CodeCamp #116 Add SROIE to dataset preparer

dataset_zoo/sroie/metafile.yml

@@ -0,0 +1,31 @@
+Name: 'Scanned Receipts OCR and Information Extraction'
+Paper:
+  Title: ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction
+  URL: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8977955
+  Venue: ICDAR
+  Year: '2019'
+  BibTeX: '@INPROCEEDINGS{8977955,
+  author={Huang, Zheng and Chen, Kai and He, Jianhua and Bai, Xiang and Karatzas, Dimosthenis and Lu, Shijian and Jawahar, C. V.},
+  booktitle={2019 International Conference on Document Analysis and Recognition (ICDAR)}, 
+  title={ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction}, 
+  year={2019},
+  volume={},
+  number={},
+  pages={1516-1520},
+  doi={10.1109/ICDAR.2019.00244}}'
+Data:
+  Website: https://rrc.cvc.uab.es/?ch=13
+  Language:
+    - English
+  Scene:
+    - Document
+  Granularity:
+    - Word
+  Tasks:
+    - textdet
+    - textrecog
+    - textspotting
+  License:
+    Type: CC BY 4.0
+    Link: https://creativecommons.org/licenses/by/4.0/
+  Format: .txt

dataset_zoo/sroie/sample_anno.md

@@ -0,0 +1,9 @@
+**Text Detection, Text Recognition and Text Spotting**
+
+```text
+# x1,y1,x2,y2,x3,y3,x4,y4,trans
+
+72,25,326,25,326,64,72,64,TAN WOON YANN
+50,82,440,82,440,121,50,121,BOOK TA .K(TAMAN DAYA) SDN BND
+205,121,285,121,285,139,205,139,789417-W
+```

dataset_zoo/sroie/textdet.py

@@ -0,0 +1,76 @@
+data_root = 'data/sroie'
+cache_path = 'data/cache'
+
+data_obtainer = dict(
+ type='NaiveDataObtainer',
+ cache_path=cache_path,
+ data_root=data_root,
+ files=[
+        dict(
+            url='https://doc-b4-c8-drive-data-export.googleusercontent.com'
+            '/download/fjpfehrefh7sl37sr71jeh2bhss0bjnc/frvcn2hirmtpmhokmdp'
+            'dfb5f9mn3vmu2/1671610500000/ab5eb9ff-0939-4733-b13e-b91ccd5ca3'
+            'e9/103212024722882466354/ADt3v-PlZRXqj94_z156zbyAJvCgP_INPDXqz'
+            'Uqez3jcQBO0TCy1AXXkuWPgRLCbyQC5x7cisBfEtqGdAHlGKo9yJnvAcv12GsA'
+            'HS2ppinZhj2_kFlcQqmCIUogMe2iKzsSZ3RMSbgTMIfIMSlDcZ-UTI5OfXCLR3'
+            'JhZ31ZCxYBYEmrqaMSrO_L55dUzNw-pgCxeE56qpoLYWQo-oGmpKfX4fLdbJkN'
+            'xcC49uXCHHdHifHjpTCFn0B6-XCVdp9uX0fweojHWNiyD_Z7WRzIOmrBF0MM3t'
+            'mlCN8O4Txu8gskuUPqvc66WzRaIFXcfEdYq_QLe4gD-8fr8L6q4-u26TsDAly2'
+            'f9937mA==?nonce=ou9fflkqd9ie0&user=103212024722882466354&authu'
+            'ser=0&hash=ert0codc6560intrkm24htb1ven4cvau',
+            save_name='0325updated.task1train(626p)-20221205T094142Z-001.zip',
+            md5='3883fa9ef6ade95a8d3b9076813ad848',
+            split=['train'],
+            content=['image', 'annotation'],
+            mapping=[['0325updated/0325updated.task1train(626p)/*.jpg', 'textdet_imgs/train'],
+                     ['0325updated/0325updated.task1train(626p)/*.txt', 'annotations/train']]),
+        dict(
+            url='https://doc-0o-2o-drive-data-export.googleusercontent.com/'
+            'download/fjpfehrefh7sl37sr71jeh2bhss0bjnc/16u970fcc7dd54arckv'
+            'rpjbd6ecdkull/1671538500000/b3194449-f672-4f77-8021-1a9650df6a'
+            'a4/103212024722882466354/ADt3v-MXYOvylQYausMHix7WhseI1d0YLyqt'
+            'B2r8n1QPTJebve8oJFf4_8APh0L7r-HyE0CyjhxRXf8bM909oFE2sWKEulqEnv'
+            'ussVQdvFh73dlC7goMbGSb1-EfUWR4wXpHpsoPYVOjw1grQiExl0v_P3LHaD9Er'
+            'TkZkA3ZhR-q9iKUq_7i7eyXbdhT35l34Xnal7mFap2P2ZdacoBLzD2LDI1GRqXt'
+            'lnMKWm4KnTZuBGBNXFxJGjjnhy3x4j9meSt_eod0vZzyfAgs5ThHM1kk6dc8pT'
+            'KAM84p0z2cp-N0GJgi8pLMZR8nPdxKBJNipOzp4Y_8tUGO?authuser=0&nonc'
+            'e=vkamrsalrga2q&user=103212024722882466354&hash=8trg3mjsqhc8hf'
+            '6uhim8jqirsjdp0r2l',
+            save_name='task1&2_test(361p)-20221205T104647Z-001.zip',
+            md5='1b05af23e4b38ca27d19cfe95272418f',
+            split=['test'],
+            content=['image'],
+            mapping=[['task1&2_test(361p)-20221205T104647Z-001/task1_2_test(361p)', 'textdet_imgs/test']]),
+        dict(
+            url='https://doc-4c-2o-drive-data-export.googleusercontent.com/'
+            'download/fjpfehrefh7sl37sr71jeh2bhss0bjnc/cc96iun157a4pj0p3v284'
+            'ra800a04jff/1671610500000/8c3588ab-67fe-4d4d-8a0c-d105e4cbcfd3/'
+            '103212024722882466354/ADt3v-Ovr_nucmMNIjxpVbCHhn2p5_N7rtbldYPUt'
+            'HF_k1dtcWih0LnE1BSUuHNhlf7MF4mcABQFhpaEIZX_GIkaDOUJ3IT8gSnMiz'
+            '5aaK225clwIWyEBmZHqKC3e87Gz785sWQUSRLxucU3k2JCvyfI0uwnlozNcICY'
+            'fRn2pPnCmGL4-iqm6MtsH9fzy5p_3nWpgw6TN5q14-2wT4CsIdMK_kPizJCzkV'
+            'GkYkiRmYp3AfQso1kxGn5x1h1KsI9ofz9VnJJDmLITqILz7ax8_5IIsMVkgDkxg'
+            'FJM8pUfdVPQw2Y1n96Hm3M0UGWM2m-ZVxQJExRLTDL-CCC1AWkLAY6EwWFmpnDt'
+            'dg==?nonce=6aol4ohc1essk&user=103212024722882466354&authuser=0'
+            '&hash=mci04vpisvduilokqck7la6as0qrd2ut',
+            save_name='text.task1&2-test（361p)-20221205T112052Z-001.zip',
+            md5='0bf94b74a5baadfe2bb0cd72889127a5',
+            split=['test'],
+            content=['annotation'],
+            mapping=[['text/text.task1_2-test（361p)', 'annotations/test']]),
+    ])
+
+data_converter = dict(
+    type='TextDetDataConverter',
+    splits=['train', 'test'],
+    data_root=data_root,
+    gatherer=dict(
+        type='pair_gather',
+        suffixes=['.jpg'],
+        rule=[r'X(\d+)\.([jJ][pP][gG])', r'X\1.txt']),
+    parser=dict(type='SROIETextDetAnnParser', encoding='utf-8-sig'),
+    dumper=dict(type='JsonDumper'),
+    delete=['text', 'task1&2_test(361p)-20221205T104647Z-001', '0325updated', 'annotations']
+)
+
+config_generator = dict(type='TextDetConfigGenerator', data_root=data_root)

dataset_zoo/sroie/textrecog.py

@@ -0,0 +1,5 @@
+_base_ = ['textdet.py']
+
+data_converter = dict(type='TextRecogCropConverter')
+
+config_generator = dict(type='TextRecogConfigGenerator')

dataset_zoo/sroie/textspotting.py

@@ -0,0 +1,5 @@
+_base_ = ['textdet.py']
+
+data_converter = dict(type='TextSpottingDataConverter')
+
+config_generator = dict(type='TextSpottingConfigGenerator')

mmocr/datasets/preparers/data_converter.py

@@ -164,6 +164,8 @@ def pair_gather(self, img_path: str, suffixes: List, rule: Sequence,
         """
         files = list()
         for file in list_files(img_path, suffixes):
+            if not re.match(rule[0], osp.basename(file)):
+                continue
             file2 = re.sub(rule[0], rule[1], osp.basename(file))
             file2 = file.replace(osp.basename(file), file2)
             file2 = file2.replace(self.img_dir, 'annotations')

mmocr/datasets/preparers/data_obtainer.py

@@ -1,6 +1,7 @@
 # Copyright (c) OpenMMLab. All rights reserved.
 import os
 import os.path as osp
+import glob
 import shutil
 import ssl
 import urllib.request as request
@@ -148,7 +149,14 @@ def move(self, mapping: List[Tuple[str, str]]) -> None:
         for src, dst in mapping:
             src = osp.join(self.data_root, src)
             dst = osp.join(self.data_root, dst)
-            if osp.exists(src) and not osp.exists(dst):
+
+            if '*' in src:
+                mkdir_or_exist(dst)
+                for f in glob.glob(src):
+                    if not osp.exists(osp.join(dst, osp.basename(f))):
+                        shutil.move(f, dst)
+
+            elif osp.exists(src) and not osp.exists(dst):
                 shutil.move(src, dst)
 
     def clean(self) -> None:

mmocr/datasets/preparers/parsers/__init__.py

@@ -5,9 +5,10 @@
 from .svt_parser import SVTTextDetAnnParser
 from .totaltext_parser import TotaltextTextDetAnnParser
 from .wildreceipt_parser import WildreceiptKIEAnnParser
+from .sroie_parser import SROIETextDetAnnParser
 
 __all__ = [
     'ICDARTxtTextDetAnnParser', 'ICDARTxtTextRecogAnnParser',
     'TotaltextTextDetAnnParser', 'WildreceiptKIEAnnParser',
-    'COCOTextDetAnnParser', 'SVTTextDetAnnParser'
+    'COCOTextDetAnnParser', 'SVTTextDetAnnParser', 'SROIETextDetAnnParser'
 ]

mmocr/datasets/preparers/parsers/sroie_parser.py

@@ -0,0 +1,74 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+from typing import List, Optional, Tuple
+
+from mmocr.utils import bbox2poly
+from ..data_preparer import DATA_PARSERS
+from .base import BaseParser
+
+
+@DATA_PARSERS.register_module()
+class SROIETextDetAnnParser(BaseParser):
+    """SROIE Txt Format Text Detection Annotation Parser.
+
+    The original annotation format of this dataset is stored in txt files,
+    which is formed as the following format:
+        x1, y1, x2, y2, x3, y3, x4, y4, transcription
+
+    Args:
+        separator (str): The separator between each element in a line. Defaults
+            to ','.
+        ignore (str): The text to be ignored. Defaults to '###'.
+        format (str): The format of the annotation. Defaults to
+            'x1,y1,x2,y2,x3,y3,x4,trans'.
+        encoding (str): The encoding of the annotation file. Defaults to
+            'utf-8-sig'.
+        nproc (int): The number of processes to parse the annotation. Defaults
+            to 1.
+        remove_strs (List[str], Optional): Used to remove redundant strings in
+            the transcription. Defaults to None.
+        mode (str, optional): The mode of the box converter. Supported modes
+            are 'xywh' and 'xyxy'. Defaults to None.
+    """
+
+    def __init__(self,
+                 separator: str = ',',
+                 ignore: str = '###',
+                 format: str = 'x1,y1,x2,y2,x3,y3,x4,y4,trans',
+                 encoding: str = 'utf-8-sig',
+                 nproc: int = 1,
+                 remove_strs: Optional[List[str]] = None,
+                 mode: str = None) -> None:
+        self.sep = separator
+        self.format = format
+        self.encoding = encoding
+        self.ignore = ignore
+        self.mode = mode
+        self.remove_strs = remove_strs
+        super().__init__(nproc=nproc)
+
+    def parse_file(self, file: Tuple, split: str) -> Tuple:
+        """Parse single annotation."""
+        img_file, txt_file = file
+        instances = list()
+        try:
+        # there might be some illegal symbols in the annotation
+        # which cannot be parsed by loader
+            for anno in self.loader(txt_file, self.sep, self.format,
+                                    self.encoding):
+                anno = list(anno.values())
+                if self.remove_strs is not None:
+                    for strs in self.remove_strs:
+                        for i in range(len(anno)):
+                            if strs in anno[i]:
+                                anno[i] = anno[i].replace(strs, '')
+                poly = list(map(float, anno[0:-1]))
+                if self.mode is not None:
+                    poly = bbox2poly(poly, self.mode)
+                    poly = poly.tolist()
+                text = anno[-1]
+                instances.append(
+                    dict(poly=poly, text=text, ignore=text == self.ignore))
+        except Exception:
+            pass
+
+        return img_file, instances