Papers › An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its...

An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition

21 Jul 2015arXiv:1507.05717archive 2025-07-28

Baoguang Shi, Xiang Bai, Cong Yao

Image-based sequence recognition has been a long-standing research topic in computer vision. In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence recognition. A novel neural network architecture, which integrates feature extraction, sequence modeling and transcription into a unified framework, is proposed. Compared with previous systems for scene text recognition, the proposed architecture possesses four distinctive properties: (1) It is end-to-end trainable, in contrast to most of the existing algorithms whose components are separately trained and tuned. (2) It naturally handles sequences in arbitrary lengths, involving no character segmentation or horizontal scale normalization. (3) It is not confined to any predefined lexicon and achieves remarkable performances in both lexicon-free and lexicon-based scene text recognition tasks. (4) It generates an effective yet much smaller model, which is more practical for real-world application scenarios. The experiments on standard benchmarks, including the IIIT-5K, Street View Text and ICDAR datasets, demonstrate the superiority of the proposed algorithm over the prior arts. Moreover, the proposed algorithm performs well in the task of image-based music score recognition, which evidently verifies the generality of it.

PaperPDFCodeCode 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 81 code samples: 80 from 21 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 81: 66 ran (of which 0 constructed an object rather than computing a result; 49 with no instrument failure: 1 honoured, 1 violated, 47 with no contract checked; 17 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; 8 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 80 samples from 21 repositories, 65 ran (49 with no instrument failure; 16 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 66 samples that ran have no recorded date.

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

9ruddls3/CRNN_Pytorch mentioned on GitHubpytorchSyntology: not harvested report
CodeAchieveDream/crnn_model mentioned on GitHubpytorchSyntology: not harvested report
Crespo-dong/caffe_ocr mentioned on GitHubSyntology: not harvested report
DCSong/CRNN-DenseNet mentioned on GitHubpytorchMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
DnanaDev/CRNN_for_OCR mentioned on GitHubtfSyntology: not harvested report
FLming/CRNN.tf2 mentioned on GitHubtfMITSyntology: 2 samples, 0 ran · 2 unverified report
GitYCC/crnn-pytorch mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
HassamChundrigar/Urdu-Ocr mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
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
L706077/OCR-CRNN mentioned on GitHubpytorchMITSyntology: 1 sample, 0 ran · 1 unverified report
Liumihan/CRNN_kreas mentioned on GitHubtfSyntology: not harvested report
Liumihan/CRNN_pytorch mentioned on GitHubpytorchSyntology: not harvested report
MaybeShewill-CV/CRNN_Tensorflow mentioned on GitHubtfSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
Media-Smart/vedastr mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
Mingtzge/2019-CCF-BDCI-OCR-MCZJ-OCR-IdentificationIDElement mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Image-to-Image Translation with Conditional Adversarial Networks (arXiv:1611.07004; that paper's own run record: 74 ran (of which 0 constructed an object rather than computing a result; 66 with no instrument failure: 4 honoured, 5 violated, 57 with no contract checked; 8 where Syntology's instrument failed) · 48 unverified); nothing checks that they implement this paper's method. report
PaddlePaddle/PaddleOCR mentioned on GitHubpaddleApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to... (arXiv:2508.19944; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
PratirupG/Handwriting-Recognition mentioned on GitHubtfSyntology: not harvested report
SYR-Aegis/BrailleOCR mentioned on GitHubpytorchSyntology: not harvested report
WenmuZhou/PytorchOCR mentioned on GitHubpytorchSyntology: not harvested report
WenmuZhou/Segmentation-Free_OCR mentioned on GitHubtfGPL-3.0Syntology: not harvested report
Yuting-Gao/CRNN_Mxnet mentioned on GitHubtfSyntology: not harvested report
abdulwaheedsoudagar/ImageTextTranslation mentioned on GitHubtfSyntology: not harvested report
abhiraman/Capstone_Project mentioned on GitHubpytorchSyntology: not harvested report
anuragcp/iocl-deepocr mentioned on GitHubtfSyntology: not harvested report
bai-shang/CRNN_CTC_Tensorflow mentioned on GitHubtfSyntology: not harvested report
bai-shang/OCR_TF_CRNN_CTC mentioned on GitHubtfSyntology: not harvested report
bai-shang/crnn_ctc_ocr.Tensorflow mentioned on GitHubtfSyntology: not harvested report
bai-shang/crnn_ctc_ocr_tf mentioned on GitHubtfSyntology: not harvested report
bgshih/crnn mentioned on GitHubpytorchMITSyntology: not harvested report
bharatsush/TextSpotting mentioned on GitHubtfSyntology: not harvested report
bhavitvyamalik/OCR-using-CRNN mentioned on GitHubSyntology: not harvested report
carnotaur/crnn-tutorial mentioned on GitHubpytorchSyntology: not harvested report
chandan5362/Indian-Number-Plate-Recognition mentioned on GitHubSyntology: not harvested report
chauthehan/CRNN_OCR_CMND mentioned on GitHubSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
cipri-tom/type-aware-crnn mentioned on GitHubtfGPL-3.0Syntology: not harvested report
cjxxx0/license mentioned on GitHubtfSyntology: not harvested report
courao/ocr.pytorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Detecting Text in Natural Image with Connectionist Text Proposal Network (arXiv:1609.03605; that paper's own run record: 30 ran (of which 0 constructed an object rather than computing a result; 27 with no instrument failure: 3 honoured, 1 violated, 23 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
foamliu/CRNN mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
githubharald/simplehtr mentioned on GitHubtfMITSyntology: not harvested report
harish2704/pottan-ocr mentioned on GitHubpytorchMITSyntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
jackknife007/crnn mentioned on GitHubtfSyntology: 4 samples, 3 ran (3 instrument-failed) · 1 unverified report
juanluisrosaramos/CRNN_OCR mentioned on GitHubtfSyntology: not harvested report
junstar92/hangul-syllable-recognition mentioned on GitHubtfSyntology: not harvested report
lidongliang666/cv_deep_learning mentioned on GitHubpytorchSyntology: not harvested report
lostsword/character_recognition mentioned on GitHubmindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Detecting Text in Natural Image with Connectionist Text Proposal Network (arXiv:1609.03605; that paper's own run record: 30 ran (of which 0 constructed an object rather than computing a result; 27 with no instrument failure: 3 honoured, 1 violated, 23 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
mindee/doctr mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Real-time Scene Text Detection with Differentiable Binarization (arXiv:1911.08947; that paper's own run record: 20 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
mineshmathew/pytorch_rnn_examples mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
moto8xpk/DataExtractionJejuMLCamp mentioned on GitHubSyntology: not harvested report
mrzaizai2k/Information-recognition-on-the-university-test-paper mentioned on GitHubtfMITSyntology: 17 samples, 14 ran (0 instrument-failed) · 3 unverified report
naveen-kumar-123/Handwritten-text-recognition---CNN-and-LSTM mentioned on GitHubtfMITSyntology: not harvested report
nithyadurai87/pottan-ocr-tamil mentioned on GitHubpytorchMITSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
oyxhust/CNN-LSTM-CTC-text-recognition mentioned on GitHubtfSyntology: 5 samples, 5 ran (5 instrument-failed) · 0 unverified report
qjadud1994/CRNN-Keras mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
rajmuchhala/Raj-Muchhala---Sr.-ML-Engineer--ML-Assignmen mentioned on GitHubSyntology: not harvested report
rickyHong/CRNN-Tensorflow-Text-repl mentioned on GitHubtfSyntology: not harvested report
samueltin/tf-crnn_backup20180808 mentioned on GitHubtfGPL-3.0Syntology: not harvested report
sbillburg/CRNN-with-STN mentioned on GitHubtfSyntology: 1 sample, 0 ran · 1 unverified report
senlinuc/caffe_ocr mentioned on GitHubSyntology: not harvested report
sgenza/tf_crnn mentioned on GitHubtfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
shivaverma/Score-Time-Detection mentioned on GitHubpytorchSyntology: not harvested report
shreshtashetty/OCR mentioned on GitHubtfSyntology: not harvested report
solivr/tf-crnn mentioned on GitHubtfGPL-3.0Syntology: not harvested report
sonamghosh/local_hack_day_2018 mentioned on GitHubpytorchSyntology: not harvested report
tanmaysheoran/CRNN-Sequence-Text-Recognition mentioned on GitHubSyntology: not harvested report
topdu/openocr mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene... (arXiv:2103.06495; that paper's own run record: 18 ran (of which 11 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified) and CVF open access id Du_SVTRv2_CTC_Beats_Encoder-Decoder_Models_in_Scene_Text_Recognition_ICCV_2025_paper (that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
tranbahien/CTC-OCR mentioned on GitHubtfSyntology: not harvested report
wacr2008/tensorflow_crnn mentioned on GitHubtfSyntology: not harvested report
wangrui1996/crnnLicensePlateRecognition mentioned on GitHubtfSyntology: not harvested report
weinman/cnn_lstm_ctc_ocr mentioned on GitHubtfGPL-3.0Syntology: not harvested report
xmy0916/pytorch_crnn mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
xusongpei/crnn-ctc mentioned on GitHubtfSyntology: not harvested report
zhiqwang/crnn.pytorch mentioned on GitHubpytorchMITSyntology: not harvested report
zhiqwang/image-captioning mentioned on GitHubpytorchMITSyntology: not harvested report
ztoString/CRNN_CTC_OCR_TensorFlow mentioned on GitHubtfSyntology: not harvested report
zwenwang/CTPN_Pytorch mentioned on GitHubpytorchSyntology: not harvested report
zyasjtu/CNN-RNN-CTC mentioned on GitHubtfSyntology: not harvested report
2023-MindSpore-1/ms-code-210 mindsporeSyntology: not harvested report
Holmeyoung/crnn-pytorch pytorchMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
WenmuZhou/crnn.pytorch pytorchApache-2.0Syntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
kurapan/CRNN tfMITSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
meijieru/crnn.pytorch pytorchMITSyntology: not harvested report
mindspore-lab/mindocr mindsporenot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: not harvested report
sartaj0/TextRecognition-Pytorch pytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 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

81 samples harvested: 66 ran (of which 0 constructed an object rather than computing a result; 49 with no instrument failure: 1 honoured, 1 violated, 47 with no contract checked; 17 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
1ran · violated contract
9ran · our draft was wrong
8ran; the contract check could not run
47ran
15unverified

Licence: 17 of the 81 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 21 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. 1 sample is listed last, in a group without a repository. “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”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

DCSong/CRNN-DenseNet community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
collate_fn in 500 papers main_v2.py ran MIT (permissive) · 1034c8100229cfaa · report fixture: signature data_list:list/1/tuple · returned list · level recorded 2026-09-26
create_an_image data_generator/generator.py ran MIT (permissive) · 4a328dcfa78235f0 · report fixture: signature bground_path:str/0/str, width:int/0/int, height:int/0/int · returned Image · level recorded 2026-09-26
cv_imread infer.py ran MIT (permissive) · d8dedde195599807 · report fixture: signature file_path:str/0/str · returned ndarray · level recorded 2026-09-26
darken_func data_generator/generator.py ran MIT (permissive) · 6f137578ee4c9a8c · report fixture: signature image:Image/0/? · returned Image · level recorded 2026-09-26
decode_trueLabel main_v2.py ran MIT (permissive) · 62c9fb7421034e69 · report fixture: signature labels:Tensor/1/int, label_lengths:Tensor/1/int · returned list · level recorded 2026-09-26
sto_choice_from_info_str data_generator/generator.py unverified MIT (permissive) · 699d3ccd431d7c10 · report
FLming/CRNN.tf2 community (archive-listed) 2 samples, 0 ran · 2 unverified
build_model in 469 papers crnn/models.py unverified MIT (permissive) · 296ecf73d26896df · report
vgg_style crnn/models.py unverified MIT (permissive) · ce63cd357ce4255f · report
GitYCC/crnn-pytorch community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
beam_search_decode src/ctc_decoder.py ran MIT (permissive) · 3cc6d82c871b003e · report fixture: signature emission_log_prob:ndarray/2/float, blank:int/0/int, beam_size:int/0/int · returned list · level recorded 2026-09-26
greedy_decode in 9 papers src/ctc_decoder.py ran MIT (permissive) · f056f6c91ff28c7e · report fixture: signature emission_log_prob:ndarray/2/float, blank:int/0/int · returned list · level recorded 2026-09-26
prefix_beam_decode src/ctc_decoder.py ran MIT (permissive) · 37410a7cdba16e43 · report fixture: signature emission_log_prob:ndarray/2/float, blank:int/0/int, beam_size:int/0/int · returned list · level recorded 2026-09-26
synth90k_collate_fn src/dataset.py ran MIT (permissive) · fbb057bc924b5ded · report fixture: signature batch:list/1/tuple · returned tuple · level recorded 2026-09-26
HassamChundrigar/Urdu-Ocr community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
dense_to_text utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · b4d833e2c3bc615e · report fixture: returned str · level recorded 2026-09-22
L706077/OCR-CRNN community (archive-listed) 1 sample, 0 ran · 1 unverified
checkImageIsValid in 5 papers tool/create_dataset.py unverified MIT (permissive) · 196d7ffb0297719f · report
MaybeShewill-CV/CRNN_Tensorflow community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
args_str2bool tools/train_shadownet.py ran · violated contract MIT (permissive) · eba8919c2ae4a92f · report fixture: signature arg_value:str/0/str · returned bool · level recorded 2026-09-22
compute_net_gradients tools/train_shadownet.py ran · our draft was wrong MIT (permissive) · 2de2452efe03beb8 · report fixture: signature images:Tensor/4/float, labels:Tensor/1/int, net:callable/0/?, optimizer:StandInOptimizer/0/?, is_net_first_initialized:bool/0/bool · returned tuple · level recorded 2026-09-22
chauthehan/CRNN_OCR_CMND community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
decode_label prediction.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · ca246044b67802d8 · report fixture: signature label:list/1/list, chars:list/1/str · returned str · level recorded 2026-09-22
encode_utf8_string build_dataset.py ran · honoured contract no licence file found · pointer only · 1406f043e92b305c · report fixture: signature text:str/0/str, length:int/0/int, dic:dict/0/?, null_char_id:int/0/int · returned list · level recorded 2026-09-22
fastdecode prediction.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic no licence file found · pointer only · ad699c48847e4fa9 · report fixture: signature y_pred:list/1/ndarray, chars:str/0/str · returned str · level recorded 2026-09-22
foamliu/CRNN community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_learning_rate in 19 papers utils.py ran MIT (permissive) · f12870d2ed1448f7 · report fixture: signature optimizer:SGD/0/? · returned float · level recorded 2026-09-26
image_resize in 11 papers data_gen.py ran MIT (permissive) · 56c10a1bd102696b · report fixture: signature image:ndarray/3/int, width:int/0/int, height:int/0/int, inter:int/0/int · returned ndarray · level recorded 2026-09-26
harish2704/pottan-ocr community (archive-listed) 6 samples, 4 ran (0 instrument-failed) · 2 unverified
get_bg_value pottan_ocr/custom_dataset.py ran MIT (permissive) · 38df7f768aeaae08 · report fixture: signature img:ndarray/3/int · returned int64 · level recorded 2026-09-26
myOpen pottan_ocr/utils.py ran MIT (permissive) · 32a5943a79da34f1 · report fixture: signature fname:str/0/str, mode:str/0/str · returned TextIOWrapper · level recorded 2026-09-26
normaizeImg pottan_ocr/utils.py ran MIT (permissive) · 2ebd71c551e6a0af · report fixture: signature img:ndarray/2/int, channel_axis:int/0/int · returned ndarray · level recorded 2026-09-26
normalizeBatch pottan_ocr/utils.py ran MIT (permissive) · 5b549bdb59cee992 · report fixture: signature batch:list/1/tuple, channel_axis:int/0/int · returned tuple · level recorded 2026-09-26
compute_pred_size pottan_ocr/custom_dataset.py unverified MIT (permissive) · 23144073b24afafe · report
getTrainingTexts pottan_ocr/dataset.py unverified MIT (permissive) · 04d204671d905b25 · report
jackknife007/crnn community (archive-listed) 4 samples, 3 ran (3 instrument-failed) · 1 unverified
get_image_and_text cnn+lstm+ctc.py ran · our draft was wrong no licence file found · pointer only · f49ea6d719e3ce02 · report fixture: signature path:str/0/str · returned tuple · level recorded 2026-09-22
get_sparse_tuple cnn+lstm+ctc.py ran · our draft was wrong no licence file found · pointer only · fd70c122a864030b · report fixture: returned tuple · level recorded 2026-09-22
get_text in 18 papers generate.py ran · our draft was wrong fingerprinted no licence file found · pointer only · dd0c2e41c087ec45 · report fixture: signature low:int/0/int, high:int/0/int, char_set:list/1/str · returned str · level recorded 2026-09-22
get_test_data in 10 papers cnn+lstm+ctc.py unverified no licence file found · pointer only · 9d05adb33343f13f · report
mrzaizai2k/Information-recognition-on-the-university-test-paper community (archive-listed) 17 samples, 14 ran (0 instrument-failed) · 3 unverified
augmentation in 17 papers source/imgtocsv.py ran fingerprinted MIT (permissive) · 873e142b9e566547 · report fixture: signature image:ndarray/2/int · returned ndarray · level recorded 2026-09-26
avg_wer source/create_metrics_OCR.py ran fingerprinted MIT (permissive) · de25232d166b4079 · report fixture: signature wer_scores:list/1/float, combined_ref_len:int/0/int · returned float · level recorded 2026-09-26
build_digit_model source/digit_model.py ran MIT (permissive) · 39edc5dd93906ed7 · report fixture: signature alphabets:str/0/str, max_str_len:int/0/int, img_width:int/0/int, img_height:int/0/int · returned tuple · level recorded 2026-09-26
build_word_model source/word_model.py ran MIT (permissive) · a1d537aa281c06d1 · report fixture: signature alphabets:list/1/str, max_str_len:int/0/int, img_width:int/0/int, img_height:int/0/int · returned tuple · level recorded 2026-09-26
char_errors source/create_metrics_OCR.py ran MIT (permissive) · 1f6ce9a5a3fefdb6 · report fixture: signature reference:str/0/str, hypothesis:str/0/str, ignore_case:bool/0/bool, remove_space:bool/0/bool · returned tuple · level recorded 2026-09-26
elastic_transform source/imgtocsv.py ran MIT (permissive) · 913bff8998669099 · report fixture: signature image:ndarray/2/float, alpha:float/0/float, sigma:float/0/float, random_state:RandomState/0/? · returned ndarray · level recorded 2026-09-26
label_to_num source/digit_train.py ran MIT (permissive) · d7024ede039d8d7a · report fixture: signature label:str/0/str · returned ndarray · level recorded 2026-09-26
num_to_label source/GUI.py ran MIT (permissive) · c71ecf200d7b47ff · report fixture: signature num:list/1/int, alphabets:str/0/str · returned str · level recorded 2026-09-26
num_to_label source/digit_train.py ran fingerprinted MIT (permissive) · 12a7e5523e0d5c4a · report fixture: signature num:list/1/int · returned str · level recorded 2026-09-26
predictions source/EAST.py ran MIT (permissive) · c9d1cf745655ed5e · report fixture: signature prob_score:ndarray/4/float, geo:ndarray/4/float · returned tuple · level recorded 2026-09-26
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
source/helper.py ran MIT (permissive) · 24597781733e9f0c · report fixture: signature img:ndarray/2/int, imgSize:tuple/1/int · returned ndarray · level recorded 2026-09-26
removeline source/Preprocessing.py ran MIT (permissive) · 1411d589bfc89bcc · report fixture: signature image:ndarray/2/int · returned ndarray · level recorded 2026-09-26
scheduler in 12 papers source/digit_train.py ran fingerprinted MIT (permissive) · 09177472a69b0aef · report fixture: signature epoch:int/0/int · returned float · level recorded 2026-09-26
word_errors source/create_metrics_OCR.py ran MIT (permissive) · 18d6344ade1b7bde · report fixture: signature reference:str/0/str, hypothesis:str/0/str, ignore_case:bool/0/bool, delimiter:str/0/str · returned tuple · level recorded 2026-09-26
alignImages source/Preprocessing.py unverified MIT (permissive) · 739081312362bdc6 · report
class_list source/Excel.py unverified MIT (permissive) · b366183f43c64854 · report
number_augment source/prepare_MSSV_dataset.py unverified MIT (permissive) · c1de96bd44318dd0 · report
nithyadurai87/pottan-ocr-tamil community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
levenshtein in 8 papers ocropy/ocrolib/edist.py ran fingerprinted MIT (permissive) · f50d8818f0a6b156 · report fixture: signature a:str/0/str, b:str/0/str · returned int · level recorded 2026-09-26
normaizeImg pottan_ocr/dataset.py ran MIT (permissive) · c3a16e37a8c26936 · report fixture: signature img:ndarray/2/int · returned Tensor · level recorded 2026-09-26
readFile in 6 papers pottan_ocr/utils.py ran MIT (permissive) · 1d4c2738c60c2109 · report fixture: signature fname:str/0/str · returned str · level recorded 2026-09-26
readLines pottan_ocr/utils.py ran MIT (permissive) · 88d6c289716c5525 · report fixture: signature fname:str/0/str · returned list · level recorded 2026-09-26
summary in 21 papers ocropy/ocrolib/exceptions.py ran fingerprinted MIT (permissive) · 4e697031db9e32d5 · report fixture: signature x:ndarray/2/float · returned str · level recorded 2026-09-26
xlevenshtein ocropy/ocrolib/edist.py ran MIT (permissive) · 8f842fd357c173e0 · report fixture: signature a:str/0/str, b:str/0/str, context:int/0/int · returned tuple · level recorded 2026-09-26
findNHFromFile pottan_ocr/ocr.py unverified MIT (permissive) · 64e1f2ed134eaa53 · report
oyxhust/CNN-LSTM-CTC-text-recognition community (archive-listed) 5 samples, 5 ran (5 instrument-failed) · 0 unverified
Accuracy in 7 papers train_lstm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · c1f5f90a5fe029c1 · report fixture: signature label:ndarray/2/int, pred:ndarray/2/float · returned float · level recorded 2026-09-22
Accuracy in 7 papers train_bi_lstm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 39b54be8c212cdc0 · report fixture: signature label:ndarray/2/int, pred:list/1/ndarray · returned float · level recorded 2026-09-22
Accuracy in 7 papers train_crnn.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 7688c4824425a1ea · report fixture: signature label:ndarray/2/int, pred:ndarray/2/float · returned float · level recorded 2026-09-22
ctc_label train_lstm.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted no licence file found · pointer only · 130856163be0ac52 · report fixture: signature p:list/1/int · returned list · level recorded 2026-09-22
remove_blank train_lstm.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted no licence file found · pointer only · 436e8501e30a7cb4 · report fixture: signature l:list/1/int · returned list · level recorded 2026-09-22
qjadud1994/CRNN-Keras community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
label_to_hangul Prediction.py ran · our draft was wrong fingerprinted MIT (permissive) · c979b2811c6d87de · report fixture: signature label:str/0/str · returned str · level recorded 2026-09-22
sbillburg/CRNN-with-STN community (archive-listed) 1 sample, 0 ran · 1 unverified
loc_net CRNN_with_STN.py unverified no licence file found · pointer only · 8f9b18959fd4541f · report
sgenza/tf_crnn community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
arrays2labels model/utils.py ran MIT (permissive) · 871cd40e81d189dd · report fixture: signature arrays:list/1/list, alphabet:str/0/str · returned list · level recorded 2026-09-26
read_config in 49 papers model/utils.py ran MIT (permissive) · 3192c8faf3910bdf · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-26
sparse_tuple_from model/utils.py ran MIT (permissive) · 924a9985cfa71dbe · report fixture: signature sequences:list/1/list · returned tuple · level recorded 2026-09-26
xmy0916/pytorch_crnn community (archive-listed) 1 sample, 0 ran · 1 unverified
get_crnn model/model.py unverified no licence file found · pointer only · 093288b6c8663ae1 · report
Holmeyoung/crnn-pytorch community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
assureRatio utils.py ran fingerprinted MIT (permissive) · bc714562632bad86 · report fixture: signature img:Tensor/4/float · returned Tensor · level recorded 2026-09-26
checkImageIsValid in 5 papers tool/create_dataset.py ran MIT (permissive) · bbe9f57bb5f10da7 · report fixture: signature imageBin:bytes/0/? · returned bool · level recorded 2026-09-26
oneHot utils.py ran MIT (permissive) · ccf0cad12e00b757 · report fixture: signature v:Tensor/1/int, v_length:Tensor/1/int, nc:int/0/int · returned Tensor · level recorded 2026-09-26
read_data_from_file tool/create_dataset.py ran MIT (permissive) · 9cb644f7ac131353 · report fixture: signature file_path:str/0/str · returned tuple · level recorded 2026-09-26
read_data_from_folder tool/create_dataset.py ran MIT (permissive) · 267a91d5ae5788a5 · report fixture: signature folder_path:str/0/str · returned tuple · level recorded 2026-09-26
trans_pos tool/convert_t7.py ran MIT (permissive) · ee286d9708b8f2e8 · report fixture: signature param:ndarray/2/float, part_indexes:list/1/int, dim:int/0/int · returned ndarray · level recorded 2026-09-26
WenmuZhou/crnn.pytorch community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
conv1x1 in 691 papers modeling/backbone/resnet_torch.py ran · our draft was wrong Apache-2.0 (permissive) · d9def42110729a85 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers modeling/backbone/resnet_torch.py ran · our draft was wrong Apache-2.0 (permissive) · 160bb14bd76201b4 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
kurapan/CRNN community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
create_result_subdir utils.py ran MIT (permissive) · 3a30552afd9800fe · report fixture: signature result_dir:str/0/str · returned str · level recorded 2026-09-26
pad_image in 27 papers utils.py ran MIT (permissive) · 92b4c2d4b7627a61 · report fixture: signature img:ndarray/3/int, img_size:tuple/1/int, nb_channels:int/0/int · returned ndarray · level recorded 2026-09-26
resize_image in 74 papers utils.py ran MIT (permissive) · 4dd30f678b132ee5 · report fixture: signature img:ndarray/3/int, img_size:tuple/1/int · returned ndarray · level recorded 2026-09-26
ctc_lambda_func models.py unverified MIT (permissive) · d58585cb2e4794d7 · report
loc_net models.py unverified MIT (permissive) · c195fa75ab2456ab · report
sartaj0/TextRecognition-Pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
decodeText inferenceWithOnnx.py ran · our draft was wrong fingerprinted no licence file found · pointer only · e5d49b58c143d9eb · report fixture: signature scores:ndarray/3/float · returned str · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
chunker in 11 papers repository not located ran · our draft was wrong licence of this copy not recorded · ec7977b6ec96dce1 · report fixture: signature seq:list/1/int, size:int/0/int · returned generator · level recorded 2026-09-22

Tasks

Optical Character Recognition (OCR)Scene Text Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Scene Text Recognition ICDAR 2003 CRNN Accuracy 89.4 #12 of 12 Archive leaderboard report
Scene Text Recognition ICDAR2013 CRNN Accuracy 86.7 #37 of 38 Archive leaderboard report
Scene Text Recognition SVT CRNN Accuracy 80.8 #36 of 37 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