Researchers have developed a Convolutional Neural Network (CNN) with attention mechanisms to identify writers of historical Arabic manuscripts. The study, using the Muharaf dataset, expanded writer labels and established new baselines for writer identification under both line-level and page-disjoint evaluation protocols. The CNN model achieved high accuracy on line-level identification, demonstrating its potential for historical analysis and manuscript provenance. AI
影响 Provides a new benchmark and practical resource for historical document analysis and writer identification.
排序理由 Academic paper detailing a new model and dataset evaluation for writer identification.
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
