This document describes how to train and use a cascade of boosted classifiers for rapid object detection. A large set of over-complete haar-like features provide the basis for the simple individual classifiers. Examples of object detection tasks are face, eye and nose detection, as well as logo detection.
The sample detection task in this document is logo detection, since logo detection does not require the collection of large set of registered and carefully marked object samples. Instead we assume that from one prototype image, a very large set of derived object examples can be derived (createsamples utility, see below).
A detailed description of the training/evaluation algorithm can be found in [1] and [2].
For training a training samples must be collected. There are two sample types: negative samples and positive samples. Negative samples correspond to non-object images. Positive samples correspond to object images.
Negative samples are taken from arbitrary images. These images must not contain object representations. Negative samples are passed through background description file. It is a text file in which each text line contains the filename (relative to the directory of the description file) of negative sample image. This file must be created manually. Note that the negative samples and sample images are also called background samples or background samples images, and are used interchangeably in this document
Example of negative description file:
Directory structure:
/img
img1.jpg
img2.jpg
bg.txt
File bg.txt:
img/img1.jpg
img/img2.jpg
Positive samples are created by createsamples
utility. They may be created from single object image or from collection of
previously marked up images.
The single object image may for instance contain a company logo. Then are large set of positive samples are created from the given object image by randomly rotating, changing the logo color as well as placing the logo on arbitrary background.
The amount and range of randomness can be controlled by command line arguments.
Command line arguments:
- vec <vec_file_name>
name of the output file containing the positive samples for training
- img <image_file_name>
source object image (e.g., a company logo)
- bg <background_file_name>
background description file; contains a list of images into which randomly distorted versions of the object are pasted for positive sample generation
- num <number_of_samples>
number of positive samples to generate
- bgcolor <background_color>
background color (currently grayscale images are assumed); the background color denotes the transparent color. Since there might be compression artifacts, the amount of color tolerance can be specified by –bgthresh. All pixels between bgcolor-bgthresh and bgcolor+bgthresh are regarded as transparent.
- bgthresh <background_color_threshold>
- inv
if specified, the colors will be inverted
- randinv
if specified, the colors will be inverted randomly
- maxidev <max_intensity_deviation>
maximal intensity deviation of foreground samples pixels
- maxxangle <max_x_rotation_angle>,
- maxyangle <max_y_rotation_angle>,
- maxzangle <max_z_rotation_angle>
maximum rotation angles in radians
-show
if specified, each sample will be shown. Pressing ‘Esc’ will continue creation process without samples showing. Useful debugging option.
- w <sample_width>
width (in pixels) of the output samples
- h <sample_height>
height (in pixels) of the output samples
For following procedure is used to create a sample object instance:
The source image is rotated random around all three axes. The chosen angle is limited my -max?angle. Next pixels of intensities in the range of [bg_color-bg_color_threshold; bg_color+bg_color_threshold] are regarded as transparent. White noise is added to the intensities of the foreground. If –inv key is specified then foreground pixel intensities are inverted. If –randinv key is specified then it is randomly selected whether for this sample inversion will be applied. Finally, the obtained image is placed onto arbitrary background from the background description file, resized to the pixel size specified by –w and –h and stored into the file specified by the –vec command line parameter.
Positive samples also may be obtained from a collection of previously marked up images. This collection is described by text file similar to background description file. Each line of this file corresponds to collection image. The first element of the line is image file name. It is followed by number of object instances. The following numbers are the coordinates of bounding rectangles (x, y, width, height).
Example of description file:
Directory structure:
/img
img1.jpg
img2.jpg
info.dat
File info.dat:
img/img1.jpg 1 140 100 45 45
img/img2.jpg 2 100 200 50 50 50 30 25 25
Image img1.jpg contains single object instance with bounding rectangle (140, 100, 45, 45). Image img2.jpg contains two object instances.
In order to create positive samples from such collection –info argument should be specified instead of –img:
- info <collection_file_name>
description file of marked up images collection
The scheme of sample creation in this case is as follows. The object instances are taken from images. Then they are resized to samples size and stored in output file. No distortion is applied, so the only affecting arguments are –w, -h, -show and –num.
createsamples utility may be used for examining samples stored in positive samples file. In order to do this only –vec, –w and –h parameters should be specified.
Note that for training, it does not matter how positive samples files are generated. So the createsamples utility is only one way to collect/create a vector file of positive samples.
The next step after samples creation is training of classifier. It is performed by the haartraining utility.
Command line arguments:
- data <dir_name>
directory name in which the trained classifier is stored
- vec <vec_file_name>
file name of positive sample file (created by trainingsamples utility or by any other means)
- bg <background_file_name>
background description file
- npos <number_of_positive_samples>,
- nneg <number_of_negative_samples>
number of positive/negative samples used in training of each classifier stage. Reasonable values are npos = 7000 and nneg = 3000.
- nstages <number_of_stages>
number of stages to be trained
- nsplits <number_of_splits>
determines the weak classifier used in stage classifiers. If 1, then a simple stump classifier is used, if 2 and more, then CART classifier with number_of_splits internal (split) nodes is used
- mem <memory_in_MB>
Available memory in MB for precalculation. The more memory you have the faster the training process
- sym (default),
- nonsym
specifies whether the object class under training has vertical symmetry or not. Vertical symmetry speeds up training process. For instance, frontal faces show off vertical symmetry
- minhitrate <min_hit_rate>
minimal desired hit rate for each stage classifier. Overall hit rate may be estimated as (min_hit_rate^number_of_stages)
- maxfalsealarm <max_false_alarm_rate>
maximal desired false alarm rate for each stage classifier. Overall false alarm rate may be estimated as (max_false_alarm_rate^number_of_stages)
- weighttrimming <weight_trimming>
Specifies wheter and how much weight trimming should be used. A decent choice is 0.90.
- eqw
- mode <BASIC (default) | CORE | ALL>
selects the type of haar features set used in training. BASIC use only upright features, while ALL uses the full set of upright and 45 degree rotated feature set. See [1] for more details.
- w <sample_width>,
- h <sample_height>
Size of training samples (in pixels). Must have exactly the same values as used during training samples creation (utility trainingsamples)
Note: in order to use multiprocessor advantage a compiler that supports OpenMP 1.0 standard should be used.
OpenCV cvHaarDetectObjects() function (in particular haarFaceDetect demo) is used for detection.
In order to evaluate the performance of trained classifier a collection of marked up images is needed. When such collection is not available test samples may be created from single object image by createsamples utility. The scheme of test samples creation in this case is similar to training samples creation since each test sample is a background image into which a randomly distorted and randomly scaled instance of the object picture is pasted at a random position.
If both –img and –info arguments are specified then test samples will be created by createsamples utility. The sample image is arbitrary distorted as it was described below, then it is placed at random location to background image and stored. The corresponding description line is added to the file specified by –info argument.
The –w and –h keys determine the minimal size of placed object picture.
The test image file name format is as follows:
imageOrderNumber_x_y_width_height.jpg, where x, y, width and height are the coordinates of placed object bounding rectangle.
Note that you should use a background images set different from the background image set used during training.
In order to evaluate the performance of the classifier performance utility may be used. It takes a collection of marked up 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.
Command line arguments:
- data <dir_name>
directory name in which the trained classifier is stored
- info <collection_file_name>
file with test samples description
- maxSizeDiff <max_size_difference>,
- maxPosDiff <max_position_difference>
determine the criterion of reference and detected rectangles coincidence. Default values are 1.5 and 0.3 respectively.
- sf <scale_factor>,
detection parameter. Default value is 1.2.
- w <sample_width>,
- h <sample_height>
Size of training samples (in pixels). Must have exactly the same values as used during training (utility haartraining)
[1] Rainer Lienhart and Jochen Maydt. An Extended Set of Haar-like Features for Rapid Object Detection. Submitted to ICIP2002.
[2] Alexander Kuranov, Rainer Lienhart, and Vadim Pisarevsky. An Empirical Analysis of Boosting Algorithms for Rapid Objects With an Extended Set of Haar-like Features. Intel Technical Report MRL-TR-July02-01, 2002.