Comparative Study Based on De-Occlusion and Reconstruction of Face Images in Degraded Conditions
Bibliographic record
Abstract
In the recent years, the face recognition task has attracted the attention of researchers due to its efficiency in several domains such as surveillance and access control. Unfortunately, there are multiple challenges that decrease the performance of face recognition. Partial occlusion is the most challenging one since it often causes a great lack of information. The main purpose of this paper is to prove that facial reconstruction improves the results of facial recognition compared to de-occlusion and full-face recognition in the presence of occlusion. Our objective is to achieve occluded-face recognition, de-occluded-face recognition, and reconstructed-face recognition. Regarding face reconstruction, we introduce two different methods based on Laplacian pyramid blending and CycleGANs. In order to validate our work, we perform two different feature extraction techniques: hand-crafted features and learned features exploiting the final layers of a pre-trained deep architecture model. The experimental results on the EURECOM Kinect Face Dataset (EKFD) and the IST-EURECOM Light Field Face Database (IST-EURECOM LFFD) show that the proposed face reconstruction approach, compared with the face de-occlusion and occluded-face recognition ones, clearly improves the face recognition task. Our method boosts the classification performance in comparison with the state-of-the-art methods, achieving 94.66% on EKFD and 72.35% on IST-EURECOM LFFD.
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 | 0.001 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".