MétaCan
Menu
Back to cohort

Multi-Character Recognition using EMNIST

2018· article· en· W2868811703 on OpenAlexaff
Shobhit Maheshwari, Rddhima Raghunand

Bibliographic record

VenueJIMS8I - International Journal of Information Communication and Computing Technology · 2018
Typearticle
Languageen
FieldComputer Science
TopicHandwritten Text Recognition Techniques
Canadian institutionsInnovation Cluster (Canada)
Fundersnot available
KeywordsCharacter (mathematics)Character recognitionComputer scienceArtificial intelligenceNatural language processingPattern recognition (psychology)PsychologyMathematicsGeometry

Abstract

fetched live from OpenAlex

In this paper, we present a model for handwritten multiple-character recognition. This model consists of a classifier which recognizes an individual character, and a series of image processing algorithms that extract individual character regions from a given image and feed it to the classifier. We make use of a Convolutional Neural Network (CNN)-a state-of-the-art solution to object recognition-for the task of classification, and train it on the recently published Extended MNIST (EMNIST) dataset, achieving an accuracy close to 90%. We then make use of Canny Edge Detection and dilation to segment the given image and feed it to the aforementioned classifier. The EMNIST dataset has the potential to become a standard benchmark in computer vision systems, however, limited literature on this dataset has been published as of now. Hence this paper seeks to further validate the dataset and give an indication of the potential performance achievable using the same.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.981
Threshold uncertainty score0.474

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.002
Open science0.0010.001
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.029
GPT teacher head0.309
Teacher spread0.280 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2018
Admission routes1
Has abstractyes

Explore more

Same venueJIMS8I - International Journal of Information Communication and Computing TechnologySame topicHandwritten Text Recognition TechniquesFrench-language works237,207