RFL: Simplifying Chemical Structure Recognition with Ring-Free Language
This work addresses a domain-specific problem in chemical informatics by simplifying recognition tasks, though it is incremental as it builds on existing methods with a novel decomposition strategy.
The paper tackles the challenge of recognizing complex chemical structures with rings and branches in Optical Chemical Structure Recognition by proposing a Ring-Free Language (RFL) that decomposes structures hierarchically, achieving superior performance over state-of-the-art methods in printed and handwritten scenarios.
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.