X-Git-Url: http://git.maemo.org/git/?p=opencv;a=blobdiff_plain;f=debian%2Fopencv-performance.1;fp=debian%2Fopencv-performance.1;h=e21ab01f77036183332aa6a4fc1fb59522209b1b;hp=0000000000000000000000000000000000000000;hb=e4c14cdbdf2fe805e79cd96ded236f57e7b89060;hpb=454138ff8a20f6edb9b65a910101403d8b520643

diff --git a/debian/opencv-performance.1 b/debian/opencv-performance.1
new file mode 100644
index 0000000..e21ab01
--- /dev/null
+++ b/debian/opencv-performance.1
@@ -0,0 +1,125 @@
+.TH "OPENCV\-PERFORMANCE" "1" "May 2008" "OpenCV" "User Commands"
+
+
+.SH NAME
+opencv-performance \- evaluate the performance of the classifier
+
+
+.SH SYNOPSIS
+.B opencv\-performance [options]
+
+
+.SH DESCRIPTION
+.PP
+.B 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.
+.PP
+When there is no such collection available test samples may be created from single
+object image by the
+.BR opencv\-createsamples (1)
+utility. The scheme of test samples creation in this case is similar to training samples
+.PP
+In the output, the table should be read:
+.TP
+.RB \(aq Hits \(aq
+shows the number of correctly found objects
+.TP
+.RB \(aq Missed \(aq
+shows the number of missed objects (must exist but are not found, also known
+as false negatives)
+.TP
+.RB \(aq False \(aq
+shows the number of false alarms (must not exist but are found, also known
+as false positives)
+
+
+.SH OPTIONS
+.PP
+.B opencv\-performance
+supports the following options:
+
+.PP
+
+.TP
+.BI "\-data " classifier_directory_name
+The directory, in which the classifier can be found.
+
+.TP
+.BI "\-info " collection_file_name
+File with test samples description.
+
+.TP
+.BI "\-maxSizeDiff " max_size_difference
+Determine the size criterion of reference and detected coincidence.
+The default is
+.IR 1.500000 .
+
+.TP
+.BI "\-maxPosDiff " max_position_difference
+Determine the position criterion of reference and detected coincidence.
+The default is
+.IR 0.300000 .
+
+.TP
+.BI "\-sf " scale_factor
+Scale the detection window in each iteration. The default is
+.IR 1.200000 .
+
+.TP
+.B \-ni
+Don't save detection result to an image. This could be useful, if
+.I collection_file_name
+contains paths.
+
+.TP
+.BI "\-nos " number_of_stages
+Number of stages to use. The default is
+.I \-1
+(all stages are used).
+
+.TP
+.BI "\-rs " roc_size
+The default is
+.IR \40 .
+
+.TP
+.BI "\-h " sample_height
+The sample height (must have the same value as used during creation).
+The default is
+.IR 24 .
+
+.TP
+.BI "\-w " sample_width
+The sample width (must have the same value as used during creation).
+The default is
+.IR 24 .
+
+.PP
+The same information is shown, if
+.B opencv\-performance
+is called without any arguments/options.
+
+
+.SH EXAMPLES
+.PP
+To create training samples from one image applying distortions and show the
+results:
+.IP
+.B opencv\-performance -data trainout -info tests.dat
+
+
+.SH SEE ALSO
+.PP
+.BR opencv\-createsamples (1),
+.BR opencv\-haartraing (1)
+.PP
+More information and examples can be found in the OpenCV documentation.
+
+
+.SH AUTHORS
+.PP
+This manual page was written by \fBDaniel Leidert\fR <\&daniel.leidert@wgdd.de\&>
+for the Debian project (but may be used by others).