The Impact of Downsampling Methods on Face Recognition in Electronic Identity Card
Bibliographic record
Abstract
Electronic identity cards have limited storage capacity, necessitating the downsizing of images to be stored. Downsampling is a method used to reduce the size of images, but it can result in the loss of essential facial features, impacting face recognition performance. Therefore, the selection of an appropriate downsampling method becomes crucial. In this study, we evaluated and compared the face recognition performance of five different downsampling methods, such as Bicubic Interpolation, Bilinear Interpolation, Lanczos Interpolation, Nearest Neighbour, and Inter-Area using the Asian Face Image Database PF01. We measured the face recognition performance using False Rejection Rate (FRR) at various levels of False Acceptance Rate (FAR). Nearest Neighbour had consistently demonstrated the lowest performance across various scenarios, making it unsuitable for downsampling. In contrast, Bicubic Interpolation has consistently outperformed other methods and is favored for downsampling. In cases where downsizing to a much lower size is required, Lanczos Interpolation offers a preferable option. Our experimental results revealed that the choice of the downsampling method significantly influenced face recognition performance up to 8.41% at specific FAR values. This study highlights the critical importance of selecting the right downsampling method to preserve essential facial features, ensuring optimal face recognition performance for electronic identity cards.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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 source (direct Gemma or distilled Codex), 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".