def crop(save_gt_path, json_path, save_path):
if os.path.exists(save_path):
shutil.rmtree(save_path, ignore_errors=True)
os.makedirs(save_path, exist_ok=True)
data = load_gt(json_path)
file_list = []
for img_path, gt in tqdm(data.items()):
img = Image.open(img_path).convert('RGB')
img_name = pathlib.Path(img_path).stem
for i, (polygon, text, illegibility, language) in enumerate(
zip(gt['polygons'], gt['texts'], gt['illegibility_list'],
gt['language_list'])):
if illegibility:
continue
polygon = np.array(polygon)
roi_img_save_path = os.path.join(save_path,
'{}_{}.jpg'.format(img_name, i))
# 对于只有四个点的图片，反射变换后存储
if len(polygon) == 4:
np_img = np.asarray(img)
roi_img = four_point_transform(np_img, polygon)
roi_img = Image.fromarray(roi_img).convert('RGB')
else:
x_min = polygon[:, 0].min()
x_max = polygon[:, 0].max()
y_min = polygon[:, 1].min()
y_max = polygon[:, 1].max()
roi_img = img.crop((x_min, y_min, x_max, y_max))
roi_img.save(roi_img_save_path)
file_list.append(roi_img_save_path + '\t' + text + '\t' + language)
# plt.title(text)
# plt.imshow(roi_img)
# plt.show()
save(file_list, save_gt_path)
def cvt_det(gt_path, save_path, img_folder):
"""
将icdar2015格式的gt转换为json格式
:param gt_path:
:param save_path:
:return:
"""
gt_dict = {'data_root': img_folder}
data_list = []
origin_gt = load(gt_path)
for img_name, gt in tqdm(origin_gt.items()):
cur_gt = {'img_name': img_name + '.jpg', 'annotations': []}
for line in gt:
cur_line_gt = {'polygon': [], 'text': '', 'illegibility': False, 'language': 'Latin'}
chars_gt = [{'polygon': [], 'char': '', 'illegibility': False, 'language': 'Latin'}]
cur_line_gt['chars'] = chars_gt
# 字符串级别的信息
cur_line_gt['polygon'] = line['points']
cur_line_gt['text'] = line['transcription']
cur_line_gt['illegibility'] = line['illegibility']
cur_line_gt['language'] = line['language']
cur_gt['annotations'].append(cur_line_gt)
data_list.append(cur_gt)
gt_dict['data_list'] = data_list
save(gt_dict, save_path)
def cvt(gt_path, save_path, img_folder):
"""
将icdar2015格式的gt转换为json格式
:param gt_path:
:param save_path:
:return:
"""
gt_dict = {'data_root': img_folder}
data_list = []
for file_path in tqdm(get_file_list(gt_path, p_postfix=['.txt'])):
content = load(file_path)
file_path = pathlib.Path(file_path)
img_name = file_path.name.replace('.txt', '.jpg')
cur_gt = {'img_name': img_name, 'annotations': []}
for line in content:
cur_line_gt = {'polygon': [], 'text': '', 'illegibility': False, 'language': 'Latin'}
chars_gt = [{'polygon': [], 'char': '', 'illegibility': False, 'language': 'Latin'}]
cur_line_gt['chars'] = chars_gt
line = line.split(',')
# 字符串级别的信息
x1, y1, x2, y2, x3, y3, x4, y4 = list(map(float, line[:8]))
cur_line_gt['polygon'] = [[x1, y1], [x2, y2], [x3, y3], [x4, y4]]
cur_line_gt['text'] = line[-1]
cur_line_gt['illegibility'] = True if cur_line_gt['text'] == '*' or cur_line_gt['text'] == '###' else False
cur_gt['annotations'].append(cur_line_gt)
data_list.append(cur_gt)
gt_dict['data_list'] = data_list
save(gt_dict, save_path)
def cvt(gt_path, save_path, imgs_folder):
gt_dict = {'data_root': imgs_folder}
data_list = []
ct = load(gt_path)
for img_id, anns in tqdm(ct.items()):
img_name = img_id.replace('gt', 'img') + '.jpg'
cur_gt = {'img_name': img_name, 'annotations': []}
for ann in anns:
cur_line_gt = {
'polygon': [],
'text': '',
'illegibility': False,
'language': 'Latin'
}
chars_gt = [{
'polygon': [],
'char': '',
'illegibility': False,
'language': 'Latin'
}]
cur_line_gt['chars'] = chars_gt
cur_line_gt['polygon'] = ann['points']
cur_line_gt['illegibility'] = ann['illegibility']
cur_gt['annotations'].append(cur_line_gt)
if len(cur_gt['annotations']) > 0:
data_list.append(cur_gt)
gt_dict['data_list'] = data_list
save(gt_dict, save_path)
print(len(gt_dict), len(data_list))
def cvt_rec(gt_path, save_path, img_folder):
origin_gt = load(gt_path)
file_list = []
for img_name, gt in tqdm(origin_gt.items()):
assert len(gt) == 1
gt = gt[0]
img_path = os.path.join(img_folder, img_name + '.jpg')
file_list.append(img_path + '\t' + gt['transcription'] + '\t' + gt['language'])
save(file_list, save_path)
def cvt(gt_path, save_path, img_folder):
content = load(gt_path)
file_list = []
for line in tqdm(content):
line = line.split('\t')
img_path = os.path.join(img_folder, line[-2])
if not os.path.exists(img_path):
print(img_path)
file_list.append(img_path + '\t' + line[-1] + '\t' + 'Chinese')
# img = Image.open(img_path)
# plt.title(line[-1])
# plt.imshow(img)
# plt.show()
save(file_list, save_path)
def cvt(gt_path, save_path, img_folder):
content = load(gt_path)
file_list = []
for i, line in tqdm(enumerate(content)):
try:
line = line.split('.jpg ')
img_path = os.path.join(img_folder, line[-2])
file_list.append(img_path + '.jpg' + '\t' + line[-1] + '\t' +
'Chinese')
# img = Image.open(img_path)
# plt.title(line[-1])
# plt.imshow(img)
# plt.show()
except:
a = 1
save(file_list, save_path)
def cvt(gt_path, save_path, img_folder):
content = load(gt_path)
file_list = []
for line in tqdm(content):
img_relative_path = line.split(' ')[0]
img_path = os.path.join(img_folder, img_relative_path)
img_path = pathlib.Path(img_path)
label = img_path.stem.split('_')[1]
if not img_path.exists():
print(img_path)
file_list.append(str(img_path) + '\t' + label + '\t' + 'English')
# img = Image.open(img_path)
# plt.title(label)
# plt.imshow(img)
# plt.show()
save(file_list, save_path)
def cvt(gt_path, save_path, imgs_folder):
gt_dict = {'data_root': imgs_folder}
data_list = []
ct = COCO_Text(gt_path)
train_img_ids = ct.getImgIds(imgIds=ct.val)
for img_id in tqdm(train_img_ids):
img = ct.loadImgs(img_id)[0]
# img_path = os.path.join(imgs_folder, img['file_name'])
# if not os.path.exists(img_path):
# continue
cur_gt = {'img_name': img['file_name'], 'annotations': []}
annIds = ct.getAnnIds(imgIds=img['id'])
anns = ct.loadAnns(annIds)
for ann in anns:
if len(ann['utf8_string']) == 0:
continue
cur_line_gt = {
'polygon': [],
'text': '',
'illegibility': False,
'language': 'Latin'
}
chars_gt = [{
'polygon': [],
'char': '',
'illegibility': False,
'language': 'Latin'
}]
cur_line_gt['chars'] = chars_gt
cur_line_gt['language'] = ann['language']
chars_gt[0]['language'] = ann['language']
cur_line_gt['polygon'] = np.array(ann['mask']).reshape(-1,
2).tolist()
cur_line_gt['text'] = ann['utf8_string']
cur_line_gt['illegibility'] = True if ann[
'legibility'] == "illegible" else False
cur_gt['annotations'].append(cur_line_gt)
if len(cur_gt['annotations']) > 0:
data_list.append(cur_gt)
gt_dict['data_list'] = data_list
save(gt_dict, save_path)
print(len(gt_dict), len(data_list))
def cvt(self):
gt_dict = {'data_root': self.img_folder}
data_list = []
pbar = tqdm(total=len(self.imageNames))
for imageName, wordBBoxes, texts in zip(self.imageNames,
self.wordBBoxes,
self.transcripts):
wordBBoxes = np.expand_dims(
wordBBoxes, axis=2) if (wordBBoxes.ndim == 2) else wordBBoxes
_, _, numOfWords = wordBBoxes.shape
text_polys = wordBBoxes.reshape([8, numOfWords],
order='F').T # num_words * 8
text_polys = text_polys.reshape(numOfWords, 4,
2) # num_of_words * 4 * 2
transcripts = [word for line in texts for word in line.split()]
if numOfWords != len(transcripts):
continue
cur_gt = {'img_name': imageName, 'annotations': []}
for polygon, text in zip(text_polys, transcripts):
cur_line_gt = {
'polygon': [],
'text': '',
'illegibility': False,
'language': 'Latin'
}
chars_gt = [{
'polygon': [],
'char': '',
'illegibility': False,
'language': 'Latin'
}]
cur_line_gt['chars'] = chars_gt
cur_line_gt['text'] = text
cur_line_gt['polygon'] = polygon.tolist()
cur_line_gt['illegibility'] = text in ['###', '*']
cur_gt['annotations'].append(cur_line_gt)
data_list.append(cur_gt)
pbar.update(1)
pbar.close()
gt_dict['data_list'] = data_list
save(gt_dict, save_path)
def cvt(gt_path, save_path, img_folder):
"""
将icdar2015格式的gt转换为json格式
:param gt_path:
:param save_path:
:return:
"""
gt_dict = {'data_root': img_folder}
data_list = []
for file_path in tqdm(get_file_list(gt_path, p_postfix=['.json'])):
content = load(file_path)
file_path = pathlib.Path(file_path)
img_name = file_path.stem + '.jpg'
cur_gt = {'img_name': img_name, 'annotations': []}
char_polygon_list, char_illegibility_list, char_text_list = decode_chars(
content['chars'])
for line in content['lines']:
cur_line_gt = {
'polygon': [],
'text': '',
'illegibility': False,
'language': 'Latin'
}
chars_gt = [{
'polygon': [],
'char': '',
'illegibility': False,
'language': 'Latin'
}]
cur_line_gt['chars'] = chars_gt
# 字符串级别的信息
cur_line_gt['polygon'] = np.array(line['points']).reshape(
-1, 2).tolist()
cur_line_gt['text'] = line['transcription']
cur_line_gt[
'illegibility'] = True if line['ignore'] == 1 else False
str_len = len(line['transcription'])
# 字符信息
flag = False
for char_idx in range(len(char_polygon_list)):
for str_idx in range(1, str_len + 1):
if ''.join(
char_text_list[char_idx:char_idx +
str_idx]) == line['transcription']:
chars_gt = []
for j in range(char_idx, char_idx + str_idx):
chars_gt.append({
'polygon':
char_polygon_list[j],
'char':
char_text_list[j],
'illegibility':
char_illegibility_list[j],
'language':
'Latin'
})
cur_line_gt['chars'] = chars_gt
char_polygon_list = char_polygon_list[char_idx +
str_len:]
char_text_list = char_text_list[char_idx + str_len:]
char_illegibility_list = char_illegibility_list[
char_idx + str_len:]
flag = True
break
if flag:
break
cur_gt['annotations'].append(cur_line_gt)
data_list.append(cur_gt)
gt_dict['data_list'] = data_list
save(gt_dict, save_path)