TibOCR-Bench: A Comprehensive Benchmark and Training Pipeline for Tibetan Multimodal OCR

To effectively support the training and evaluation of Tibetan OCR models in practical application scenarios involving multiple fonts and complex text structures, we have constructed a multi-source, high-quality Tibetan text image dataset. The overall data construction includes two complementary strategies: forward construction and reverse construction. (1) Positive construction: Firstly, collect Tibetan language images in real scenes, and then manually annotate the corresponding text content. This method ensures the authenticity and practical relevance of the data, effectively covering the diverse language usage scenarios and inherent complexity in Tibetan OCR tasks. (2) Reverse construction: Firstly, select text content suitable for OCR tasks (such as advertising slogans, slogans, or standard documents), then choose appropriate background images and use multiple fonts and visual effects to synthesize the text image dataset. This method efficiently enhances the structural diversity and scale of the dataset. These two strategies complement each other and together form a comprehensive resource library for training and evaluating Tibetan OCR models.