icdar2015文本检测样本展示

python脚本如下，可以用于确认标注没是否存在问题。

import os
import glob
from natsort import natsorted
import cv2
import numpy as np


def get_file_list(folder_path: str, p_postfix: list = None, sub_dir: bool = True) -> list:
    """
    获取所给文件目录里的指定后缀的文件,读取文件列表目前使用的是 os.walk 和 os.listdir ，这两个目前比 pathlib 快很多
    :param filder_path: 文件夹名称
    :param p_postfix: 文件后缀,如果为 [.*]将返回全部文件
    :param sub_dir: 是否搜索子文件夹
    :return: 获取到的指定类型的文件列表
    """
    assert os.path.exists(folder_path) and os.path.isdir(folder_path)
    if p_postfix is None:
        p_postfix = ['.jpg']
    if isinstance(p_postfix, str):
        p_postfix = [p_postfix]
    file_list = [x for x in glob.glob(folder_path + '/**/*.*', recursive=True) if
                 os.path.splitext(x)[-1] in p_postfix or '.*' in p_postfix]
    return natsorted(file_list)


def get_boxes(file_path: str):
    anno_file = ""
    if file_path.endswith(".jpg"):
        anno_file = file_path.replace("img", "gt").replace(".jpg", ".txt")
        if os.path.isfile(anno_file):
            # print(anno_file, "文件存在")
            stature = 1
        else:
            # print(anno_file, "文件不存在")
            stature = 0
        f = open(anno_file, encoding='utf-8')
        x1, y1, x2, y2, x3, y3, x4, y4 = 0, 0, 0, 0, 0, 0, 0, 0
        chars = ""
        box_list = []

        for line in f.readlines():
            # print(line)
            data = line.replace('\n', '')
            substr = data.split(',')
            locate = substr[:8]
            [x1, y1, x2, y2, x3, y3, x4, y4] = [int(x) for x in locate]
            chars = substr[8:]
            org_loc = [x1, y1, x2, y2, x3, y3, x4, y4]
            box_list.append(org_loc)
        box_list = np.array(box_list)
        return box_list

def draw_bbox(img_path, result, color=(255, 0, 0), thickness=2):
    if isinstance(img_path, str):
        img_path = cv2.imread(img_path)
        # img_path = cv2.cvtColor(img_path, cv2.COLOR_BGR2RGB)
    img_path = img_path.copy()
    for point in result:
        point = point.astype(int)
        cv2.polylines(img_path, [point], True, color, thickness)
    return img_path

def show_img(imgs: np.ndarray, title='img'):
    color = (len(imgs.shape) == 3 and imgs.shape[-1] == 3)
    imgs = np.expand_dims(imgs, axis=0)
    for i, img in enumerate(imgs):
        plt.figure()
        plt.title('{}_{}'.format(title, i))
        plt.imshow(img, cmap=None if color else 'gray')
    plt.show()

def init_args():
    import argparse
    parser = argparse.ArgumentParser(description='')
    parser.add_argument('--input_folder', default=r'F:\dataset\img', type=str, help='img path for predict')
    parser.add_argument('--output_folder', default='./test/output', type=str, help='img path for output')
    parser.add_argument('--show', action='store_true', help='show result')
    parser.add_argument('--save_resut', action='store_true', help='save box and score to txt file')
    args = parser.parse_args()
    return args


if __name__ == '__main__':
    import pathlib
    from tqdm import tqdm
    import matplotlib.pyplot as plt

    args = init_args()
    img_folder = pathlib.Path(args.input_folder)
    for img_path in tqdm(get_file_list(args.input_folder, p_postfix=['.jpg'])):
        boxes_list = get_boxes(img_path)
        boxes_list.resize(len(boxes_list), 4, 2)
        img = draw_bbox(cv2.imread(img_path)[:, :, ::-1], boxes_list)
        if args.show:
            show_img(img, title=os.path.basename(img_path))
            plt.show()

            # 保存结果到路径
        os.makedirs(args.output_folder, exist_ok=True)
        img_path = pathlib.Path(img_path)
        output_path = os.path.join(args.output_folder, img_path.stem + '_result.jpg')
        cv2.imwrite(output_path, img[:, :, ::-1])