SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1507.05717 · 2015

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

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 81 functions out of this paper's own repositories and ran 19 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
oyxhust/CNN-LSTM-CTC-text-recognition reimplementation 5 of 5
jackknife007/crnn reimplementation 3 of 4
chauthehan/CRNN_OCR_CMND reimplementation 3 of 3
MaybeShewill-CV/CRNN_Tensorflow reimplementation 2 of 2
WenmuZhou/crnn.pytorch pwc_unofficial 2 of 2
copy not recorded — 1 of 1
sartaj0/TextRecognition-Pytorch reimplementation 1 of 1
HassamChundrigar/Urdu-Ocr reimplementation 1 of 1
qjadud1994/CRNN-Keras reimplementation 1 of 1
mrzaizai2k/Information-recognition-on-the-university-test-paper pwc_unofficial 0 of 17
nithyadurai87/pottan-ocr-tamil pwc_unofficial 0 of 7
Holmeyoung/crnn-pytorch pwc_unofficial 0 of 6
DCSong/CRNN-DenseNet pwc_unofficial 0 of 6
harish2704/pottan-ocr pwc_unofficial 0 of 6
kurapan/CRNN pwc_unofficial 0 of 5
GitYCC/crnn-pytorch pwc_unofficial 0 of 4
sgenza/tf_crnn pwc_unofficial 0 of 3
FLming/CRNN.tf2 pwc_unofficial 0 of 2
foamliu/CRNN pwc_unofficial 0 of 2
L706077/OCR-CRNN pwc_unofficial 0 of 1
xmy0916/pytorch_crnn reimplementation 0 of 1
sbillburg/CRNN-with-STN extension 0 of 1
FunctionStatusWhere it lives
Accuracy Ran oyxhust/CNN-LSTM-CTC-text-recognition/train_lstm.py
pointer only (licence: NONE) · get_code("c1f5f90a5fe029c1")
Accuracy Ran oyxhust/CNN-LSTM-CTC-text-recognition/train_bi_lstm.py
pointer only (licence: NONE) · get_code("39b54be8c212cdc0")
Accuracy Ran oyxhust/CNN-LSTM-CTC-text-recognition/train_crnn.py
pointer only (licence: NONE) · get_code("7688c4824425a1ea")
args_str2bool Ran MaybeShewill-CV/CRNN_Tensorflow/tools/train_shadownet.py
code served (permissive licence) · get_code("eba8919c2ae4a92f")
chunker Ran this paper's copy was not recorded; identical code first harvested from danielzuegner/robust-gcn
pointer only · get_code("ec7977b6ec96dce1")
compute_net_gradients Ran MaybeShewill-CV/CRNN_Tensorflow/tools/train_shadownet.py
code served (permissive licence) · get_code("2de2452efe03beb8")
conv1x1 Ran WenmuZhou/crnn.pytorch/modeling/backbone/resnet_torch.py
code served (permissive licence) · get_code("d9def42110729a85")
conv3x3 Ran WenmuZhou/crnn.pytorch/modeling/backbone/resnet_torch.py
code served (permissive licence) · get_code("160bb14bd76201b4")
ctc_label Ran oyxhust/CNN-LSTM-CTC-text-recognition/train_lstm.py
pointer only (licence: NONE) · get_code("130856163be0ac52")
decodeText Ran sartaj0/TextRecognition-Pytorch/inferenceWithOnnx.py
pointer only (licence: NONE) · get_code("e5d49b58c143d9eb")
decode_label Ran chauthehan/CRNN_OCR_CMND/prediction.py
pointer only (licence: NONE) · get_code("ca246044b67802d8")
dense_to_text Ran HassamChundrigar/Urdu-Ocr/utils.py
pointer only (licence: NONE) · get_code("b4d833e2c3bc615e")
encode_utf8_string Ran chauthehan/CRNN_OCR_CMND/build_dataset.py
pointer only (licence: NONE) · get_code("1406f043e92b305c")
fastdecode Ran chauthehan/CRNN_OCR_CMND/prediction.py
pointer only (licence: NONE) · get_code("ad699c48847e4fa9")
get_image_and_text Ran jackknife007/crnn/cnn+lstm+ctc.py
pointer only (licence: NONE) · get_code("f49ea6d719e3ce02")
get_sparse_tuple Ran jackknife007/crnn/cnn+lstm+ctc.py
pointer only (licence: NONE) · get_code("fd70c122a864030b")
get_text Ran jackknife007/crnn/generate.py
pointer only (licence: NONE) · get_code("dd0c2e41c087ec45")
label_to_hangul Ran qjadud1994/CRNN-Keras/Prediction.py
code served (permissive licence) · get_code("c979b2811c6d87de")
remove_blank Ran oyxhust/CNN-LSTM-CTC-text-recognition/train_lstm.py
pointer only (licence: NONE) · get_code("436e8501e30a7cb4")
alignImages Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/Preprocessing.py
code served (permissive licence) · get_code("739081312362bdc6")
arrays2labels Not yet run sgenza/tf_crnn/model/utils.py
code served (permissive licence) · get_code("871cd40e81d189dd")
assureRatio Not yet run Holmeyoung/crnn-pytorch/utils.py
code served (permissive licence) · get_code("bc714562632bad86")
augmentation Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/imgtocsv.py
code served (permissive licence) · get_code("873e142b9e566547")
avg_wer Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/create_metrics_OCR.py
code served (permissive licence) · get_code("de25232d166b4079")
beam_search_decode Not yet run GitYCC/crnn-pytorch/src/ctc_decoder.py
code served (permissive licence) · get_code("3cc6d82c871b003e")
build_digit_model Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/digit_model.py
code served (permissive licence) · get_code("39edc5dd93906ed7")
build_model Not yet run FLming/CRNN.tf2/crnn/models.py
code served (permissive licence) · get_code("296ecf73d26896df")
build_word_model Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/word_model.py
code served (permissive licence) · get_code("a1d537aa281c06d1")
char_errors Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/create_metrics_OCR.py
code served (permissive licence) · get_code("1f6ce9a5a3fefdb6")
checkImageIsValid Not yet run Holmeyoung/crnn-pytorch/tool/create_dataset.py
code served (permissive licence) · get_code("bbe9f57bb5f10da7")
checkImageIsValid Not yet run L706077/OCR-CRNN/tool/create_dataset.py
code served (permissive licence) · get_code("196d7ffb0297719f")
class_list Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/Excel.py
code served (permissive licence) · get_code("b366183f43c64854")
collate_fn Not yet run DCSong/CRNN-DenseNet/main_v2.py
code served (permissive licence) · get_code("1034c8100229cfaa")
compute_pred_size Not yet run harish2704/pottan-ocr/pottan_ocr/custom_dataset.py
code served (permissive licence) · get_code("23144073b24afafe")
create_an_image Not yet run DCSong/CRNN-DenseNet/data_generator/generator.py
code served (permissive licence) · get_code("4a328dcfa78235f0")
create_result_subdir Not yet run kurapan/CRNN/utils.py
code served (permissive licence) · get_code("3a30552afd9800fe")
ctc_lambda_func Not yet run kurapan/CRNN/models.py
code served (permissive licence) · get_code("d58585cb2e4794d7")
cv_imread Not yet run DCSong/CRNN-DenseNet/infer.py
code served (permissive licence) · get_code("d8dedde195599807")
darken_func Not yet run DCSong/CRNN-DenseNet/data_generator/generator.py
code served (permissive licence) · get_code("6f137578ee4c9a8c")
decode_trueLabel Not yet run DCSong/CRNN-DenseNet/main_v2.py
code served (permissive licence) · get_code("62c9fb7421034e69")
elastic_transform Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/imgtocsv.py
code served (permissive licence) · get_code("913bff8998669099")
findNHFromFile Not yet run nithyadurai87/pottan-ocr-tamil/pottan_ocr/ocr.py
code served (permissive licence) · get_code("64e1f2ed134eaa53")
getTrainingTexts Not yet run harish2704/pottan-ocr/pottan_ocr/dataset.py
code served (permissive licence) · get_code("04d204671d905b25")
get_bg_value Not yet run harish2704/pottan-ocr/pottan_ocr/custom_dataset.py
code served (permissive licence) · get_code("38df7f768aeaae08")
get_crnn Not yet run xmy0916/pytorch_crnn/model/model.py
pointer only (licence: NONE) · get_code("093288b6c8663ae1")
get_learning_rate Not yet run foamliu/CRNN/utils.py
code served (permissive licence) · get_code("f12870d2ed1448f7")
get_test_data Not yet run jackknife007/crnn/cnn+lstm+ctc.py
pointer only (licence: NONE) · get_code("9d05adb33343f13f")
greedy_decode Not yet run GitYCC/crnn-pytorch/src/ctc_decoder.py
code served (permissive licence) · get_code("f056f6c91ff28c7e")
image_resize Not yet run foamliu/CRNN/data_gen.py
code served (permissive licence) · get_code("56c10a1bd102696b")
label_to_num Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/digit_train.py
code served (permissive licence) · get_code("d7024ede039d8d7a")
levenshtein Not yet run nithyadurai87/pottan-ocr-tamil/ocropy/ocrolib/edist.py
code served (permissive licence) · get_code("f50d8818f0a6b156")
loc_net Not yet run sbillburg/CRNN-with-STN/CRNN_with_STN.py
pointer only (licence: NONE) · get_code("8f9b18959fd4541f")
loc_net Not yet run kurapan/CRNN/models.py
code served (permissive licence) · get_code("c195fa75ab2456ab")
myOpen Not yet run harish2704/pottan-ocr/pottan_ocr/utils.py
code served (permissive licence) · get_code("32a5943a79da34f1")
normaizeImg Not yet run harish2704/pottan-ocr/pottan_ocr/utils.py
code served (permissive licence) · get_code("2ebd71c551e6a0af")
normaizeImg Not yet run nithyadurai87/pottan-ocr-tamil/pottan_ocr/dataset.py
code served (permissive licence) · get_code("c3a16e37a8c26936")
normalizeBatch Not yet run harish2704/pottan-ocr/pottan_ocr/utils.py
code served (permissive licence) · get_code("5b549bdb59cee992")
num_to_label Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/GUI.py
code served (permissive licence) · get_code("c71ecf200d7b47ff")
num_to_label Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/digit_train.py
code served (permissive licence) · get_code("12a7e5523e0d5c4a")
number_augment Not yet run mrzaizai2k/Information-recognition-on-the-university-test-paper/source/prepare_MSSV_dataset.py
code served (permissive licence) · get_code("c1de96bd44318dd0")

Showing the first 60. An agent gets every one from get_harvested_code_for_paper("1507.05717").

Repositories linked to this paper

More are linked than shown here.

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1507.05717")
get_code_for_paper("1507.05717")
have("1507.05717")

Connect an agent — have() is free.