MétaCan
Menu
Back to cohort
Record W2087975376 · doi:10.1109/icecs.2011.6122385

Image processing technique for segmenting microstructural porosity of laser-welded thermoplastics

2011· article· en· W2087975376 on OpenAlex
Karl Leboeuf, Iman Makaremi, Roberto Muscedere, Majid Ahmadi

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicIndustrial Vision Systems and Defect Detection
Canadian institutionsUniversity of Windsor
Fundersnot available
KeywordsWeldingMaterials sciencePixelPorosityThermoplasticImage segmentationProcess (computing)Image processingNoise (video)SegmentationLaserComposite materialMicrostructureComputer scienceArtificial intelligenceImage (mathematics)Optics

Abstract

fetched live from OpenAlex

Plastics are used in a truly vast number of applications, and research is continously carried out to improve every aspect of the plastics industry. A recent study of laser transmission welding [1] required cross-sectional images of the weld's microstructure to be analyzed for the presence of pores, which are tiny bubbles that may form during the weld process. It is believed that the number and size of pores may be indicative of the weld strength [1]. The current state of the art for detecting these pores involves manually drawing a contour around each one; a laborious process given that a typical sample may have hundreds-to-thousands of pores. This paper presents a segmentation system for classifying the pixels of a microstructural image of a thermoplastic laser weld as either belonging to a pore or the background. The algorithm is robust in terms of dealing with noise from flbreglass strands, cloudy pores, and varying exposure time. On average, it is estimated that the proposed algorithm is able to correctly classify pores at a rate of approximately 90% without requiring any user intervention.

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)0.000
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: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.342
Threshold uncertainty score0.313

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
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 head0.023
GPT teacher head0.229
Teacher spread0.206 · 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