MétaCan
Menu
Back to cohort
Record W4309355783 · doi:10.1002/9781119861850.ch10

Smart Text Reader System for People who are Blind Using Machine and Deep Learning

2022· other· en· W4309355783 on OpenAlexaff
Zobeir Raisi, Mohamed A. Naiel, Georges Younes, Paul Fieguth, John Zelek

Bibliographic record

Venuenot available
Typeother
Languageen
FieldComputer Science
TopicHandwritten Text Recognition Techniques
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsVariety (cybernetics)Artificial intelligenceSightComputer scienceField (mathematics)ParsingDeep learningData sciencePopulationAutomationBenchmark (surveying)Everyday lifeMachine learningHuman–computer interactionEngineeringCartographyGeographyMedicine

Abstract

fetched live from OpenAlex

The World Health Organization (WHO) estimates that more than one-sixth of the world's population suffers from some form of visual impairment worldwide. With such a large number of people affected by vision issues, several breakthroughs in technology, both on the hardware and software sides, are needed to make a positive impact and improve the quality of life for blind and sight-impaired people. In particular, the ability to parse text from their surrounding is a crucial aspect that can empower blind people to become active members of society and help them lead an everyday life. Detection and recognition of text in natural images are two significant problems in the field of computer vision, having a wide variety of applications in the analysis of sports videos, autonomous driving, and industrial automation, to name a few, with challenges based on how text is represented and affected by environmental conditions. The current state-of-the-art in text detection and/or recognition has exploited advancements in deep learning and has reported a superior accuracy on benchmark datasets when tackling multi-resolution and multi-oriented text, however, there still remain challenges affecting text in the wild images that cause existing methods to underperform due to models not able to generalize to unseen data from insufficient labeled data. The objectives of this survey chapter are as follows. First, offering the reader not only a review of recent advancements in scene text detection and recognition, but also the results of extensive experiments using a unified evaluation framework that assesses pre-trained models of the selected methods on challenging cases, with the application of consistent evaluation criteria. Second, identifying several existing challenges for detecting or recognizing text in the wild images, namely, in-plane-rotation, multi-oriented and multi-resolution text, perspective distortion, illumination reflection, partial occlusion, complex fonts, and special characters. Finally, the chapter offers insights into potential research directions to address current challenges encountered by scene text detection and recognition techniques.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.016
Threshold uncertainty score0.055

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0010.002
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0160.016

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 head0.022
GPT teacher head0.261
Teacher spread0.239 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

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
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicHandwritten Text Recognition TechniquesFrench-language works237,207