MétaCan
Menu
Back to cohort

Real-Time Defect Classification at the Edge: A Lightweight CNN Approach for Industrial-Scale Applications

2025· article· W7140311245 on OpenAlexaff
Yuanyuan Liu, Xiaoxue Yang, Haijiang Li, J. Christina Wang

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicAdvanced Neural Network Applications
Canadian institutions123 Certification (Canada)
Fundersnot available
KeywordsFeature (linguistics)Pattern recognition (psychology)Noise (video)Convolutional neural networkIdentification (biology)

Abstract

fetched live from OpenAlex

We introduce a lightweight CNN-based framework for real-time classification of surface defects and efficient deployment on industrial edge devices. The method was evaluated on the NEU-CLS dataset using several compact convolutional architectures. The GhostNet-based variant delivered the most balanced performance across accuracy, efficiency, and inference speed. For practical validation, the trained model was exported to ONNX format and deployed on a Raspberry Pi 4B, achieving stable real-time inference with hardware costs under 100 USD. The deployment workflow integrates preprocessing, streamlined inference, and result output, making it suitable for quality control scenarios. Visual outcomes and classification consistency across multiple defect types demonstrate the model's generalization and reliability. Designed for resource-constrained environments, this solution offers a deployable path toward high-precision defect recognition in embedded industrial applications.

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: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.011

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0020.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0020.001

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 head0.043
GPT teacher head0.291
Teacher spread0.248 · 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 designSimulation or modeling
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
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicAdvanced Neural Network ApplicationsFrench-language works237,207