Facial Expression Recognition under Difficult Conditions: A Comprehensive Study on Edge Directional Texture Patterns
Bibliographic record
Abstract
Abstract In recent years, research in automated facial expression recognition has attained significant attention for its potential applicability in human-computer interaction, surveillance systems, animation, and consumer electronics. However, recognition in uncontrolled environments under the presence of illumination and pose variations, low-resolution video, occlusion, and random noise is still a challenging research problem. In this paper, we investigate recognition of facial expression in difficult conditions by means of an effective facial feature descriptor, namely the directional ternary pattern (DTP). Given a face image, the DTP operator describes the facial feature by quantizing the eight-directional edge response values, capturing essential texture properties, such as presence of edges, corners, points, lines, etc. We also present an enhancement of the basic DTP encoding method, namely the compressed DTP (cDTP) that can describe the local texture more effectively with fewer features. The recognition performances of the proposed DTP and cDTP descriptors are evaluated using the Cohn-Kanade (CK) and the Japanese female facial expression (JAFFE) database. In our experiments, we simulate difficult conditions using original database images with lighting variations, low-resolution images obtained by down-sampling the original, and images corrupted with Gaussian noise. In all cases, the proposed method outperforms some of the well-known face feature descriptors.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".