Papers › Detecting Text in Natural Image with Connectionist Text Proposal Network

Detecting Text in Natural Image with Connectionist Text Proposal Network

12 Sep 2016arXiv:1609.03605archive 2025-07-28

Zhi Tian, Weilin Huang, Tong He, Pan He, Yu Qiao

We propose a novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image. The CTPN detects a text line in a sequence of fine-scale text proposals directly in convolutional feature maps. We develop a vertical anchor mechanism that jointly predicts location and text/non-text score of each fixed-width proposal, considerably improving localization accuracy. The sequential proposals are naturally connected by a recurrent neural network, which is seamlessly incorporated into the convolutional network, resulting in an end-to-end trainable model. This allows the CTPN to explore rich context information of image, making it powerful to detect extremely ambiguous text. The CTPN works reliably on multi-scale and multi- language text without further post-processing, departing from previous bottom-up methods requiring multi-step post-processing. It achieves 0.88 and 0.61 F-measure on the ICDAR 2013 and 2015 benchmarks, surpass- ing recent results [8, 35] by a large margin. The CTPN is computationally efficient with 0:14s/image, by using the very deep VGG16 model [27]. Online demo is available at: http://textdet.com/.

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 35 code samples harvested from 8 repositories linked to this paper: 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. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 35 samples from 8 repositories, 30 ran (27 with no instrument failure; 3 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

CrazySummerday/ctpn.pytorch mentioned on GitHubpytorchMITSyntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
HangZhouShuChengKeJi/text-detection-ctpn mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
JingJLiu/ICDAR2019.github.io mentioned on GitHubSyntology: not harvested report
Sanster/tf_ctpn mentioned on GitHubtfMITSyntology: 13 samples, 11 ran (2 instrument-failed) · 2 unverified report
Walleclipse/ChineseAddress_OCR mentioned on GitHubSyntology: not harvested report
alorozco53/text-detection-ctpn mentioned on GitHubtfMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
aravindvenu7/Handwritten-Character-Recognition mentioned on GitHubSyntology: not harvested report
courao/ocr.pytorch mentioned on GitHubpytorchMITSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
eragonruan/text-detection-ctpn mentioned on GitHubtfMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
eric4421/MTWI-2018 mentioned on GitHubpytorchSyntology: not harvested report
lostsword/character_recognition mentioned on GitHubmindsporeApache-2.0Syntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
opconty/pytorch_ctpn mentioned on GitHubpytorchSyntology: not harvested report
tranbahien/CTPN-TensorFlow mentioned on GitHubtfSyntology: not harvested report
yangcan2017/text-detection-ctpn mentioned on GitHubtfMITSyntology: not harvested report
yunhai0920/company-name-id mentioned on GitHubSyntology: not harvested report
zhaobomin/pytorch-ocr mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
zwenwang/CTPN_Pytorch mentioned on GitHubpytorchSyntology: not harvested report
2023-MindSpore-1/ms-code-133 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code1 mindsporeSyntology: not harvested report
2023-MindSpore-4/Code10 mindsporeSyntology: not harvested report
2024-MindSpore-1/Code4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large... (arXiv:2305.05773; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
2024-MindSpore-1/Code4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DeepTextMark: A Deep Learning-Driven Text Watermarking Approach for Identifying Large... (arXiv:2305.05773; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
BADBADBADBOY/paddle.ctpn paddleSyntology: not harvested report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
code-implementation1/Code9 mindsporeSyntology: not harvested report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

35 samples harvested: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
1ran; the contract check could not run
23ran
5unverified

Licence: 2 of the 35 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 8 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. 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.

CrazySummerday/ctpn.pytorch community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
bbox_transfrom ctpn/utils.py ran fingerprinted MIT (permissive) · 24c53f3b46c06a72 · report fixture: signature anchors:ndarray/2/float, gtboxes:ndarray/2/float · returned ndarray · level recorded 2026-09-26
compute_iou in 68 papers ctpn/utils.py ran fingerprinted MIT (permissive) · 5dfe6dd29f57f960 · report fixture: signature anchors:ndarray/2/float, bbox:ndarray/2/float · returned ndarray · level recorded 2026-09-26
gen_anchor ctpn/utils.py ran MIT (permissive) · 1b8bcc0ce345dcea · report fixture: signature featuresize:tuple/1/int, scale:int/0/int, heights:list/1/int, widths:list/1/int · returned ndarray · level recorded 2026-09-26
readxml ctpn/dataset.py ran MIT (permissive) · 43aa0c2175ad6786 · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-26
HangZhouShuChengKeJi/text-detection-ctpn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
allowed_file in 6 papers main/web.py ran · violated contract MIT (permissive) · 9624be8c5b35939c · report fixture: signature filename:str/0/str · returned bool · level recorded 2026-09-22
Sanster/tf_ctpn community (archive-listed) 13 samples, 11 ran (2 instrument-failed) · 2 unverified
bbox_transform in 11 papers lib/model/bbox_transform.py ran fingerprinted MIT (permissive) · 84dcf978d5570762 · report fixture: signature ex_rois:ndarray/2/float, gt_rois:ndarray/2/float · returned ndarray · level recorded 2026-09-25
bbox_transform_inv in 11 papers lib/model/bbox_transform.py ran fingerprinted MIT (permissive) · db910de1a7c014bc · report fixture: signature boxes:ndarray/2/float, deltas:ndarray/2/float · returned ndarray · level recorded 2026-09-26
clip_boxes in 10 papers lib/model/bbox_transform.py ran fingerprinted MIT (permissive) · d24c99284beca7a6 · report fixture: signature boxes:ndarray/2/float, im_shape:tuple/1/int · returned ndarray · level recorded 2026-09-25
find_in_path lib/setup_cpu.py ran fingerprinted MIT (permissive) · ca14946efd571693 · report fixture: signature name:str/0/str, path:str/0/str · returned str · level recorded 2026-09-25
generate_anchors in 19 papers lib/layer_utils/generate_anchors.py ran MIT (permissive) · 1ffc760a4459d409 · report fixture: signature base_height:int/0/int, num_anchors:int/0/int, anchor_width:int/0/int, h_ratio_step:float/0/float · returned ndarray · level recorded 2026-09-26
generate_anchors_pre lib/layer_utils/generate_anchors.py ran MIT (permissive) · 782e46a465c0d3f1 · report fixture: signature height:int/0/int, width:int/0/int, feat_stride:int/0/int, num_anchors:int/0/int, anchor_width:int/0/int, anchor_h_ratio_step:float/0/float · returned tuple · level recorded 2026-09-26
parse_rec in 26 papers lib/datasets/voc_eval.py ran · our draft was wrong MIT (permissive) · 0eafc51289a49033 · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-26
unique_boxes in 21 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · 8a015c012f507631 · report fixture: signature boxes:ndarray/2/float, scale:float/0/float · returned ndarray · level recorded 2026-09-26
voc_ap in 44 papers
census: 5 implementations from 10 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind float, dtype float64 · arg 2: rank 1, kind float, dtype float64
lib/datasets/voc_eval.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) here; the stored copy is pointer only · 95c31c78be42f723 · report fixture: signature rec:ndarray/1/float, prec:ndarray/1/float, use_07_metric:bool/0/bool · returned float64 · level recorded 2026-09-22
xywh_to_xyxy in 24 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · d3e019b11b709edb · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-26
xyxy_to_xywh in 23 papers lib/datasets/ds_utils.py ran · honoured contract fingerprinted MIT (permissive) · a832e5017f504280 · report fixture: signature boxes:ndarray/2/float · returned ndarray · level recorded 2026-09-26
get_imdb in 22 papers lib/datasets/factory.py unverified MIT (permissive) · 3be9228820b46ef3 · report
voc_eval in 19 papers lib/datasets/voc_eval.py unverified MIT (permissive) · 7fc3942117603f02 · report
alorozco53/text-detection-ctpn community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
bbox_transform in 11 papers lib/fast_rcnn/bbox_transform.py ran fingerprinted MIT (permissive) · 7f1817340309b32e · report fixture: signature ex_rois:ndarray/2/float, gt_rois:ndarray/2/float · returned ndarray · level recorded 2026-09-26
bbox_transform_inv in 11 papers lib/fast_rcnn/bbox_transform.py ran fingerprinted MIT (permissive) · d49676163bce1480 · report fixture: signature boxes:ndarray/2/float, deltas:ndarray/2/float · returned ndarray · level recorded 2026-09-26
clip_boxes in 10 papers lib/text_connector/other.py ran fingerprinted MIT (permissive) · 22b228f6941b5b16 · report fixture: signature boxes:ndarray/2/float, im_shape:tuple/1/int · returned ndarray · level recorded 2026-09-26
threshold in 9 papers lib/text_connector/other.py ran fingerprinted MIT (permissive) · d11f151f0452c0a7 · report fixture: signature coords:ndarray/2/float, min_:ndarray/1/float, max_:ndarray/1/float · returned ndarray · level recorded 2026-09-26
get_imdb in 22 papers lib/datasets/factory.py unverified MIT (permissive) · e3d6d8098adf58aa · report
courao/ocr.pytorch community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
cal_iou in 8 papers detect/ctpn_utils.py ran MIT (permissive) · f2bdee89194ccb33 · report fixture: signature box1:ndarray/1/float, box1_area:float/0/float, boxes2:ndarray/2/float, boxes2_area:ndarray/1/float · returned ndarray · level recorded 2026-09-26
conv3x3 in 1,376 papers recognize/crnn.py ran MIT (permissive) · 938e4e638f594536 · report fixture: signature nIn:int/0/int, nOut:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-26
gen_anchor detect/ctpn_utils.py ran MIT (permissive) · fc27893bf6fb8354 · report fixture: signature featuresize:tuple/1/int, scale:int/0/int · returned ndarray · level recorded 2026-09-26
resize in 108 papers
census: 10 implementations from 14 papers, 5 distinct outputs across 2 buckets, one shared input per bucket
detect/ctpn_utils.py ran MIT (permissive) · 38401bcff05e1d84 · report fixture: signature image:ndarray/3/int, width:int/0/int, height:NoneType/0/?, inter:int/0/int · returned ndarray · level recorded 2026-09-26
sort_box ocr.py ran MIT (permissive) · 0bb4ac67d48f720d · report fixture: signature box:list/1/list · returned list · level recorded 2026-09-26
dumpRotateImage ocr.py unverified MIT (permissive) · a042b74b081841eb · report
eragonruan/text-detection-ctpn community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
resize_im ctpn/demo_pb.py ran MIT (permissive) · b9828f64fd08b6f3 · report fixture: signature im:ndarray/3/int, scale:int/0/int, max_scale:NoneType/0/? · returned tuple · level recorded 2026-09-26
lostsword/character_recognition community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
addZeros code/generate_dataset.py ran Apache-2.0 (permissive) · 4334c57883b372a3 · report fixture: signature s_:str/0/str · returned str · level recorded 2026-09-26
create_label code/ctpn/src/create_dataset.py ran Apache-2.0 (permissive) · 965956d702b2c2ee · report fixture: signature train_img_dir:str/0/str, train_txt_dir:str/0/str, prefix:str/0/str · returned tuple · level recorded 2026-09-26
strsort code/generate_dataset.py ran Apache-2.0 (permissive) · 74f85a99e9a1fa74 · report fixture: signature alist:list/1/str · returned list · level recorded 2026-09-26
get_char_nums code/generate_dataset.py unverified Apache-2.0 (permissive) · 6121b647865394aa · report
zhaobomin/pytorch-ocr community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
init_optimizer in 11 papers train_ctpn.py ran · our draft was wrong no licence file found · pointer only · 99b4d1927696d2e8 · report fixture: signature model:callable/0/?, lr:float/0/float · returned tuple · level recorded 2026-09-22

Tasks

Scene Text Detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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