Enhancing Human Authentication with a Hybrid Deep Learning-Based Palm Fusion Model Utilizing RGB Images
Bibliographic record
Abstract
Multimodal biometric systems are gaining significant interest for their performance advantages over single-modal systems. Palm print and palm vein biometrics are particularly popular due to their high accuracy, resilience, and user-friendliness in human recognition. Additionally, their simultaneous acquisition and shared recognition algorithms make them ideal for fusion-based recognition. Much of the prior research in palm fusion has primarily concentrated on extracting features from palm print and palm vein using Near Infrared images. Furthermore, the majority of palm fusion architectures have employed distinct fusion modes, overlooking the potential benefits of integrating fusion levels. This paper presents a novel approach in palm fusion utilizing RGB images by combining the Saturation, Red, Green, and Blue channels. We introduce the Mobile Palm Fusion Net (MPFNet), a hybrid deep learning model that seamlessly integrates feature and score level fusion within a single architecture, leading to enhanced overall recognition performance. We extensively evaluate the proposed method using six publicly available palm databases and ensure its ease of reproducibility for future research comparisons. The results demonstrate that our MPFNet model surpasses the performance of the compared related methods, exhibiting a lower Equal Error Rate and a more compact size.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| 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) | 0.002 | 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".