Efficient adaptive face recognition systems based on capture conditions
Bibliographic record
Abstract
In many face recognition (FR) applications, changing capture conditions lead to divergence between facial models stored during enrollment and faces captured during operations. Moreover, it is often costly or infeasible to capture several high quality reference samples a priori to design representative facial models. Although self-updating models using high-confidence face captures appear promising, they raise several challenges when capture conditions change. In particular, face models of individuals may be corrupted by misclassified input captures, and their growth may require pruning to bound system complexity over time. This paper presents a system for self-update of facial models that exploits changes in capture conditions to assure the relevance of templates and to limit the growth of template galleries. The set of reference templates (facial model) of an individual is only updated to include new faces that are captured under significantly different conditions. In a particular implementation of this system, illumination changes are detected in order to select face captures from bio-login to be stored in a gallery. Face captures from a built-in still or video camera are taken at periodic intervals to authenticate the user having accessed a secured computer or network. Experimental results produced with the DIEE dataset show that the proposed system provides a comparable level of performance to the FR system that self-updates the gallery on all high-confidence face captures, but with significantly lower complexity, i.e., number of templates per individual.
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
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".