Ocean-OCR: Towards General OCR Application via a Vision-Language Model

TL;DR

Ocean-OCR is a large multimodal language model specifically designed to excel in various optical character recognition tasks, outperforming existing OCR models and demonstrating versatile understanding across multiple text-related scenarios.

Contribution

This paper introduces Ocean-OCR, a 3-billion parameter vision-language model with state-of-the-art OCR performance and broad applicability to general understanding tasks.

Findings

Outperforms professional OCR models like TextIn and PaddleOCR

Excels in document understanding, scene text, and handwritten recognition

Demonstrates robust OCR capabilities across diverse scenarios

Abstract

Multimodal large language models (MLLMs) have shown impressive capabilities across various domains, excelling in processing and understanding information from multiple modalities. Despite the rapid progress made previously, insufficient OCR ability hinders MLLMs from excelling in text-related tasks. In this paper, we present \textbf{Ocean-OCR}, a 3B MLLM with state-of-the-art performance on various OCR scenarios and comparable understanding ability on general tasks. We employ Native Resolution ViT to enable variable resolution input and utilize a substantial collection of high-quality OCR datasets to enhance the model performance. We demonstrate the superiority of Ocean-OCR through comprehensive experiments on open-source OCR benchmarks and across various OCR scenarios. These scenarios encompass document understanding, scene text recognition, and handwritten recognition, highlighting the robust OCR capabilities of Ocean-OCR. Note that Ocean-OCR is the first MLLM to outperform professional OCR models such as TextIn and PaddleOCR.