Papers › EMNIST: an extension of MNIST to handwritten letters

EMNIST: an extension of MNIST to handwritten letters

17 Feb 2017arXiv:1702.05373archive 2025-07-28

Gregory Cohen, Saeed Afshar, Jonathan Tapson, André van Schaik

The MNIST dataset has become a standard benchmark for learning, classification and computer vision systems. Contributing to its widespread adoption are the understandable and intuitive nature of the task, its relatively small size and storage requirements and the accessibility and ease-of-use of the database itself. The MNIST database was derived from a larger dataset known as the NIST Special Database 19 which contains digits, uppercase and lowercase handwritten letters. This paper introduces a variant of the full NIST dataset, which we have called Extended MNIST (EMNIST), which follows the same conversion paradigm used to create the MNIST dataset. The result is a set of datasets that constitute a more challenging classification tasks involving letters and digits, and that shares the same image structure and parameters as the original MNIST task, allowing for direct compatibility with all existing classifiers and systems. Benchmark results are presented along with a validation of the conversion process through the comparison of the classification results on converted NIST digits and the MNIST digits.

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 14 code samples harvested from 3 repositories linked to this paper: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 14 samples from 3 repositories, 13 ran (13 with no instrument failure; 0 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.

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.

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

Chizuchizu/amplify-hackathon mentioned on GitHubpytorchMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
CottonBall811/English-Alphabet-OCR mentioned on GitHubSyntology: not harvested report
JPDaly/MultilayerPerceptron mentioned on GitHubSyntology: not harvested report
JustRodneyLee/ML101-OCR mentioned on GitHubGPL-3.0Syntology: not harvested report
Lornatang/TensorFlow-MNIST mentioned on GitHubtfApache-2.0Syntology: 10 samples, 9 ran (0 instrument-failed) · 1 unverified report
NikhilVanapalli/Gesture-Recognition-for-HCI mentioned on GitHubtfSyntology: not harvested report
Sharron4me/EMNIST-Prediction-Model mentioned on GitHubSyntology: not harvested report
Whole-Brain/mnist-reader mentioned on GitHubMITSyntology: not harvested report
adipro7/Handwritten-Captcha-Recognition mentioned on GitHubtfSyntology: not harvested report
ajlee19/GestureKeyboard mentioned on GitHubSyntology: not harvested report
andrewbespaly/canvas_character_recognition mentioned on GitHubtfSyntology: not harvested report
astridrou/fiveLetterClassification mentioned on GitHubtfSyntology: not harvested report
austin-hill/EMNIST-CNN mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
bnjobam/EMNIST-analysis mentioned on GitHubtfSyntology: not harvested report
christianversloot/extra_keras_datasets mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
chuiyunjun/projectCSC413 mentioned on GitHubSyntology: not harvested report
compSciKai/CMPT414-Term-Project-Tensorflow-OCR mentioned on GitHubtfSyntology: not harvested report
henriquemeloo/psi3571-handwriting-recognition mentioned on GitHubSyntology: not harvested report
hosford42/EMNIST mentioned on GitHubNOASSERTIONSyntology: not harvested report
jamilruet13/bangla-english-handwritten-digit-recognition-cnn mentioned on GitHubSyntology: not harvested report
minhduchoang301/AmsText-OCR--website mentioned on GitHubtfSyntology: not harvested report
minhduchoang301/OCR-community-website mentioned on GitHubtfSyntology: not harvested report
mohitiitb/DummyRepo mentioned on GitHubtfSyntology: not harvested report
mohitiitb/NeuralNetworkVerification_GlobalRobustness mentioned on GitHubtfSyntology: not harvested report
rlh1994/cw_wame_optimiser_cnn mentioned on GitHubtfSyntology: not harvested report
sequedakarina/reconocimiento-de-caracteres-y-reproduccion-de-voz mentioned on GitHubSyntology: not harvested report
shivang2k/CharacterClassifier mentioned on GitHubtfSyntology: not harvested report
spikeeSakshu/CharacterRecognition mentioned on GitHubnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
zmr1128/EMNIST mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 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.

Code Syntology ran Syntology

14 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 1 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
12ran
1unverified

Licence: 1 of the 14 samples is 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 3 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.

Chizuchizu/amplify-hackathon community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
get_weight in 21 papers src/utils.py ran fingerprinted MIT (permissive) · 6eee3173de8e2ce0 · report fixture: signature w:list/1/int, k:int/0/int · returned int · level recorded 2026-09-26
minmax in 12 papers src/utils.py ran fingerprinted MIT (permissive) · 49fda2edf096ba10 · report fixture: signature x:Tensor/1/float · returned Tensor · level recorded 2026-09-26
standardization in 8 papers src/utils.py ran fingerprinted MIT (permissive) · 2dc8b2021e28ec53 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-26
Lornatang/TensorFlow-MNIST community (archive-listed) 10 samples, 9 ran (0 instrument-failed) · 1 unverified
AlexNet in 8 papers v0_2/models.py ran Apache-2.0 (permissive) · 083164bfbeb0d9ca · report fixture: signature include_top:bool/0/bool, input_tensor:NoneType/0/?, input_shape:tuple/1/int, pooling:NoneType/0/?, classes:int/0/int · returned Functional · level recorded 2026-09-26
AlexNet in 8 papers v0_1/models/alexnet.py ran Apache-2.0 (permissive) · 5aca9cbf66d5ea31 · report fixture: signature include_top:bool/0/bool, input_tensor:NoneType/0/?, input_shape:tuple/1/int, pooling:NoneType/0/?, classes:int/0/int · returned Functional · level recorded 2026-09-26
CNN in 23 papers v0_2/models.py ran Apache-2.0 (permissive) · 640fbef861b1331b · report fixture: signature include_top:bool/0/bool, input_tensor:NoneType/0/?, input_shape:tuple/1/int, pooling:NoneType/0/?, classes:int/0/int · returned Functional · level recorded 2026-09-26
LeNet in 5 papers v0_2/models.py ran Apache-2.0 (permissive) · 95aaaa71dd002c63 · report fixture: signature include_top:bool/0/bool, input_tensor:NoneType/0/?, input_shape:tuple/1/int, pooling:NoneType/0/?, classes:int/0/int · returned Functional · level recorded 2026-09-26
VGG16 in 7 papers v0_1/models/vgg16.py ran Apache-2.0 (permissive) · ce11fac8cedd9a15 · report fixture: returned Functional · level recorded 2026-09-26
VGG19 in 6 papers v0_1/models/vgg19.py ran Apache-2.0 (permissive) · d3303b2b9b7cd348 · report fixture: signature include_top:bool/0/bool, input_tensor:NoneType/0/?, input_shape:tuple/1/int, pooling:NoneType/0/?, classes:int/0/int · returned Functional · level recorded 2026-09-26
process_image in 43 papers v0_2/dataset.py ran Apache-2.0 (permissive) · 8f4ab24d39a5686c · report fixture: signature image:EagerTensor/4/float, label:EagerTensor/1/int, height:int/0/int, width:int/0/int · returned tuple · level recorded 2026-09-26
process_image_with_kmnist v0_1/datasets/kmnist.py ran Apache-2.0 (permissive) · 32796d02041ad8bf · report fixture: signature image:EagerTensor/4/int, label:EagerTensor/1/int, height:int/0/int, width:int/0/int · returned tuple · level recorded 2026-09-26
process_image_with_mnist v0_1/datasets/mnist.py ran Apache-2.0 (permissive) · 9cbd84255dff2fe5 · report fixture: signature image:EagerTensor/4/int, label:EagerTensor/1/int, height:int/0/int, width:int/0/int · returned tuple · level recorded 2026-09-26
process_image_with_emnist v0_1/datasets/emnist.py unverified Apache-2.0 (permissive) · 20087ccac441201c · report
zmr1128/EMNIST community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
rotate in 56 papers emnist.py ran · honoured contract fingerprinted no licence file found · pointer only · c905d83a8c7c8cfe · report fixture: signature image:ndarray/2/float · returned ndarray · level recorded 2026-09-22

Tasks

General ClassificationImage Classification

Datasets

Introduced by this paper, per the archive.

EMNIST

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification EMNIST-Balanced OPIUM Classifier Accuracy 78.94 #18 of 20 Archive leaderboard report
Image Classification EMNIST-Balanced Linear Classifier Accuracy 50.93 #20 of 20 Archive leaderboard report
Image Classification EMNIST-Digits OPIUM Classifier Accuracy (%) 96.30 #6 of 7 Archive leaderboard report
Image Classification EMNIST-Digits Linear Classifier Accuracy (%) 84.70 #7 of 7 Archive leaderboard report
Image Classification EMNIST-Letters OPIUM Classifier Accuracy 85.27 #10 of 11 Archive leaderboard report
Image Classification EMNIST-Letters Linear Classifier Accuracy 55.78 #11 of 11 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