Handwriting Recognition in Historical Documents with Multimodal LLM
This addresses the challenge of digitizing handwritten manuscripts for cultural preservation, though it is incremental as it compares existing methods rather than introducing a new approach.
The paper tackles the problem of handwriting recognition in historical documents by evaluating the accuracy of transcriptions generated by the multimodal LLM Gemini against state-of-the-art Transformer-based methods, finding that Gemini achieves competitive performance with fewer training data requirements.
There is an immense quantity of historical and cultural documentation that exists only as handwritten manuscripts. At the same time, performing OCR across scripts and different handwriting styles has proven to be an enormously difficult problem relative to the process of digitizing print. While recent Transformer based models have achieved relatively strong performance, they rely heavily on manually transcribed training data and have difficulty generalizing across writers. Multimodal LLM, such as GPT-4v and Gemini, have demonstrated effectiveness in performing OCR and computer vision tasks with few shot prompting. In this paper, I evaluate the accuracy of handwritten document transcriptions generated by Gemini against the current state of the art Transformer based methods. Keywords: Optical Character Recognition, Multimodal Language Models, Cultural Preservation, Mass digitization, Handwriting Recognitio