int main(int argc, char** argv)
{
static struct option icf_options[] = {
/* help */
{"help", 0, 0, 0},
/* required parameters */
{"positive-list", 1, 0, 0},
{"background-list", 1, 0, 0},
{"validate-list", 1, 0, 0},
{"working-dir", 1, 0, 0},
{"negative-count", 1, 0, 0},
{"positive-count", 1, 0, 0},
{"acceptance", 1, 0, 0},
{"size", 1, 0, 0},
{"feature-size", 1, 0, 0},
{"weak-classifier-count", 1, 0, 0},
/* optional parameters */
{"base-dir", 1, 0, 0},
{"grayscale", 1, 0, 0},
{"margin", 1, 0, 0},
{"deform-shift", 1, 0, 0},
{"deform-angle", 1, 0, 0},
{"deform-scale", 1, 0, 0},
{"min-dimension", 1, 0, 0},
{"bootstrap", 1, 0, 0},
{0, 0, 0, 0}
};
char* positive_list = 0;
char* background_list = 0;
char* validate_list = 0;
char* working_dir = 0;
char* base_dir = 0;
int negative_count = 0;
int positive_count = 0;
ccv_icf_new_param_t params = {
.grayscale = 0,
.margin = ccv_margin(0, 0, 0, 0),
.size = ccv_size(0, 0),
.deform_shift = 1,
.deform_angle = 0,
.deform_scale = 0.075,
.feature_size = 0,
.weak_classifier = 0,
.min_dimension = 2,
.bootstrap = 3,
.detector = ccv_icf_default_params,
};
params.detector.step_through = 4; // for faster negatives bootstrap time
int i, k;
char* token;
char* saveptr;
while (getopt_long_only(argc, argv, "", icf_options, &k) != -1)
{
switch (k)
{
case 0:
exit_with_help();
case 1:
positive_list = optarg;
break;
case 2:
background_list = optarg;
break;
case 3:
validate_list = optarg;
break;
case 4:
working_dir = optarg;
break;
case 5:
negative_count = atoi(optarg);
break;
case 6:
positive_count = atoi(optarg);
break;
case 7:
params.acceptance = atof(optarg);
break;
case 8:
token = strtok_r(optarg, "x", &saveptr);
params.size.width = atoi(token);
token = strtok_r(0, "x", &saveptr);
params.size.height = atoi(token);
break;
case 9:
params.feature_size = atoi(optarg);
break;
case 10:
params.weak_classifier = atoi(optarg);
break;
case 11:
base_dir = optarg;
break;
case 12:
params.grayscale = !!atoi(optarg);
break;
case 13:
token = strtok_r(optarg, ",", &saveptr);
params.margin.left = atoi(token);
token = strtok_r(0, ",", &saveptr);
params.margin.top = atoi(token);
token = strtok_r(0, ",", &saveptr);
params.margin.right = atoi(token);
token = strtok_r(0, ",", &saveptr);
params.margin.bottom = atoi(token);
break;
case 14:
params.deform_shift = atof(optarg);
break;
case 15:
params.deform_angle = atof(optarg);
break;
case 16:
params.deform_scale = atof(optarg);
break;
case 17:
params.min_dimension = atoi(optarg);
break;
case 18:
params.bootstrap = atoi(optarg);
break;
}
}
assert(positive_list != 0);
assert(background_list != 0);
assert(validate_list != 0);
assert(working_dir != 0);
assert(positive_count > 0);
assert(negative_count > 0);
assert(params.size.width > 0);
assert(params.size.height > 0);
ccv_enable_cache(512 * 1024 * 1024);
FILE* r0 = fopen(positive_list, "r");
assert(r0 && "positive-list doesn't exists");
FILE* r1 = fopen(background_list, "r");
assert(r1 && "background-list doesn't exists");
FILE* r2 = fopen(validate_list, "r");
assert(r2 && "validate-list doesn't exists");
char* file = (char*)malloc(1024);
ccv_decimal_pose_t pose;
int dirlen = (base_dir != 0) ? strlen(base_dir) + 1 : 0;
ccv_array_t* posfiles = ccv_array_new(sizeof(ccv_file_info_t), 32, 0);
// roll pitch yaw
while (fscanf(r0, "%s %f %f %f %f %f %f %f", file, &pose.x, &pose.y, &pose.a, &pose.b, &pose.roll, &pose.pitch, &pose.yaw) != EOF)
{
ccv_file_info_t file_info;
file_info.filename = (char*)ccmalloc(1024);
if (base_dir != 0)
{
strncpy(file_info.filename, base_dir, 1024);
file_info.filename[dirlen - 1] = '/';
}
strncpy(file_info.filename + dirlen, file, 1024 - dirlen);
file_info.pose = pose;
ccv_array_push(posfiles, &file_info);
}
fclose(r0);
size_t len = 1024;
ssize_t read;
ccv_array_t* bgfiles = (ccv_array_t*)ccv_array_new(sizeof(ccv_file_info_t), 32, 0);
while ((read = getline(&file, &len, r1)) != -1)
{
while(read > 1 && isspace(file[read - 1]))
read--;
file[read] = 0;
ccv_file_info_t file_info;
file_info.filename = (char*)ccmalloc(1024);
if (base_dir != 0)
{
strncpy(file_info.filename, base_dir, 1024);
file_info.filename[dirlen - 1] = '/';
}
strncpy(file_info.filename + dirlen, file, 1024 - dirlen);
ccv_array_push(bgfiles, &file_info);
}
fclose(r1);
ccv_array_t* validatefiles = ccv_array_new(sizeof(ccv_file_info_t), 32, 0);
// roll pitch yaw
while (fscanf(r2, "%s %f %f %f %f %f %f %f", file, &pose.x, &pose.y, &pose.a, &pose.b, &pose.roll, &pose.pitch, &pose.yaw) != EOF)
{
ccv_file_info_t file_info;
file_info.filename = (char*)ccmalloc(1024);
if (base_dir != 0)
{
strncpy(file_info.filename, base_dir, 1024);
file_info.filename[dirlen - 1] = '/';
}
strncpy(file_info.filename + dirlen, file, 1024 - dirlen);
file_info.pose = pose;
ccv_array_push(validatefiles, &file_info);
}
fclose(r2);
free(file);
ccv_icf_classifier_cascade_t* classifier = ccv_icf_classifier_cascade_new(posfiles, positive_count, bgfiles, negative_count, validatefiles, working_dir, params);
char filename[1024];
snprintf(filename, 1024, "%s/final-cascade", working_dir);
ccv_icf_write_classifier_cascade(classifier, filename);
for (i = 0; i < posfiles->rnum; i++)
{
ccv_file_info_t* file_info = (ccv_file_info_t*)ccv_array_get(posfiles, i);
free(file_info->filename);
}
ccv_array_free(posfiles);
for (i = 0; i < bgfiles->rnum; i++)
{
ccv_file_info_t* file_info = (ccv_file_info_t*)ccv_array_get(bgfiles, i);
free(file_info->filename);
}
ccv_array_free(bgfiles);
for (i = 0; i < validatefiles->rnum; i++)
{
ccv_file_info_t* file_info = (ccv_file_info_t*)ccv_array_get(validatefiles, i);
free(file_info->filename);
}
ccv_array_free(validatefiles);
ccv_disable_cache();
return 0;
}
void ccv_enable_default_cache(void)
{
ccv_enable_cache(CCV_DEFAULT_CACHE_SIZE);
}
int main(int argc, char** argv)
{
static struct option swt_options[] = {
/* help */
{"help", 0, 0, 0},
/* optional parameters */
{"size", 1, 0, 0},
{"low-thresh", 1, 0, 0},
{"high-thresh", 1, 0, 0},
{"max-height", 1, 0, 0},
{"min-height", 1, 0, 0},
{"min-area", 1, 0, 0},
{"aspect-ratio", 1, 0, 0},
{"std-ratio", 1, 0, 0},
{"thickness-ratio", 1, 0, 0},
{"height-ratio", 1, 0, 0},
{"intensity-thresh", 1, 0, 0},
{"letter-occlude-thresh", 1, 0, 0},
{"distance-ratio", 1, 0, 0},
{"intersect-ratio", 1, 0, 0},
{"letter-thresh", 1, 0, 0},
{"elongate-ratio", 1, 0, 0},
{"breakdown-ratio", 1, 0, 0},
{"breakdown", 1, 0, 0},
{"iterations", 1, 0, 0},
{"base-dir", 1, 0, 0},
{0, 0, 0, 0}
};
if (argc <= 1)
exit_with_help();
ccv_swt_param_t params = {
.interval = 1,
.same_word_thresh = { 0.2, 0.8 },
.min_neighbors = 1,
.scale_invariant = 0,
.size = 3,
.low_thresh = 78,
.high_thresh = 214,
.max_height = 300,
.min_height = 10,
.min_area = 75,
.letter_occlude_thresh = 2,
.aspect_ratio = 10,
.std_ratio = 0.5,
.thickness_ratio = 1.5,
.height_ratio = 2.0,
.intensity_thresh = 45,
.distance_ratio = 3.0,
.intersect_ratio = 2.0,
.letter_thresh = 3,
.elongate_ratio = 1.3,
.breakdown = 1,
.breakdown_ratio = 1.0,
};
ccv_swt_range_t size_range = {
.min_value = 1,
.max_value = 3,
.step = 2,
.enable = 1,
};
ccv_swt_range_t low_thresh_range = {
.min_value = 50,
.max_value = 150,
.step = 1,
.enable = 1,
};
ccv_swt_range_t high_thresh_range = {
.min_value = 200,
.max_value = 350,
.step = 1,
.enable = 1,
};
ccv_swt_range_t max_height_range = {
.min_value = 500,
.max_value = 500,
.step = 1,
.enable = 1,
};
ccv_swt_range_t min_height_range = {
.min_value = 5,
.max_value = 30,
.step = 1,
.enable = 1,
};
ccv_swt_range_t min_area_range = {
.min_value = 10,
.max_value = 100,
.step = 1,
.enable = 1,
};
ccv_swt_range_t letter_occlude_thresh_range = {
.min_value = 0,
.max_value = 5,
.step = 1,
.enable = 1,
};
ccv_swt_range_t aspect_ratio_range = {
.min_value = 5,
.max_value = 15,
.step = 1,
.enable = 1,
};
ccv_swt_range_t std_ratio_range = {
.min_value = 0.1,
.max_value = 1.0,
.step = 0.01,
.enable = 1,
};
ccv_swt_range_t thickness_ratio_range = {
.min_value = 1.0,
.max_value = 2.0,
.step = 0.1,
.enable = 1,
};
ccv_swt_range_t height_ratio_range = {
.min_value = 1.0,
.max_value = 3.0,
.step = 0.1,
.enable = 1,
};
ccv_swt_range_t intensity_thresh_range = {
.min_value = 1,
.max_value = 50,
.step = 1,
.enable = 1,
};
ccv_swt_range_t distance_ratio_range = {
.min_value = 1.0,
.max_value = 5.0,
.step = 0.1,
.enable = 1,
};
ccv_swt_range_t intersect_ratio_range = {
.min_value = 0.0,
.max_value = 5.0,
.step = 0.1,
.enable = 1,
};
ccv_swt_range_t letter_thresh_range = {
.min_value = 0,
.max_value = 5,
.step = 1,
.enable = 1,
};
ccv_swt_range_t elongate_ratio_range = {
.min_value = 0.1,
.max_value = 2.5,
.step = 0.1,
.enable = 1,
};
ccv_swt_range_t breakdown_ratio_range = {
.min_value = 0.5,
.max_value = 1.5,
.step = 0.01,
.enable = 1,
};
int i, j, k, iterations = 10;
while (getopt_long_only(argc - 1, argv + 1, "", swt_options, &k) != -1)
{
switch (k)
{
case 0:
exit_with_help();
case 1:
decode_range(optarg, &size_range);
break;
case 2:
decode_range(optarg, &low_thresh_range);
break;
case 3:
decode_range(optarg, &high_thresh_range);
break;
case 4:
decode_range(optarg, &max_height_range);
break;
case 5:
decode_range(optarg, &min_height_range);
break;
case 6:
decode_range(optarg, &min_area_range);
break;
case 7:
decode_range(optarg, &aspect_ratio_range);
break;
case 8:
decode_range(optarg, &std_ratio_range);
break;
case 9:
decode_range(optarg, &thickness_ratio_range);
break;
case 10:
decode_range(optarg, &height_ratio_range);
break;
case 11:
decode_range(optarg, &intensity_thresh_range);
break;
case 12:
decode_range(optarg, &letter_occlude_thresh_range);
break;
case 13:
decode_range(optarg, &distance_ratio_range);
break;
case 14:
decode_range(optarg, &intersect_ratio_range);
break;
case 15:
decode_range(optarg, &letter_thresh_range);
break;
case 16:
decode_range(optarg, &elongate_ratio_range);
break;
case 17:
decode_range(optarg, &breakdown_ratio_range);
break;
case 18:
params.breakdown = !!atoi(optarg);
break;
case 19:
iterations = atoi(optarg);
break;
case 20:
chdir(optarg);
break;
}
}
FILE* r = fopen(argv[1], "rt");
if (!r)
exit_with_help();
ccv_enable_cache(1024 * 1024 * 1024);
ccv_array_t* aof = ccv_array_new(sizeof(char*), 64, 0);
ccv_array_t* aow = ccv_array_new(sizeof(ccv_array_t*), 64, 0);
ccv_array_t* cw = 0;
char* file = (char*)malloc(1024);
size_t len = 1024;
ssize_t read;
while ((read = getline(&file, &len, r)) != -1)
{
while(read > 1 && isspace(file[read - 1]))
read--;
file[read] = 0;
double x, y, width, height;
int recognized = sscanf(file, "%lf %lf %lf %lf", &x, &y, &width, &height);
if (recognized == 4)
{
ccv_rect_t rect = {
.x = (int)(x + 0.5),
.y = (int)(y + 0.5),
.width = (int)(width + 0.5),
.height = (int)(height + 0.5)
};
ccv_array_push(cw, &rect);
} else {
char* name = (char*)malloc(ccv_min(1023, strlen(file)) + 1);
strncpy(name, file, ccv_min(1023, strlen(file)) + 1);
ccv_array_push(aof, &name);
cw = ccv_array_new(sizeof(ccv_rect_t), 1, 0);
ccv_array_push(aow, &cw);
}
}
free(file);
printf("loaded %d images for parameter search of:\n", aof->rnum);
if (size_range.enable)
printf(" - canny size from %d to %d, += %lg\n", (int)(size_range.min_value + 0.5), (int)(size_range.max_value + 0.5), size_range.step);
if (std_ratio_range.enable)
printf(" - std threshold ratio from %lg to %lg, += %lg\n", std_ratio_range.min_value, std_ratio_range.max_value, std_ratio_range.step);
if (max_height_range.enable)
printf(" - maximum height from %d to %d, += %lg\n", (int)(max_height_range.min_value + 0.5), (int)(max_height_range.max_value + 0.5), max_height_range.step);
if (min_height_range.enable)
printf(" - minimum height from %d to %d, += %lg\n", (int)(min_height_range.min_value + 0.5), (int)(min_height_range.max_value + 0.5), min_height_range.step);
if (min_area_range.enable)
printf(" - minimum area from %d to %d, += %lg\n", (int)(min_area_range.min_value + 0.5), (int)(min_area_range.max_value + 0.5), min_area_range.step);
if (letter_occlude_thresh_range.enable)
printf(" - letter occlude threshold from %d to %d, += %lg\n", (int)(letter_occlude_thresh_range.min_value + 0.5), (int)(letter_occlude_thresh_range.max_value + 0.5), letter_occlude_thresh_range.step);
if (aspect_ratio_range.enable)
printf(" - aspect ratio threshold from %lg to %lg, += %lg\n", aspect_ratio_range.min_value, aspect_ratio_range.max_value, aspect_ratio_range.step);
if (thickness_ratio_range.enable)
printf(" - thickness ratio threshold from %lg to %lg, += %lg\n", thickness_ratio_range.min_value, thickness_ratio_range.max_value, thickness_ratio_range.step);
if (height_ratio_range.enable)
printf(" - height ratio threshold from %lg to %lg, += %lg\n", height_ratio_range.min_value, height_ratio_range.max_value, height_ratio_range.step);
if (intensity_thresh_range.enable)
printf(" - intensity threshold from %d to %d, += %lg\n", (int)(intensity_thresh_range.min_value + 0.5), (int)(intensity_thresh_range.max_value + 0.5), intensity_thresh_range.step);
if (distance_ratio_range.enable)
printf(" - distance ratio threshold from %lg to %lg, += %lg\n", distance_ratio_range.min_value, distance_ratio_range.max_value, distance_ratio_range.step);
if (intersect_ratio_range.enable)
printf(" - intersect ratio threshold from %lg to %lg, += %lg\n", intersect_ratio_range.min_value, intersect_ratio_range.max_value, intersect_ratio_range.step);
if (letter_thresh_range.enable)
printf(" - minimum number of letters from %d to %d, += %lg\n", (int)(letter_thresh_range.min_value + 0.5), (int)(letter_thresh_range.max_value + 0.5), letter_thresh_range.step);
if (elongate_ratio_range.enable)
printf(" - elongate ratio threshold from %lg to %lg, += %lg\n", elongate_ratio_range.min_value, elongate_ratio_range.max_value, elongate_ratio_range.step);
if (breakdown_ratio_range.enable)
printf(" - breakdown ratio threshold from %lg to %lg, += %lg\n", breakdown_ratio_range.min_value, breakdown_ratio_range.max_value, breakdown_ratio_range.step);
if (low_thresh_range.enable)
printf(" - canny low threshold from %d to %d, += %lg\n", (int)(low_thresh_range.min_value + 0.5), (int)(low_thresh_range.max_value + 0.5), low_thresh_range.step);
if (high_thresh_range.enable)
printf(" - canny high threshold from %d to %d, += %lg\n", (int)(high_thresh_range.min_value + 0.5), (int)(high_thresh_range.max_value + 0.5), high_thresh_range.step);
double best_f = 0, best_precision = 0, best_recall = 0;
double a = 0.5;
double v;
ccv_swt_param_t best_params = params;
#define optimize(parameter, type, rounding) \
if (parameter##_range.enable) \
{ \
params = best_params; \
int total_iterations = 0; \
for (v = parameter##_range.min_value; v <= parameter##_range.max_value; v += parameter##_range.step) \
++total_iterations; \
double* precision = (double*)ccmalloc(sizeof(double) * total_iterations); \
double* recall = (double*)ccmalloc(sizeof(double) * total_iterations); \
double* total_words = (double*)ccmalloc(sizeof(double) * total_iterations); \
memset(precision, 0, sizeof(double) * total_iterations); \
memset(recall, 0, sizeof(double) * total_iterations); \
memset(total_words, 0, sizeof(double) * total_iterations); \
double total_truth = 0; \
for (j = 0; j < aof->rnum; j++) \
{ \
char* name = *(char**)ccv_array_get(aof, j); \
ccv_dense_matrix_t* image = 0; \
ccv_read(name, &image, CCV_IO_GRAY | CCV_IO_ANY_FILE); \
ccv_array_t* truth = *(ccv_array_t**)ccv_array_get(aow, j); \
total_truth += truth->rnum; \
for (v = parameter##_range.min_value, k = 0; v <= parameter##_range.max_value; v += parameter##_range.step, k++) \
{ \
params.parameter = (type)(v + rounding); \
ccv_array_t* words = ccv_swt_detect_words(image, params); \
double one_precision = 0, one_recall = 0; \
_ccv_evaluate_wolf(words, truth, params, &one_precision, &one_recall); \
assert(one_precision <= words->rnum + 0.1); \
precision[k] += one_precision; \
recall[k] += one_recall; \
total_words[k] += words->rnum; \
ccv_array_free(words); \
FLUSH("perform SWT on %s (%d / %d) for " #parameter " = (%lg <- [%lg, %lg])", name, j + 1, aof->rnum, v, parameter##_range.min_value, parameter##_range.max_value); \
} \
ccv_matrix_free(image); \
} \
for (v = parameter##_range.min_value, j = 0; v <= parameter##_range.max_value; v += parameter##_range.step, j++) \
{ \
params.parameter = (type)(v + rounding); \
double f, total_precision = precision[j], total_recall = recall[j]; \
total_precision /= total_words[j]; \
total_recall /= total_truth; \
f = 1.0 / (a / total_precision + (1.0 - a) / total_recall); \
if (f > best_f) \
{ \
best_params = params; \
best_f = f; \
best_precision = total_precision; \
best_recall = total_recall; \
} \
FLUSH("current harmonic mean : %.2lf%%, precision : %.2lf%%, recall : %.2lf%% ; best harmonic mean : %.2lf%%, precision : %.2lf%%, recall : %.2lf%% ; at " #parameter " = %lg (%lg <- [%lg, %lg])", f * 100, total_precision * 100, total_recall * 100, best_f * 100, best_precision * 100, best_recall * 100, (double)best_params.parameter, v, parameter##_range.min_value, parameter##_range.max_value); \
} \
printf("\n"); \
ccfree(precision); \
ccfree(recall); \
ccfree(total_words); \
}
for (i = 0; i < iterations; i++)
{
optimize(size, int, 0.5);
optimize(std_ratio, double, 0);
optimize(max_height, int, 0.5);
optimize(min_height, int, 0.5);
optimize(min_area, int, 0.5);
optimize(letter_occlude_thresh, int, 0.5);
optimize(aspect_ratio, double, 0);
optimize(thickness_ratio, double, 0);
optimize(height_ratio, double, 0);
optimize(intensity_thresh, int, 0.5);
optimize(distance_ratio, double, 0);
optimize(intersect_ratio, double, 0);
optimize(letter_thresh, int, 0.5);
optimize(elongate_ratio, double, 0);
optimize(breakdown_ratio, double, 0);
optimize(low_thresh, int, 0.5);
optimize(high_thresh, int, 0.5);
printf("At iteration %d(of %d) : best parameters for swt is:\n"
"\tsize = %d\n"
"\tlow_thresh = %d\n"
"\thigh_thresh = %d\n"
"\tmax_height = %d\n"
"\tmin_height = %d\n"
"\tmin_area = %d\n"
"\tletter_occlude_thresh = %d\n"
"\taspect_ratio = %lf\n"
"\tstd_ratio = %lf\n"
"\tthickness_ratio = %lf\n"
"\theight_ratio = %lf\n"
"\tintensity_thresh = %d\n"
"\tdistance_ratio = %lf\n"
"\tintersect_ratio = %lf\n"
"\tletter_thresh = %d\n"
"\telongate_ratio = %lf\n"
"\tbreakdown_ratio = %lf\n",
i + 1, iterations,
best_params.size,
best_params.low_thresh,
best_params.high_thresh,
best_params.max_height,
best_params.min_height,
best_params.min_area,
best_params.letter_occlude_thresh,
best_params.aspect_ratio,
best_params.std_ratio,
best_params.thickness_ratio,
best_params.height_ratio,
best_params.intensity_thresh,
best_params.distance_ratio,
best_params.intersect_ratio,
best_params.letter_thresh,
best_params.elongate_ratio,
best_params.breakdown_ratio);
}
#undef optimize
for (i = 0; i < aof->rnum; i++)
{
char* name = *(char**)ccv_array_get(aof, i);
free(name);
ccv_array_t* cw = *(ccv_array_t**)ccv_array_get(aow, i);
ccv_array_free(cw);
}
ccv_array_free(aof);
ccv_array_free(aow);
ccv_drain_cache();
return 0;
}
