PaddleOCR 文字检测部分源码学习(9)-后处理(1)

2021SC@SDUSC
代码位置: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.

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",
                 **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
        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 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)
            if self.score_mode == "fast":
                score = self.box_score_fast(pred, points.reshape(-1, 2))
            else:
                score = self.box_score_slow(pred, contour)
            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):
        '''
        box_score_fast: use bbox mean score as the mean score
        '''
        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 box_score_slow(self, bitmap, contour):
        '''
        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(np.int32), 1)
        return cv2.mean(bitmap[ymin:ymax + 1, xmin:xmax + 1], mask)[0]

    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

        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]
            boxes, scores = self.boxes_from_bitmap(pred[batch_index], mask,
                                                   src_w, src_h)

            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",
                 **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)

    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

PaddleOCR 文字检测部分源码学习(9)-后处理(1)_第1张图片
1)传统分割方法的后处理
图一蓝色箭头所示:首先,设定一个固定的阈值,将分割网络生成的概率图转换为二值图像;然后,采用像素聚类等启发式技术将像素分组为文本实例。(原论文翻译)

缺点:由于是在pixel层面操作,比较复杂且时间消耗较大。

2)DBNet后处理
DBNet的pipeline(如图1中红色箭头所示)目的是将二值化操作插入到分割网络中进行联合优化,这样网络可以自适应的预测图像中每一个像素点的阈值(区别去传统方法的固定阈值),从而可完全区分前景和背景的像素。

二值化阈值由网络学习得到,彻底将二值化这一步骤加入到网络里一起训练,这样最终的输出图对于阈值就会具有非常强的鲁棒性,在简化了后处理的同时提高了文本检测的效果。

关于阈值学习

1         binary = self.binarize(fuse)   #由F得到P
2         if self.training:
3             result = OrderedDict(binary=binary)  
4         else:
5             return binary    
6         if self.adaptive and self.training:
7             if self.serial:
9                 fuse = torch.cat(
10                        (fuse, nn.functional.interpolate(
11                            binary, fuse.shape[2:])), 1)
12            thresh = self.thresh(fuse)   #由F得到T

代码第4行,如果在推理阶段,直接用P得到文本框。

代码第6行,如果在训练阶段且自适应阈值,则计算threshold map。具体实现在self.thresh函数,该函数与self.binarize函数实现一样,训练得到的参数不一样。

至此,我们就得到了probability map和threshold map,通过P和T,我们就可以计算出approximate binary map。

你可能感兴趣的:(python,开发语言,后端)