OpenOCR/opendet/preprocess/db_resize_for_test.py

import math
import sys
import cv2
import numpy as np


class DetResizeForTest(object):

    def __init__(self, **kwargs):
        super(DetResizeForTest, self).__init__()
        self.resize_type = 0
        self.keep_ratio = False
        if 'image_shape' in kwargs:
            self.image_shape = kwargs['image_shape']
            self.resize_type = 1
            if 'keep_ratio' in kwargs:
                self.keep_ratio = kwargs['keep_ratio']
        elif 'limit_side_len' in kwargs:
            self.limit_side_len = kwargs['limit_side_len']
            self.limit_type = kwargs.get('limit_type', 'min')
        elif 'resize_long' in kwargs:
            self.resize_type = 2
            self.resize_long = kwargs.get('resize_long', 960)
        else:
            self.limit_side_len = 736
            self.limit_type = 'min'

    def __call__(self, data):
        img = data['image']
        if 'max_sile_len' in data:
            self.limit_side_len = data['max_sile_len']
        src_h, src_w, _ = img.shape
        if sum([src_h, src_w]) < 64:
            img = self.image_padding(img)

        if self.resize_type == 0:
            # img, shape = self.resize_image_type0(img)
            img, [ratio_h, ratio_w] = self.resize_image_type0(img)
        elif self.resize_type == 2:
            img, [ratio_h, ratio_w] = self.resize_image_type2(img)
        else:
            # img, shape = self.resize_image_type1(img)
            img, [ratio_h, ratio_w] = self.resize_image_type1(img)
        data['image'] = img
        data['shape'] = np.array([src_h, src_w, ratio_h, ratio_w])
        return data

    def image_padding(self, im, value=0):
        h, w, c = im.shape
        im_pad = np.zeros((max(32, h), max(32, w), c), np.uint8) + value
        im_pad[:h, :w, :] = im
        return im_pad

    def resize_image_type1(self, img):
        resize_h, resize_w = self.image_shape
        ori_h, ori_w = img.shape[:2]  # (h, w, c)
        if self.keep_ratio is True:
            resize_w = ori_w * resize_h / ori_h
            N = math.ceil(resize_w / 32)
            resize_w = N * 32
        ratio_h = float(resize_h) / ori_h
        ratio_w = float(resize_w) / ori_w
        img = cv2.resize(img, (int(resize_w), int(resize_h)))
        # return img, np.array([ori_h, ori_w])
        return img, [ratio_h, ratio_w]

    def resize_image_type0(self, img):
        """
        resize image to a size multiple of 32 which is required by the network
        args:
            img(array): array with shape [h, w, c]
        return(tuple):
            img, (ratio_h, ratio_w)
        """
        limit_side_len = self.limit_side_len
        h, w, c = img.shape

        # limit the max side
        if self.limit_type == 'max':
            if max(h, w) > limit_side_len:
                if h > w:
                    ratio = float(limit_side_len) / h
                else:
                    ratio = float(limit_side_len) / w
            else:
                ratio = 1.0
        elif self.limit_type == 'min':
            if min(h, w) < limit_side_len:
                if h < w:
                    ratio = float(limit_side_len) / h
                else:
                    ratio = float(limit_side_len) / w
            else:
                ratio = 1.0
        elif self.limit_type == 'resize_long':
            ratio = float(limit_side_len) / max(h, w)
        else:
            raise Exception('not support limit type, image ')
        resize_h = int(h * ratio)
        resize_w = int(w * ratio)

        resize_h = max(int(round(resize_h / 32) * 32), 32)
        resize_w = max(int(round(resize_w / 32) * 32), 32)

        try:
            if int(resize_w) <= 0 or int(resize_h) <= 0:
                return None, (None, None)
            img = cv2.resize(img, (int(resize_w), int(resize_h)))
        except:
            print(img.shape, resize_w, resize_h)
            sys.exit(0)
        ratio_h = resize_h / float(h)
        ratio_w = resize_w / float(w)
        return img, [ratio_h, ratio_w]

    def resize_image_type2(self, img):
        h, w, _ = img.shape

        resize_w = w
        resize_h = h

        if resize_h > resize_w:
            ratio = float(self.resize_long) / resize_h
        else:
            ratio = float(self.resize_long) / resize_w

        resize_h = int(resize_h * ratio)
        resize_w = int(resize_w * ratio)

        max_stride = 128
        resize_h = (resize_h + max_stride - 1) // max_stride * max_stride
        resize_w = (resize_w + max_stride - 1) // max_stride * max_stride
        img = cv2.resize(img, (int(resize_w), int(resize_h)))
        ratio_h = resize_h / float(h)
        ratio_w = resize_w / float(w)

        return img, [ratio_h, ratio_w]