performance of the classifier. It takes a collection of marked up test images, applies the classifier and outputs the performance, i.e. number of found objects, number of missed objects, number of false alarms and other information.

When there is no such collection available test samples may be created from single object image by the opencv-createsamples(1) utility. The scheme of test samples creation in this case is similar to training samples

In the output, the table should be read:

shows the number of correctly found objects
shows the number of missed objects (must exist but are not found, also known as false negatives)
shows the number of false alarms (must not exist but are found, also known as false positives)


opencv-performance supports the following options:

-data classifier_directory_name
The directory, in which the classifier can be found.
-info collection_file_name
File with test samples description.
-maxSizeDiff max_size_difference
Determine the size criterion of reference and detected coincidence. The default is 1.500000.
-maxPosDiff max_position_difference
Determine the position criterion of reference and detected coincidence. The default is 0.300000.
-sf scale_factor
Scale the detection window in each iteration. The default is 1.200000.
Don't save detection result to an image. This could be useful, if collection_file_name contains paths.
-nos number_of_stages
Number of stages to use. The default is -1 (all stages are used).
-rs roc_size
The default is 40.
-h sample_height
The sample height (must have the same value as used during creation). The default is 24.
-w sample_width
The sample width (must have the same value as used during creation). The default is 24.

The same information is shown, if opencv-performance is called without any arguments/options.


To create training samples from one image applying distortions and show the results:

opencv-performance -data trainout -info tests.dat


opencv-createsamples(1), opencv-haartraing(1)

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


This manual page was written by Daniel Leidert <> for the Debian project (but may be used by others).

Le monde récompense plus souvent les apparences du mérite que le mérite
-+- François de La Rochefoucauld (1613-1680), Maximes 166 -+-