The Histogram of Enhanced Gradients (HEG) - A Fast Descriptor for Noisy Face Recognition
Bibliographic record
Abstract
Descriptors serve as algorithms responsible for the representation and processing of multimedia files.One of the main challenges in these algorithms involves establishing a tradeoff among conflicting performance requirements such runtime, on the one hand, and standard metrics such as accuracy, precision, recall and F-score, on the other hand.To address this challenge, a novel descriptor named Histogram of Enhanced Gradients (HEG) is introduced for noisy face recognition.The methodology behind HEG involves enhancing local gradients prior to feature extraction, corroborated by the Histogram of Oriented Gradients (HOG) descriptor and adaptive filtering.Initially, facial images are divided into blocks, and features are extracted from each block using magnitude and orientation maps to discriminate between edges, details, and flat regions.Then, these features undergo denoising with an adaptive anisotropic diffusion filter, individually customized for each of these three types.Subsequently, the enhanced histograms from the blocks are concatenated to create a comprehensive feature vector representing the original noisy face image.Finally, the HEG descriptor is integrated within a supervised machine learning scheme with a Support Vector Machine as the classifier.The proposed descriptor is evaluated not only in terms of runtime and the standard metrics cited above, but also on the basis of six other similarity metrics, across three online datasets.Experimental results, conducted under different noise levels, clearly demonstrate that the HEG descriptor outperforms nine stateof-the-art descriptors on all three datasets yielding significant enhancements in runtime efficiency, with speed improvements ranging from 1.64 to 29.56 times, and notable refinements in F-score, ranging from 1.03 to 2.39 times.These results highlight the effectiveness of the HEG descriptor in capturing facial features from multimedia noisy files.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".