def compute_contour_centers(self):
"""
Compute cell centers for each contour bounding box using meanCenter()
"""
self.contour_centers = np.full((len(self.contours), 2), -1.) # -1: Contour invalid
for i in range(len(self.contours)):
if self.contours[i] is None: continue
self.contour_centers[i] = cv_algorithms.meanCenter(self.contours_bbox[i])
def compute_cell_hulls(self):
"""
Run find_table_cell_polygons() and compute a rectangle enclosing the cell (for each cell).
For most (4-point) cells, this is equivalent to the original path, however this removes
small irregularities and extra points from larger, 5+-point cells (mostly merged cells)
"""
self.compute_cell_polygons()
# cv2 convexHull / minAreaRect only work with integer coordinates.
self.cell_hulls = [
cv2.boxPoints(cv2.minAreaRect(np.rint(self.cluster_coords[path]).astype(int)))
for path in self.cell_polygons]
# Compute centers of cell hulls
self.cell_centers = np.zeros((len(self.cell_hulls), 2))
for i in range(len(self.cell_hulls)):
hull_points = self.cell_hulls[i]
self.cell_centers[i] = cv_algorithms.meanCenter(hull_points)
def find_corner_clusters(self, distance_threshold=20.):
# Find all bounding box corners
corners = []
for i in range(len(self.contours)):
if self.contours[i] is None: continue
bbox = self.contours_bbox[i]
for coord in bbox:
corners.append((coord[0], coord[1]))
# Simpler algorithm, still superfast (<40 ms for 2k corners): Compute all distances using cdist
corners = np.asarray(corners)
distmat = scipy.spatial.distance.cdist(corners, corners, 'euclidean')
ignore = np.zeros(
corners.shape[0],
np.bool) # Set to true if we found a cluster for this node already
# Find cluster in the distance matrix, i.e. node groups which are close together
cluster_coords = [] # For each cluster, a (x,y coordinate pair)
cluster_num_nodes = [
] # For each cluster, the number of nodes it consists of
cluster_coords_to_node_id = {} # (x,y) tuple => cluster ID
for i in range(corners.shape[0]):
if ignore[i]: continue
# Which nodes are close to this node, including itself
below_thresh = distmat[
i, :] < distance_threshold # Rather set this large, we can correct non-convexity later
allnodes = np.nonzero(below_thresh)[0] # index list
# Get a new ID
clusterid = len(cluster_coords)
allcorners = corners[allnodes]
cluster_coords.append(tuple(cv_algorithms.meanCenter(allcorners)))
cluster_num_nodes.append(allnodes.size)
# Also create a map from each position to the current cluster ID
# This works only because these coordinates are discrete integer pixel indices
for coord in allcorners:
cluster_coords_to_node_id[tuple(coord)] = clusterid
# Ignore all nodes in the cluster (i.e. don't assign them to a new cluster)
ignore[allnodes] = True
# Now that the size is known, we can convert to numpy arrays
self.cluster_coords = np.asarray(cluster_coords)
self.cluster_num_nodes = np.asarray(cluster_num_nodes)
self.cluster_coords_to_node_id = cluster_coords_to_node_id
def find_corner_clusters(self, distance_threshold=20.):
# Find all bounding box corners
corners = []
for i in range(len(self.contours)):
if self.contours[i] is None: continue
bbox = self.contours_bbox[i]
for coord in bbox:
corners.append((coord[0], coord[1]))
# Simpler algorithm, still superfast (<40 ms for 2k corners): Compute all distances using cdist
corners = np.asarray(corners)
distmat = scipy.spatial.distance.cdist(corners, corners, 'euclidean')
ignore = np.zeros(corners.shape[0], np.bool) # Set to true if we found a cluster for this node already
# Find cluster in the distance matrix, i.e. node groups which are close together
cluster_coords = [] # For each cluster, a (x,y coordinate pair)
cluster_num_nodes = [] # For each cluster, the number of nodes it consists of
cluster_coords_to_node_id = {} # (x,y) tuple => cluster ID
for i in range(corners.shape[0]):
if ignore[i]: continue
# Which nodes are close to this node, including itself
below_thresh = distmat[i, :] < distance_threshold # Rather set this large, we can correct non-convexity later
allnodes = np.nonzero(below_thresh)[0] # index list
# Get a new ID
clusterid = len(cluster_coords)
allcorners = corners[allnodes]
cluster_coords.append(tuple(cv_algorithms.meanCenter(allcorners)))
cluster_num_nodes.append(allnodes.size)
# Also create a map from each position to the current cluster ID
# This works only because these coordinates are discrete integer pixel indices
for coord in allcorners:
cluster_coords_to_node_id[tuple(coord)] = clusterid
# Ignore all nodes in the cluster (i.e. don't assign them to a new cluster)
ignore[allnodes] = True
# Now that the size is known, we can convert to numpy arrays
self.cluster_coords = np.asarray(cluster_coords)
self.cluster_num_nodes = np.asarray(cluster_num_nodes)
self.cluster_coords_to_node_id = cluster_coords_to_node_id
