---
name: "opencv-performance"
section: "1"
platform: "linux"
package: "libcv-dev"
version: "1.0.0-6.1"
release: "Debian 5.0 (Lenny)"
platforms: ["linux"]
url: "https://new.carta.tech/opencv-performance"
---

# opencv-performance(1)

evaluate the performance of the classifier

## NAME

opencv-performance - evaluate the performance of the classifier

## SYNOPSIS

**opencv-performance \[options\]**

## DESCRIPTION

**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)](/opencv-createsamples/1.md) utility. The scheme of test samples creation in this case is similar to training samples

In the output, the table should be read:

- '**Hits**'

  shows the number of correctly found objects

- '**Missed**'

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

- '**False**'

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

## OPTIONS

**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*.

- **-ni**

  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.

## EXAMPLES

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

-

  **opencv-performance -data trainout -info tests.dat**

## SEE ALSO

[**opencv-createsamples**(1)](/opencv-createsamples/1.md), **opencv-haartraing**(1)

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

## AUTHORS

This manual page was written by **Daniel Leidert** \<daniel.leidert@wgdd.de\> for the Debian project (but may be used by others).