source/PaddleOCR/ppocr/data/imaug/make_shrink_map.py

# copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
#
# 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.
"""
This code is refer from:
https://github.com/WenmuZhou/DBNet.pytorch/blob/master/data_loader/modules/make_shrink_map.py
"""

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals

import numpy as np
import cv2
from shapely.geometry import Polygon
import pyclipper

__all__ = ["MakeShrinkMap"]


class MakeShrinkMap(object):
    r"""
    Making binary mask from detection data with ICDAR format.
    Typically following the process of class `MakeICDARData`.
    """

    def __init__(self, min_text_size=8, shrink_ratio=0.4, **kwargs):
        self.min_text_size = min_text_size
        self.shrink_ratio = shrink_ratio
        if "total_epoch" in kwargs:
            self._base_shrink_ratio = shrink_ratio
            self._total_epoch = kwargs["total_epoch"]

    def __call__(self, data):
        image = data["image"]
        text_polys = data["polys"]
        ignore_tags = data["ignore_tags"]

        h, w = image.shape[:2]
        text_polys, ignore_tags = self.validate_polygons(text_polys, ignore_tags, h, w)
        gt = np.zeros((h, w), dtype=np.float32)
        mask = np.ones((h, w), dtype=np.float32)
        for i in range(len(text_polys)):
            polygon = text_polys[i]
            height = max(polygon[:, 1]) - min(polygon[:, 1])
            width = max(polygon[:, 0]) - min(polygon[:, 0])
            if ignore_tags[i] or min(height, width) < self.min_text_size:
                cv2.fillPoly(mask, polygon.astype(np.int32)[np.newaxis, :, :], 0)
                ignore_tags[i] = True
            else:
                if np.isnan(polygon).any():
                    ignore_tags[i] = True
                    continue
                polygon_shape = Polygon(polygon)
                subject = [tuple(l) for l in polygon]
                padding = pyclipper.PyclipperOffset()
                padding.AddPath(subject, pyclipper.JT_ROUND, pyclipper.ET_CLOSEDPOLYGON)
                shrunk = []

                # Increase the shrink ratio every time we get multiple polygon returned back
                shrink_ratio = self.shrink_ratio
                if "epoch" in data and hasattr(self, "_base_shrink_ratio"):
                    shrink_ratio = self._base_shrink_ratio + 0.2 * data[
                        "epoch"
                    ] / float(self._total_epoch)
                possible_ratios = np.arange(shrink_ratio, 1, shrink_ratio)
                np.append(possible_ratios, 1)
                # print(possible_ratios)
                for ratio in possible_ratios:
                    # print(f"Change shrink ratio to {ratio}")
                    distance = (
                        polygon_shape.area
                        * (1 - np.power(ratio, 2))
                        / polygon_shape.length
                    )
                    shrunk = padding.Execute(-distance)
                    if len(shrunk) == 1:
                        break

                if shrunk == []:
                    cv2.fillPoly(mask, polygon.astype(np.int32)[np.newaxis, :, :], 0)
                    ignore_tags[i] = True
                    continue

                for each_shrink in shrunk:
                    shrink = np.array(each_shrink).reshape(-1, 2)
                    cv2.fillPoly(gt, [shrink.astype(np.int32)], 1)

        data["shrink_map"] = gt
        data["shrink_mask"] = mask
        return data

    def validate_polygons(self, polygons, ignore_tags, h, w):
        """
        polygons (numpy.array, required): of shape (num_instances, num_points, 2)
        """
        if len(polygons) == 0:
            return polygons, ignore_tags
        assert len(polygons) == len(ignore_tags)
        for polygon in polygons:
            polygon[:, 0] = np.clip(polygon[:, 0], 0, w - 1)
            polygon[:, 1] = np.clip(polygon[:, 1], 0, h - 1)

        for i in range(len(polygons)):
            area = self.polygon_area(polygons[i])
            if abs(area) < 1:
                ignore_tags[i] = True
            if area > 0:
                polygons[i] = polygons[i][::-1, :]
        return polygons, ignore_tags

    def polygon_area(self, polygon):
        """
        compute polygon area
        """
        area = 0
        q = polygon[-1]
        for p in polygon:
            area += p[0] * q[1] - p[1] * q[0]
            q = p
        return area / 2.0