A Robust Framework for 2D Human Face Reconstruction from Half-Frontal Views in Low-Quality Surveillance Footage
Bibliographic record
Abstract
This paper proposes a robust framework for reconstructing 2D human facial images from half-frontal views, primarily captured under low-quality surveillance conditions. A custom MATLAB-based Graphical User Interface (GUI) is developed to support the complete pipeline, including frame extraction, enhancement, and face reconstruction. Representative frames are extracted and enhanced for video inputs using one of three techniques: histogram equalization, contrast stretching, or logarithmic transformation. Reconstruction involves detecting a single eye from the half-frontal image, followed by horizontal flipping and concatenation to generate a symmetric full-frontal face. The reconstructed faces are validated using the Viola-Jones object detection algorithm to confirm the presence and alignment of facial features. Quantitative evaluation uses the Structural Similarity Index (SSIM) and Jaccard Index (JI) to measure image quality and geometric accuracy. The proposed method is tested on publicly available datasets and a custom-designed dataset reflecting real-world surveillance challenges such as low resolution and poor illumination. Experimental results demonstrate that the framework delivers accurate and visually coherent reconstructions with low computational overhead, making it suitable for real-time surveillance and facial analysis applications.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".