DocumentAIKit/ppocr/postprocess/db_postprocess.py

# 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.
"""
This code is refered from:
https://github.com/WenmuZhou/DBNet.pytorch/blob/master/post_processing/seg_detector_representer.py
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import numpy as np
import cv2
import paddle
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,
                 use_dilation=False,
                 score_mode="fast",
                 box_type='quad',
                 **kwargs):
        self.thresh = thresh
        self.box_thresh = box_thresh
        self.max_candidates = max_candidates
        self.unclip_ratio = unclip_ratio
        self.min_size = 3
        self.score_mode = score_mode
        self.box_type = box_type
        assert score_mode in [
            "slow", "fast"
        ], "Score mode must be in [slow, fast] but got: {}".format(score_mode)

        self.dilation_kernel = None if not use_dilation else np.array(
            [[1, 1], [1, 1]])

    def polygons_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

        boxes = []
        scores = []

        contours, _ = cv2.findContours((bitmap * 255).astype(np.uint8),
                                       cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)

        for contour in contours[:self.max_candidates]:
            epsilon = 0.002 * cv2.arcLength(contour, True)
            approx = cv2.approxPolyDP(contour, epsilon, True)
            points = approx.reshape((-1, 2))
            if points.shape[0] < 4:
                continue

            score = self.box_score_fast(pred, points.reshape(-1, 2))
            
            if self.box_thresh > score:
                continue

            if points.shape[0] > 2:
                box = self.unclip(points, self.unclip_ratio)
                if len(box) > 1:
                    continue
            else:
                continue
            box = box.reshape(-1, 2)

            _, sside = self.get_mini_boxes(box.reshape((-1, 1, 2)))
            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.tolist())
            scores.append(score)
        return boxes, scores

    def boxes_from_bitmap(self, pred, _bitmap,classes, 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 = []
        class_indexes = []
        class_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)
            if self.score_mode == "fast":
                score, class_index, class_score = self.box_score_fast(pred, points.reshape(-1, 2), classes)
            else:
                score, class_index, class_score = self.box_score_slow(pred, contour, classes)


            print("origin score:" + str(score))
            if self.box_thresh > score:
                continue

            box = self.unclip(points, self.unclip_ratio).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("int32"))
            scores.append(score)

            class_indexes.append(class_index)
            class_scores.append(class_score)

        if classes is None:
            return np.array(boxes, dtype="int32"), scores
        else:
            return np.array(boxes, dtype="int32"), scores, class_indexes, class_scores


    def unclip(self, box, 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,classes):
        '''
        box_score_fast: use bbox mean score as the mean score
        '''
        # print(classes)
        h, w = bitmap.shape[:2]
        box = _box.copy()

        xmin = np.clip(np.floor(box[:, 0].min()).astype("int32"), 0, w - 1)
        xmax = np.clip(np.ceil(box[:, 0].max()).astype("int32"), 0, w - 1)
        ymin = np.clip(np.floor(box[:, 1].min()).astype("int32"), 0, h - 1)
        ymax = np.clip(np.ceil(box[:, 1].max()).astype("int32"), 0, h - 1)

        # box__ = box.reshape(1, -1, 2)
        



        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("int32"), 1)
        if classes is None:
            return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0], None, None
        else:
            k = 255
            class_mask = np.full((ymax - ymin + 1, xmax - xmin + 1), k, dtype=np.int32)
            
            cv2.fillPoly(class_mask, box.reshape(1, -1, 2).astype(np.int32), 0)
            classes = classes[ymin:ymax + 1, xmin:xmax + 1]

            new_classes = classes + class_mask

            # 拉平
            a = new_classes.reshape(-1)
            b = np.where(a >= k)
            # print(len(b[0].tolist()))
            classes = np.delete(a, b[0].tolist())

            class_index = np.argmax(np.bincount(classes))
            print(class_index)
            class_score = np.sum(classes == class_index) / len(classes)
            print(class_score)
            return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0], class_index, class_score

    def box_score_slow(self, bitmap, contour,classes):

        '''
        box_score_slow: use polyon mean score as the mean score
        '''
        h, w = bitmap.shape[:2]
        contour = contour.copy()
        contour = np.reshape(contour, (-1, 2))

        xmin = np.clip(np.min(contour[:, 0]), 0, w - 1)
        xmax = np.clip(np.max(contour[:, 0]), 0, w - 1)
        ymin = np.clip(np.min(contour[:, 1]), 0, h - 1)
        ymax = np.clip(np.max(contour[:, 1]), 0, h - 1)

        mask = np.zeros((ymax - ymin + 1, xmax - xmin + 1), dtype=np.uint8)

        contour[:, 0] = contour[:, 0] - xmin
        contour[:, 1] = contour[:, 1] - ymin

        cv2.fillPoly(mask, contour.reshape(1, -1, 2).astype("int32"), 1)
        if classes is None:
            return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0], None, None
        else:
            k = 999
            class_mask = np.full((ymax - ymin + 1, xmax - xmin + 1), k, dtype=np.int32)

            cv2.fillPoly(class_mask, contour.reshape(1, -1, 2).astype("int32"), 0)
            classes = classes[ymin:ymax + 1, xmin:xmax + 1]

            new_classes = classes + class_mask

            # 拉平
            a = new_classes.reshape(-1)
            b = np.where(a >= k)
            classes = np.delete(a, b[0].tolist())

            class_index = np.argmax(np.bincount(classes))
            class_score = np.sum(classes == class_index) / len(classes)

            return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0], class_index, class_score


    def __call__(self, outs_dict, shape_list):
        pred = outs_dict['maps']
        if isinstance(pred, paddle.Tensor):
            pred = pred.numpy()
        pred = pred[:, 0, :, :]
        segmentation = pred > self.thresh

        print(pred.shape)

        if "classes" in outs_dict:
            classes = outs_dict['classes']
            # print(classes)
            # print("jerome1")
            # print(classes.shape)
            # print(classes)

            # np.set_printoptions(threshold=np.inf)

            if isinstance(classes, paddle.Tensor):
                # classes = paddle.argmax(classes, axis=1, dtype='int32')
                classes = classes.numpy()
            # else:
                # classes = np.argmax(classes, axis=1).astype(np.int32)

            classes = classes[:, 0, :, :]
            print(classes.shape)

        else:
            classes = None

        boxes_batch = []
        for batch_index in range(pred.shape[0]):
            src_h, src_w, ratio_h, ratio_w = shape_list[batch_index]
            if self.dilation_kernel is not None:
                mask = cv2.dilate(
                    np.array(segmentation[batch_index]).astype(np.uint8),
                    self.dilation_kernel)
            else:
                mask = segmentation[batch_index]
            if self.box_type == 'poly':
                boxes, scores = self.polygons_from_bitmap(pred[batch_index],
                                                          mask, src_w, src_h)
            elif self.box_type == 'quad':
                if classes is None:
                    boxes, scores = self.boxes_from_bitmap(pred[batch_index], mask, None,
                                                       src_w, src_h)
              
                else:
                    boxes, scores, class_indexes, class_scores = self.boxes_from_bitmap(pred[batch_index], mask,
                                                                                      classes[batch_index],
                                                                                      src_w, src_h)
                    boxes_batch.append({'points': boxes, "classes": class_indexes, "class_scores": class_scores})
            else:
                raise ValueError("box_type can only be one of ['quad', 'poly']")

            boxes_batch.append({'points': boxes})
        return boxes_batch


class DistillationDBPostProcess(object):
    def __init__(self,
                 model_name=["student"],
                 key=None,
                 thresh=0.3,
                 box_thresh=0.6,
                 max_candidates=1000,
                 unclip_ratio=1.5,
                 use_dilation=False,
                 score_mode="fast",
                 box_type='quad',
                 **kwargs):
        self.model_name = model_name
        self.key = key
        self.post_process = DBPostProcess(
            thresh=thresh,
            box_thresh=box_thresh,
            max_candidates=max_candidates,
            unclip_ratio=unclip_ratio,
            use_dilation=use_dilation,
            score_mode=score_mode,
            box_type=box_type)

    def __call__(self, predicts, shape_list):
        results = {}
        for k in self.model_name:
            results[k] = self.post_process(predicts[k], shape_list=shape_list)
        return results