Papers › Character Region Awareness for Text Detection

Character Region Awareness for Text Detection

3 Apr 2019CVPR 2019 6arXiv:1904.01941archive 2025-07-28

Youngmin Baek, Bado Lee, Dongyoon Han, Sangdoo Yun, Hwalsuk Lee

Scene text detection methods based on neural networks have emerged recently and have shown promising results. Previous methods trained with rigid word-level bounding boxes exhibit limitations in representing the text region in an arbitrary shape. In this paper, we propose a new scene text detection method to effectively detect text area by exploring each character and affinity between characters. To overcome the lack of individual character level annotations, our proposed framework exploits both the given character-level annotations for synthetic images and the estimated character-level ground-truths for real images acquired by the learned interim model. In order to estimate affinity between characters, the network is trained with the newly proposed representation for affinity. Extensive experiments on six benchmarks, including the TotalText and CTW-1500 datasets which contain highly curved texts in natural images, demonstrate that our character-level text detection significantly outperforms the state-of-the-art detectors. According to the results, our proposed method guarantees high flexibility in detecting complicated scene text images, such as arbitrarily-oriented, curved, or deformed texts.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 40 code samples harvested from 7 repositories linked to this paper: 25 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 40 samples from 7 repositories, 25 ran (20 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

18 repositories listed; official and paper-mentioned ones first.

JaidedAI/EasyOCR mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified); nothing checks that they implement this paper's method. report
Luckygyana/Invo-AI mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
SpikeKing/CRAFT-Re-reimplementation mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
autonise/CRAFT-Remade mentioned on GitHubpytorchMITSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report
backtime92/CRAFT-Reimplementation mentioned on GitHubpytorchSyntology: not harvested report
chauthehan/CRAFT mentioned on GitHubtfSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
clovaai/CRAFT-pytorch mentioned on GitHubpytorchMITSyntology: 8 samples, 7 ran (0 instrument-failed) · 1 unverified report
dipu-bd/craft-moran-ocr mentioned on GitHubpytorchSyntology: not harvested report
gmuffiness/CRAFT-train mentioned on GitHubpytorchSyntology: not harvested report
guruL/Character-Region-Awareness-for-Text-Detection- mentioned on GitHubpytorchSyntology: not harvested report
inouetaka/CRAFT mentioned on GitHubpytorchSyntology: not harvested report
jakartaresearch/receipt-ocr mentioned on GitHubpytorchMITSyntology: 11 samples, 4 ran (0 instrument-failed) · 7 unverified report
joanrod/ocr-vqgan mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Taming Transformers for High-Resolution Image Synthesis (arXiv:2012.09841; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
namedysx/CRAFT-tensorflow mentioned on GitHubtfSyntology: not harvested report
rainbowhash/ID_CARD_Automation mentioned on GitHubpytorchSyntology: not harvested report
scoutant/signature-detect mentioned on GitHubpytorchSyntology: not harvested report
SakuraRiven/CRAFT pytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
nunenuh/craft.pytorch pytorchApache-2.0Syntology: 10 samples, 7 ran (0 instrument-failed) · 3 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

40 samples harvested: 25 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 0 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 15 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
3ran · our draft was wrong
2ran; the contract check could not run
19ran
15unverified

Licence: 4 of the 40 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 7 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

SpikeKing/CRAFT-Re-reimplementation community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
copyStateDict trainSyndata.py ran · our draft was wrong no licence file found · pointer only · cec16dc1a4349b41 · report fixture: signature state_dict:dict/0/? · returned OrderedDict · level recorded 2026-09-22
autonise/CRAFT-Remade community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
clean_annots src/utils/data_structure_ic17.py ran MIT (permissive) · 89d70e7cf93ed2df · report fixture: signature base_path:str/0/str, base_image_path:str/0/str · returned dict · level recorded 2026-09-24
denormalize_mean_variance src/utils/data_manipulation.py unverified MIT (permissive) · 0967b66c489945c3 · report
normalize_mean_variance src/utils/data_manipulation.py unverified MIT (permissive) · 57aac6f1caa06b6f · report
patch_replication_callback in 18 papers src/utils/parallel.py unverified MIT (permissive) · e50200dbeffa0133 · report
return_height_width src/utils/check_dataset.py unverified MIT (permissive) · 14efc945c083eae4 · report
chauthehan/CRAFT community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
compute_input detect.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 182a7a8c7e4855e0 · report fixture: signature image:ndarray/3/int · returned ndarray · level recorded 2026-09-22
get_rotated_width_height tools.py ran · honoured contract no licence file found · pointer only · 50ba87e95515668b · report fixture: signature box:list/1/ndarray · returned tuple · level recorded 2026-09-22
invert_input detect.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 477af6fc28a1f011 · report fixture: signature X:ndarray/3/float · returned ndarray · level recorded 2026-09-22
clovaai/CRAFT-pytorch community (archive-listed) 8 samples, 7 ran (0 instrument-failed) · 1 unverified
getDetBoxes_core craft_utils.py ran MIT (permissive) · c13a54a77b4f00e8 · report fixture: signature textmap:ndarray/2/float, linkmap:ndarray/2/float, text_threshold:float/0/float, link_threshold:float/0/float, low_text:float/0/float · returned tuple · level recorded 2026-09-24
getPoly_core craft_utils.py ran MIT (permissive) · 45f5918657dff3ff · report fixture: signature boxes:list/1/ndarray, labels:ndarray/2/int, mapper:dict/0/?, linkmap:ndarray/2/int · returned list · level recorded 2026-09-24
get_files in 30 papers file_utils.py ran fingerprinted MIT (permissive) · 5eb8f5306638605a · report fixture: signature img_dir:str/0/str · returned tuple · level recorded 2026-09-24
list_files in 33 papers file_utils.py ran fingerprinted MIT (permissive) · 3a2cb8ecd06449a7 · report fixture: signature in_path:str/0/str · returned tuple · level recorded 2026-09-24
loadImage imgproc.py ran MIT (permissive) · fcfd3b787bf16ec2 · report fixture: signature img_file:str/0/str · returned ndarray · level recorded 2026-09-24
normalizeMeanVariance imgproc.py ran MIT (permissive) · bbb59da91782eb4d · report fixture: signature in_img:ndarray/3/int, mean:tuple/1/float, variance:tuple/1/float · returned ndarray · level recorded 2026-09-24
warpCoord craft_utils.py ran fingerprinted MIT (permissive) · c2c03abebea398e0 · report fixture: signature Minv:ndarray/2/float, pt:ndarray/1/float · returned ndarray · level recorded 2026-09-24
denormalizeMeanVariance imgproc.py unverified MIT (permissive) · b9439a9c0e20cc6f · report
jakartaresearch/receipt-ocr community (archive-listed) 11 samples, 4 ran (0 instrument-failed) · 7 unverified
copy_state_dict in 7 papers src/text_detector/load_model.py ran MIT (permissive) · 57a0fb73bcfe67fa · report fixture: signature state_dict:dict/0/? · returned OrderedDict · level recorded 2026-09-24
resize_aspect_ratio src/text_detector/modules/imgproc.py ran MIT (permissive) · dfefccf0cadf1742 · report fixture: signature img:ndarray/3/int, square_size:int/0/int, interpolation:int/0/int, mag_ratio:int/0/int · returned tuple · level recorded 2026-09-24
timeit in 59 papers src/engine.py ran MIT (permissive) · d54faa5a93381208 · report fixture: signature method:callable/0/? · returned function · level recorded 2026-09-24
yaml_loader src/text_detector/modules/utils.py ran MIT (permissive) · ed031c09bde0c116 · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-24
data_preparation src/text_recognizer/infer.py unverified MIT (permissive) · 884d81c7e8570b00 · report
inference in 65 papers src/text_detector/infer.py unverified MIT (permissive) · 0080f90ce4243bd0 · report
inference in 65 papers src/text_recognizer/infer.py unverified MIT (permissive) · 4966ec7a56eb141d · report
load_craft src/text_detector/load_model.py unverified MIT (permissive) · 4de3d5024b3166bc · report
load_craft_onnx src/text_detector/load_model.py unverified MIT (permissive) · 5fa3b7d854c65f78 · report
load_star src/text_recognizer/load_model.py unverified MIT (permissive) · 495ff57c5a36a262 · report
test_net src/text_detector/infer.py unverified MIT (permissive) · 6642e901efdd1c29 · report
SakuraRiven/CRAFT community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
plot_boxes detect.py ran · our draft was wrong MIT (permissive) · d52500f5b8ec969d · report fixture: signature img:Image/0/?, boxes:list/1/list · returned Image · level recorded 2026-09-22
resize_img in 31 papers detect.py ran · our draft was wrong MIT (permissive) · 193feca2a79684d9 · report fixture: signature img:Image/0/?, long_side:int/0/int · returned tuple · level recorded 2026-09-22
nunenuh/craft.pytorch community (archive-listed) 10 samples, 7 ran (0 instrument-failed) · 3 unverified
batch_box_coordinate_to_xyminmax craft/ops/box_ops.py ran Apache-2.0 (permissive) · e4c0369feb21e11b · report fixture: signature boxes:list/1/list, to_int:bool/0/bool · returned ndarray · level recorded 2026-09-24
box_coordinate_to_xyminmax craft/ops/box_ops.py ran Apache-2.0 (permissive) · cb9cc883042ddaf7 · report fixture: signature box:tuple/1/list, to_int:bool/0/bool · returned tuple · level recorded 2026-09-24
combine_point_single craft/datasets/utils.py ran Apache-2.0 (permissive) · 9ec176e145bf2527 · report fixture: signature bx:ndarray/1/float, by:ndarray/1/float, idxpos:int/0/int, to_int:bool/0/bool · returned tuple · level recorded 2026-09-24
load_json2dict craft/datasets/utils.py ran Apache-2.0 (permissive) · 1018b4cd7ad82c3d · report fixture: signature pathfile:str/0/str · returned dict · level recorded 2026-09-24
negative_mask craft/nn/functional.py ran Apache-2.0 (permissive) · 4ee9e2489b6b87dc · report fixture: signature score:Tensor/2/float, thresh:float/0/float · returned Tensor · level recorded 2026-09-24
order_points in 5 papers craft/ops/box_ops.py ran Apache-2.0 (permissive) · aa2cc8d50d099d54 · report fixture: signature pts:ndarray/2/float · returned ndarray · level recorded 2026-09-24
positive_mask craft/nn/functional.py ran Apache-2.0 (permissive) · 1e3766c4386e7660 · report fixture: signature score:Tensor/2/float, thresh:float/0/float · returned Tensor · level recorded 2026-09-24
load_image in 273 papers craft/datasets/utils.py unverified Apache-2.0 (permissive) · c6c3b5dabfc3b506 · report
trainset_transform craft/datasets/loader.py unverified Apache-2.0 (permissive) · d465866867a306de · report
validset_transform craft/datasets/loader.py unverified Apache-2.0 (permissive) · 372dcf0bd38d6552 · report

Tasks

Scene Text DetectionText Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Detection ICDAR 2013 CRAFT H-Mean 95.2 #16 of 16 Archive leaderboard report
Scene Text Detection ICDAR 2013 CRAFT Precision 97.4 #16 of 16 Archive leaderboard report
Scene Text Detection ICDAR 2013 CRAFT Recall 93.1 #16 of 16 Archive leaderboard report
Scene Text Detection ICDAR 2015 CRAFT F-Measure 86.9 #19 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 CRAFT Precision 89.8 #19 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2015 CRAFT Recall 84.3 #19 of 43 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT CRAFT H-Mean 73.9 #8 of 14 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT CRAFT Precision 80.6 #8 of 14 Archive leaderboard report
Scene Text Detection ICDAR 2017 MLT CRAFT Recall 68.2 #8 of 14 Archive leaderboard report
Scene Text Detection MSRA-TD500 CRAFT F-Measure 82.9 #10 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 CRAFT Precision 88.2 #10 of 18 Archive leaderboard report
Scene Text Detection MSRA-TD500 CRAFT Recall 78.2 #10 of 18 Archive leaderboard report
Scene Text Detection SCUT-CTW1500 CRAFT F-Measure 83.5 #9 of 17 Archive leaderboard report
Scene Text Detection SCUT-CTW1500 CRAFT Precision 86 #9 of 17 Archive leaderboard report
Scene Text Detection SCUT-CTW1500 CRAFT Recall 81.1 #9 of 17 Archive leaderboard report
Scene Text Detection Total-Text CRAFT F-Measure 83.6% #17 of 27 Archive leaderboard report
Scene Text Detection Total-Text CRAFT Precision 87.6 #17 of 27 Archive leaderboard report
Scene Text Detection Total-Text CRAFT Recall 79.9 #17 of 27 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections