File size: 4,605 Bytes
8207382
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
# copyright (c) 2021 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.
import cv2
import os
import numpy as np
import PIL
from PIL import Image, ImageDraw, ImageFont


def draw_ser_results(
    image, ocr_results, font_path="doc/fonts/simfang.ttf", font_size=14
):
    np.random.seed(2021)
    color = (
        np.random.permutation(range(255)),
        np.random.permutation(range(255)),
        np.random.permutation(range(255)),
    )
    color_map = {
        idx: (color[0][idx], color[1][idx], color[2][idx]) for idx in range(1, 255)
    }
    if isinstance(image, np.ndarray):
        image = Image.fromarray(image)
    elif isinstance(image, str) and os.path.isfile(image):
        image = Image.open(image).convert("RGB")
    img_new = image.copy()
    draw = ImageDraw.Draw(img_new)

    font = ImageFont.truetype(font_path, font_size, encoding="utf-8")
    for ocr_info in ocr_results:
        if ocr_info["pred_id"] not in color_map:
            continue
        color = color_map[ocr_info["pred_id"]]
        text = "{}: {}".format(ocr_info["pred"], ocr_info["transcription"])

        if "bbox" in ocr_info:
            # draw with ocr engine
            bbox = ocr_info["bbox"]
        else:
            # draw with ocr groundtruth
            bbox = trans_poly_to_bbox(ocr_info["points"])
        draw_box_txt(bbox, text, draw, font, font_size, color)

    img_new = Image.blend(image, img_new, 0.7)
    return np.array(img_new)


def draw_box_txt(bbox, text, draw, font, font_size, color):
    # draw ocr results outline
    bbox = ((bbox[0], bbox[1]), (bbox[2], bbox[3]))
    draw.rectangle(bbox, fill=color)

    # draw ocr results
    if int(PIL.__version__.split(".")[0]) < 10:
        tw = font.getsize(text)[0]
        th = font.getsize(text)[1]
    else:
        left, top, right, bottom = font.getbbox(text)
        tw, th = right - left, bottom - top

    start_y = max(0, bbox[0][1] - th)
    draw.rectangle(
        [(bbox[0][0] + 1, start_y), (bbox[0][0] + tw + 1, start_y + th)],
        fill=(0, 0, 255),
    )
    draw.text((bbox[0][0] + 1, start_y), text, fill=(255, 255, 255), font=font)


def trans_poly_to_bbox(poly):
    x1 = np.min([p[0] for p in poly])
    x2 = np.max([p[0] for p in poly])
    y1 = np.min([p[1] for p in poly])
    y2 = np.max([p[1] for p in poly])
    return [x1, y1, x2, y2]


def draw_re_results(image, result, font_path="doc/fonts/simfang.ttf", font_size=18):
    np.random.seed(0)
    if isinstance(image, np.ndarray):
        image = Image.fromarray(image)
    elif isinstance(image, str) and os.path.isfile(image):
        image = Image.open(image).convert("RGB")
    img_new = image.copy()
    draw = ImageDraw.Draw(img_new)

    font = ImageFont.truetype(font_path, font_size, encoding="utf-8")
    color_head = (0, 0, 255)
    color_tail = (255, 0, 0)
    color_line = (0, 255, 0)

    for ocr_info_head, ocr_info_tail in result:
        draw_box_txt(
            ocr_info_head["bbox"],
            ocr_info_head["transcription"],
            draw,
            font,
            font_size,
            color_head,
        )
        draw_box_txt(
            ocr_info_tail["bbox"],
            ocr_info_tail["transcription"],
            draw,
            font,
            font_size,
            color_tail,
        )

        center_head = (
            (ocr_info_head["bbox"][0] + ocr_info_head["bbox"][2]) // 2,
            (ocr_info_head["bbox"][1] + ocr_info_head["bbox"][3]) // 2,
        )
        center_tail = (
            (ocr_info_tail["bbox"][0] + ocr_info_tail["bbox"][2]) // 2,
            (ocr_info_tail["bbox"][1] + ocr_info_tail["bbox"][3]) // 2,
        )

        draw.line([center_head, center_tail], fill=color_line, width=5)

    img_new = Image.blend(image, img_new, 0.5)
    return np.array(img_new)


def draw_rectangle(img_path, boxes):
    boxes = np.array(boxes)
    img = cv2.imread(img_path)
    img_show = img.copy()
    for box in boxes.astype(int):
        x1, y1, x2, y2 = box
        cv2.rectangle(img_show, (x1, y1), (x2, y2), (255, 0, 0), 2)
    return img_show