lib/ccv_icf.c

ccv_icf_classifier_cascade_new

ccv_icf_classifier_cascade_new(ccv_array_t *posfiles, int posnum, ccv_array_t *bgfiles, int negnum, ccv_array_t *testfiles, const char *dir, ccv_icf_new_param_t params)

Create a new ICF classifier cascade from given positive examples and background images. This function has a hard dependency on GSL and better be used with libdispatch for maximum efficiency.

posfiles: An array of ccv_file_info_t that gives the positive examples and their locations.
posnum: The number of positive examples that we want to use (with certain random distortions if so choose).
bgfiles: An array of ccv_file_info_t that gives the background images.
negnum: The number of negative examples will be collected during bootstrapping / initialization.
testfiles: An array of ccv_file_info_t that gives the validation examples and their locations.
dir: The directory that saves the progress.
params: A ccv_icf_new_param_t structure that defines various aspects of the training function.

return: A trained classifier cascade.

ccv_icf_new_param_t

acceptance: The percentage of validation examples will be accepted when soft cascading the classifiers that will be sued for bootstrap.
bootstrap: The number of boostrap to collect negatives.
deform_angle: The range of rotations to add distortion, in radius.
deform_scale: The range of scale changes to add distortion.
deform_shift: The range of translations to add distortion, in pixel.
detector: A ccv_icf_param_t structure that defines various aspects of the detector.
feature_size: The number of ICF features to pool from.
grayscale: Whether to exploit color in a given image.
min_dimension: The minimal size of a ICF feature region.
size: A ccv_size_t structure that defines the width and height of the classifier.
weak_classifier: The number of weak classifiers that will be used to construct the strong classifier.

ccv_icf_param_t

interval: Interval images between the full size image and the half size one. e.g. 2 will generate 2 images in between full size image and half size one: image with full size, image with 5/6 size, image with 2/3 size, image with 1/2 size.
min_neighbors: 0: no grouping afterwards. 1: group objects that intersects each other. > 1: group objects that intersects each other, and only passes these that have at least min_neighbors intersected objects.
step_through: The step size for detection.

ccv_icf_classifier_cascade_soft

void ccv_icf_classifier_cascade_soft(ccv_icf_classifier_cascade_t *cascade, ccv_array_t *posfiles, double acceptance)

Compute soft cascade thresholds to speed up the classifier cascade performance.

cascade: The trained classifier that we want to optimize soft cascade thresholds on.
posfiles: An array of ccv_array_t that gives the positive examples and their locations.
acceptance: The percentage of positive examples will be accepted when optimizing the soft cascade thresholds.

ccv_icf_read_classifier_cascade

ccv_icf_read_classifier_cascade(const char *filename)

Read a ICF classifier from a file.

filename: The file path that contains the trained ICF classifier.

return: The classifier cascade, 0 if no valid classifier cascade available.

ccv_icf_write_classifier_cascade

void ccv_icf_write_classifier_cascade(ccv_icf_classifier_cascade_t *classifier, const char *filename)

Write a ICF classifier to a file.

classifier: The classifier that we want to write to file.
filename: The file path that we want to persist the ICF classifier.

ccv_icf_classifier_cascade_free

void ccv_icf_classifier_cascade_free(ccv_icf_classifier_cascade_t *classifier)

Free up the memory of ICF classifier cascade.

classifier: The ICF classifier cascade.

ccv_icf_detect_objects

ccv_icf_detect_objects(ccv_dense_matrix_t *a, void *cascade, int count, ccv_icf_param_t params)

Using a ICF classifier cascade to detect objects in a given image. If you have several classifier cascades, it is better to use them in one method call. In this way, ccv will try to optimize the overall performance.

a: The input image.
cascade: An array of classifier cascades.
count: How many classifier cascades you’ve passed in.
params: A ccv_icf_param_t structure that defines various aspects of the detector.

return: A ccv_array_t of ccv_comp_t with detection results.