Hybrid Fingerprint Classification Using Deep Learning and Sobel Feature Fusion
Bibliographic record
Abstract
Fingerprint classification serves as a critical preprocessing step in biometric and forensic identification systems. By categorizing fingerprints into distinct types, such as Thumb, Index, Middle, Ring, and Little, the process significantly reduces the search space, thereby enhancing the efficiency, speed, and accuracy of matching algorithms. This is particularly valuable in large-scale identification tasks and law enforcement applications. However, achieving accurate classification remains challenging due to high visual similarity between classes, intra-class variability, and imbalanced datasets. In this study, we present a hybrid fingerprint classification framework, which combines deep learning-based embeddings with handcrafted Sobel edge features to improve both model robustness and interpretability. Three state-of-the-art architectures-EfficientNet: B0, ResNet50, and Vision Transformer (ViT-B/16), were employed to extract semantic feature representations, which were fused with Sobel-based statistical edge descriptors. The models were trained and evaluated on the SOCOFing dataset using a stratified 70-1515 split, with class imbalance addressed via oversampling using WeightedRandomSampler. EfficientNet-B0 achieved the best performance, with a test accuracy of 99.19%, F 1 -score of 99.18%, and recall of 99.19%. The models' reliability and precision across fingerprint classes were further validated through confusion matrix analysis and visual prediction results, demonstrating the effectiveness of the proposed hybrid approach for fine-grained fingerprint classification.
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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".