MétaCan
Menu
Back to cohort

Face Anti-Spoofing Framework Based on Optical Flow Field Texture Analysis

2024· article· en· W4407784647 on OpenAlexaff
Md. Yasin Polok, Mostofa Kafur Hossain Alvee, Fatema Rahman Moni, Md Shopon, Tahira Alam, Md. Abdul Karim

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicBiometric Identification and Security
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsComputer scienceOptical flowTexture (cosmology)Face (sociological concept)Field (mathematics)Artificial intelligenceComputer visionSpoofing attackFlow (mathematics)Computer securityImage (mathematics)MathematicsGeometry

Abstract

fetched live from OpenAlex

Deep learning is used to tackle a wide range of real-world problems. Face anti-spoofing is one of them which refers to the process of stopping fraudulent facial verification by substituting a mask, image, video, or other image to authorize individuals. Face anti-spoofing is important to prevent print and replay attacks that pose a significant danger to facial recognition systems. Numerous algorithms have been suggested to prevent such fraud. However, they showed poor accuracy. Therefore, we developed a detection method to detect facial movement and texture signals. The optical flows of a continuous video clip were extracted and analyzed for the movement's amplitude and direction. Next, the video frames were concatenated with the recovered optical flows as the network's input. To distribute the classification weights in an adaptable manner, region, and channel attention techniques were concurrently introduced. Finally, the combined motion and texture cues were sent into a convolutional network to extract features and determine whether the input video sequence represented a real face or not. Experimental results showed that the method showed high accuracy in detecting fraud.

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 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: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.979
Threshold uncertainty score0.656

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.006
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0010.000

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 head0.014
GPT teacher head0.282
Teacher spread0.267 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicBiometric Identification and SecurityFrench-language works237,207