MétaCan
Menu
Back to cohort
Record W2111484788 · doi:10.1109/rose.2011.6058545

Improving alignment of faces for recognition

2011· article· en· W2111484788 on OpenAlex

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.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicFace recognition and analysis
Canadian institutionsPolytechnique Montréal
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceArtificial intelligencePipeline (software)LandmarkFacial recognition systemFace (sociological concept)Feature extractionPattern recognition (psychology)Computer visionProcess (computing)Haar-like featuresSimilarity (geometry)Affine transformationFace detectionThree-dimensional face recognitionFeature (linguistics)Task (project management)Image (mathematics)

Abstract

fetched live from OpenAlex

Face recognition systems for uncontrolled environments often work through an alignment, feature extraction, and recognition pipeline. Effective alignment of faces is thus crucial as can be an entry point in the process and poor alignments can greatly affect recognition performance. The task of alignment is particularly difficult when a face comes from highly unconstrained environments or so called faces in the wild. A lot of recent research activity has focused on faces in the wild and even simple similarity or affine transformations have proven both effective and essential to achieving state of the art performance. In this paper we explore a straightforward, fast and effective approach to aligning faces based on detecting facial landmarks using Haar-like image features and a cascade of boosted classifiers. Our approach is reminiscent of widely used face detection approaches, but focused on much more detailed features of a face such eye centres, the nose tip and corners of the mouth. This process generates multiple candidates for each landmark and we present a fast and effective filtering strategy allowing us to find sets of landmarks that are consistent. Our experiments show that this approach can outperform contemporary methods and easily fits into popular processing pipelines for faces in the wild.

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: Other design · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.978
Threshold uncertainty score0.157

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 head0.066
GPT teacher head0.238
Teacher spread0.172 · 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

Quick stats

Citations11
Published2011
Admission routes2
Has abstractyes

Explore more

Same topicFace recognition and analysisFrench-language works237,207