MétaCan
Menu
Back to cohort
Record W4394938787 · doi:10.5267/j.ijdns.2024.3.015

Integrated multi-layer perceptron neural network and novel feature extraction for handwritten Arabic recognition

2024· article· en· W4394938787 on OpenAlex
Husam Ahmad Al Hamad, Mohammad Shehab

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

venuePublished in a venue whose home country is Canada.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueInternational Journal of Data and Network Science · 2024
Typearticle
Languageen
FieldComputer Science
TopicHandwritten Text Recognition Techniques
Canadian institutionsnot available
Fundersnot available
KeywordsComputer scienceArabicArtificial intelligencePattern recognition (psychology)Artificial neural networkFeature extractionPerceptronLayer (electronics)Feature (linguistics)Multilayer perceptronSpeech recognitionNatural language processingChemistryLinguistics

Abstract

fetched live from OpenAlex

Arabic handwritten script recognition presents an energetic area of study. These types of recognitions face several obstacles, such as vast open databases, boundless diversity in individuals' penmanship, and freestyle writing. Thus, Arabic handwriting requires effective techniques to achieve better recognition results. On the other hand, Multilayer Perceptron (MLP) is one of the most common Artificial Neural Networks (ANNs) which deals with various problems efficiently. Therefore, this study introduces a new technique called Block Density and Location Feature (BDLF) with MLP, namely BDLF-MLP, which aims to extract novel features from letter images and estimate the letter's pixel density and its location for each equal-sized block in the image. In other words, BDLF-MLP can deal with various styles of Arabic handwritten, such as overlapping letters. The BDLF-MLP starts with the Block Feature Extraction (BFE) of the image by dividing the image into sixteen parts. After that, it calculates the density and location of each block (i.e., BDLF) by finding the sum of all values inside blocks. Finally, it determines the position of the greatest pixel density to obtain better recognition accuracy. The dataset containing 720 images is used to evaluate the efficiency of the proposed technique. Also, 1440 letters are used for training and testing divided evenly between them. The experiment results illustrate that BDLF-MLP outperformed the other algorithms in the literature with an accuracy of 97.26 %.

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.

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)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.974
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0010.005
Open science0.0010.000
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 head0.070
GPT teacher head0.351
Teacher spread0.282 · 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