def test_ellipse_fitting(self,
name='insitu7545',
table_prob=TABLE_FB_PROBA):
""" """
img, _ = tl_data.load_image_2d(os.path.join(PATH_IMAGES,
name + '.jpg'))
seg, _ = tl_data.load_image_2d(os.path.join(PATH_SEGM, name + '.png'))
annot, _ = tl_data.load_image_2d(
os.path.join(PATH_ANNOT, name + '.png'))
path_center = os.path.join(PATH_CENTRE, name + '.csv')
centers = pd.read_csv(path_center, index_col=0).values[:, [1, 0]]
slic, points_all, labels = seg_fit.get_slic_points_labels(
seg, slic_size=20, slic_regul=0.3)
weights = np.bincount(slic.ravel())
points_centers = seg_fit.prepare_boundary_points_ray_edge(
seg, centers, close_points=5)
segm = np.zeros(seg.shape)
ellipses, crits = [], []
for i, points in enumerate(points_centers):
model, _ = seg_fit.ransac_segm(points,
seg_fit.EllipseModelSegm,
points_all,
weights,
labels,
table_prob,
min_samples=0.6,
residual_threshold=15,
max_trials=50)
if model is None:
continue
ellipses.append(model.params)
crit = model.criterion(points_all, weights, labels, table_prob)
crits.append(np.round(crit))
logging.info('model params: %s', repr(model.params))
logging.info('-> crit: %f', crit)
c1, c2, h, w, phi = model.params
rr, cc = tl_visu.ellipse(int(c1), int(c2), int(h), int(w), phi,
segm.shape)
segm[rr, cc] = (i + 1)
if img.ndim == 3:
img = img[:, :, 0]
fig = tl_visu.figure_ellipse_fitting(img, seg, ellipses, centers,
crits)
fig_name = 'ellipse-fitting_%s.pdf' % name
fig.savefig(os.path.join(PATH_OUTPUT, fig_name),
bbox_inches='tight',
pad_inches=0)
plt.close(fig)
score = adjusted_rand_score(annot.ravel(), segm.ravel())
self.assertGreaterEqual(score, 0.5)
def segment_fit_ellipse_ransac_segm(seg,
centers,
fn_preproc_points,
table_p,
nb_inliers=0.35,
thr_overlap=SEGM_OVERLAP):
""" segment eggs using ellipse fitting and RANDSAC strategy on segmentation
:param ndarray seg: input image / segmentation
:param [[int, int]] centers: position of centres / seeds
:param fn_preproc_points: function for detection boundary points
:param [[float]] table_p: table of probabilities being foreground / background
:param float nb_inliers: ratio of inliers for RANSAC
:param float thr_overlap: threshold for removing overlapping segmentations
:return (ndarray, [[int, int]]): resulting segmentation, updated centres
"""
slic, points_all, labels = ell_fit.get_slic_points_labels(seg,
slic_size=15,
slic_regul=0.1)
points_centers = fn_preproc_points(seg, centers)
weights = np.bincount(slic.ravel())
centres_new, ell_params = [], []
segm = np.zeros_like(seg)
for i, points in enumerate(points_centers):
lb = i + 1
ransac_model, _ = ell_fit.ransac_segm(points,
ell_fit.EllipseModelSegm,
points_all,
weights,
labels,
table_p,
min_samples=nb_inliers,
residual_threshold=25,
max_trials=250)
if ransac_model is None:
continue
logging.debug('ellipse params: %s', repr(ransac_model.params))
segm = ell_fit.add_overlap_ellipse(segm, ransac_model.params, lb,
thr_overlap)
if np.any(segm == lb):
centres_new.append(centers[i])
ell_params.append(ransac_model.params)
dict_export = {
'ellipses.csv':
pd.DataFrame(ell_params, columns=['xc', 'yc', 'a', 'b', 'theta'])
}
return segm, np.array(centres_new), dict_export