144 lines
4.9 KiB
Python
144 lines
4.9 KiB
Python
# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
from __future__ import absolute_import
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
|
|
import numpy as np
|
|
import cv2
|
|
from shapely.geometry import Polygon
|
|
import pyclipper
|
|
|
|
|
|
class DBPostProcess(object):
|
|
"""
|
|
The post process for Differentiable Binarization (DB).
|
|
"""
|
|
|
|
def __init__(self,
|
|
thresh=0.3,
|
|
box_thresh=0.7,
|
|
max_candidates=1000,
|
|
unclip_ratio=2.0,
|
|
**kwargs):
|
|
self.thresh = thresh
|
|
self.box_thresh = box_thresh
|
|
self.max_candidates = max_candidates
|
|
self.unclip_ratio = unclip_ratio
|
|
self.min_size = 3
|
|
|
|
def boxes_from_bitmap(self, pred, _bitmap, dest_width, dest_height):
|
|
'''
|
|
_bitmap: single map with shape (1, H, W),
|
|
whose values are binarized as {0, 1}
|
|
'''
|
|
|
|
bitmap = _bitmap
|
|
height, width = bitmap.shape
|
|
|
|
outs = cv2.findContours((bitmap * 255).astype(np.uint8), cv2.RETR_LIST,
|
|
cv2.CHAIN_APPROX_SIMPLE)
|
|
if len(outs) == 3:
|
|
img, contours, _ = outs[0], outs[1], outs[2]
|
|
elif len(outs) == 2:
|
|
contours, _ = outs[0], outs[1]
|
|
|
|
num_contours = min(len(contours), self.max_candidates)
|
|
|
|
boxes = []
|
|
scores = []
|
|
for index in range(num_contours):
|
|
contour = contours[index]
|
|
points, sside = self.get_mini_boxes(contour)
|
|
if sside < self.min_size:
|
|
continue
|
|
points = np.array(points)
|
|
score = self.box_score_fast(pred, points.reshape(-1, 2))
|
|
if self.box_thresh > score:
|
|
continue
|
|
|
|
box = self.unclip(points).reshape(-1, 1, 2)
|
|
box, sside = self.get_mini_boxes(box)
|
|
if sside < self.min_size + 2:
|
|
continue
|
|
box = np.array(box)
|
|
|
|
box[:, 0] = np.clip(
|
|
np.round(box[:, 0] / width * dest_width), 0, dest_width)
|
|
box[:, 1] = np.clip(
|
|
np.round(box[:, 1] / height * dest_height), 0, dest_height)
|
|
boxes.append(box.astype(np.int16))
|
|
scores.append(score)
|
|
return np.array(boxes, dtype=np.int16), scores
|
|
|
|
def unclip(self, box):
|
|
unclip_ratio = self.unclip_ratio
|
|
poly = Polygon(box)
|
|
distance = poly.area * unclip_ratio / poly.length
|
|
offset = pyclipper.PyclipperOffset()
|
|
offset.AddPath(box, pyclipper.JT_ROUND, pyclipper.ET_CLOSEDPOLYGON)
|
|
expanded = np.array(offset.Execute(distance))
|
|
return expanded
|
|
|
|
def get_mini_boxes(self, contour):
|
|
bounding_box = cv2.minAreaRect(contour)
|
|
points = sorted(list(cv2.boxPoints(bounding_box)), key=lambda x: x[0])
|
|
|
|
index_1, index_2, index_3, index_4 = 0, 1, 2, 3
|
|
if points[1][1] > points[0][1]:
|
|
index_1 = 0
|
|
index_4 = 1
|
|
else:
|
|
index_1 = 1
|
|
index_4 = 0
|
|
if points[3][1] > points[2][1]:
|
|
index_2 = 2
|
|
index_3 = 3
|
|
else:
|
|
index_2 = 3
|
|
index_3 = 2
|
|
|
|
box = [
|
|
points[index_1], points[index_2], points[index_3], points[index_4]
|
|
]
|
|
return box, min(bounding_box[1])
|
|
|
|
def box_score_fast(self, bitmap, _box):
|
|
h, w = bitmap.shape[:2]
|
|
box = _box.copy()
|
|
xmin = np.clip(np.floor(box[:, 0].min()).astype(np.int), 0, w - 1)
|
|
xmax = np.clip(np.ceil(box[:, 0].max()).astype(np.int), 0, w - 1)
|
|
ymin = np.clip(np.floor(box[:, 1].min()).astype(np.int), 0, h - 1)
|
|
ymax = np.clip(np.ceil(box[:, 1].max()).astype(np.int), 0, h - 1)
|
|
|
|
mask = np.zeros((ymax - ymin + 1, xmax - xmin + 1), dtype=np.uint8)
|
|
box[:, 0] = box[:, 0] - xmin
|
|
box[:, 1] = box[:, 1] - ymin
|
|
cv2.fillPoly(mask, box.reshape(1, -1, 2).astype(np.int32), 1)
|
|
return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0]
|
|
|
|
def __call__(self, pred, shape_list):
|
|
pred = pred.numpy()[:, 0, :, :]
|
|
segmentation = pred > self.thresh
|
|
|
|
boxes_batch = []
|
|
for batch_index in range(pred.shape[0]):
|
|
height, width = shape_list[batch_index]
|
|
boxes, scores = self.boxes_from_bitmap(
|
|
pred[batch_index], segmentation[batch_index], width, height)
|
|
|
|
boxes_batch.append({'points': boxes})
|
|
return boxes_batch
|