A Novel Swarm-Based Hybridization of Puma Optimizer and Crested Porcupine Algorithm for Complex Handwriting Recognition in Writer Identification
Bibliographic record
Abstract
Accurate handwriting recognition is a challenging problem, owing to variability in handwriting styles, distortions in writing patterns, and noise in handwritten documents.These challenges are even more severe in scripts like Devanagari and Arabic, which have complex character forms and high visual similarity among classes, requiring strong feature extraction and semantic knowledge.To address these challenges, we have developed a novel deep-learning-based handwriting recognition system that preserves the intrinsic writing dynamics and recognizes hierarchical spatial cues through multilevel abstraction and attention-driven encoding.Our framework synergistically integrates a Residual Abstraction Block, Spatial Context Encoder, Spatial Attention Generator, and Hierarchical Capsule Encoding Block to capture fine-grained spatial dependencies and contextual semantics efficiently.To further improve efficiency, we propose a hybrid puma-crested porcupine optimizer for Feature Reduction (FR), which significantly reduces the model's complexity without compromising accuracy.Extensive experiments on the Devanagari and KHATT datasets prove the effectiveness of our method.Our proposed model achieves superior recognition accuracy of 98.94% (with FR) and 93.28% (without FR) on Devanagari, and 97.36% (with FR) and 91.91% (without FR) on KHATT, outperforming various baseline methods.These findings demonstrate the robustness of our architecture in achieving high accuracy, compactness, and resilience.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".