RFL: Simplifying Chemical Structure Recognition with Ring-Free Language

TL;DR

This paper introduces Ring-Free Language (RFL), a hierarchical representation for chemical structures that simplifies recognition tasks, improves accuracy, and enhances readability in optical chemical structure recognition systems.

Contribution

The paper proposes RFL, a novel hierarchical language for chemical structures, and a universal Molecular Skeleton Decoder that together improve recognition performance over existing methods.

Findings

RFL achieves higher accuracy on printed chemical structures.

MSD improves recognition of handwritten chemical images.

The approach outperforms state-of-the-art methods in various scenarios.

Abstract

The primary objective of Optical Chemical Structure Recognition is to identify chemical structure images into corresponding markup sequences. However, the complex two-dimensional structures of molecules, particularly those with rings and multiple branches, present significant challenges for current end-to-end methods to learn one-dimensional markup directly. To overcome this limitation, we propose a novel Ring-Free Language (RFL), which utilizes a divide-and-conquer strategy to describe chemical structures in a hierarchical form. RFL allows complex molecular structures to be decomposed into multiple parts, ensuring both uniqueness and conciseness while enhancing readability. This approach significantly reduces the learning difficulty for recognition models. Leveraging RFL, we propose a universal Molecular Skeleton Decoder (MSD), which comprises a skeleton generation module that progressively predicts the molecular skeleton and individual rings, along with a branch classification module for predicting branch information. Experimental results demonstrate that the proposed RFL and MSD can be applied to various mainstream methods, achieving superior performance compared to state-of-the-art approaches in both printed and handwritten scenarios. The code is available at https://github.com/JingMog/RFL-MSD.