This group collects work that evaluates, compares, or surveys OCSR methods rather than proposing new ones. It includes the two major review papers (Rajan et al. 2020 covering rule-based methods, Musazade et al. 2022 covering the deep learning transition), benchmark studies like Krasnov et al.’s 2024 comparison of eight tools on patent images, and ablation work on output representations (Rajan et al. 2022 on SMILES vs. SELFIES vs. InChI). The shared evaluation campaigns, TREC-Chem 2011 and CLEF-IP 2012, are represented both by their overview papers and by individual system descriptions (OSRA, ChemReader, Imago, chemoCR, and MolRec entries), providing a snapshot of the field’s state at those points in time.

YearPaperKey Idea
2011Chemical Structure Reconstruction with chemoCR (2011)Hybrid pattern recognition and rule-based expert system for OCSR
2011ChemReader Image-to-Structure OCR at TREC 2011 Chemical IRChemReader evaluation achieving 93% accuracy on TREC 2011
2011Imago: Open-Source Chemical Structure Recognition (2011)Open-source C++ toolkit for 2D chemical structure image recognition
2011MolRec: Rule-Based OCSR System at TREC 2011 BenchmarkRule-based OCSR using vectorization, achieving 95% on TREC 2011
2011OSRA at TREC-CHEM 2011: Optical Structure RecognitionOpen-source pipeline for converting chemical images to SMILES/SDF
2011Overview of the TREC 2011 Chemical IR Track BenchmarkBenchmark for patent prior art and chemical image recognition
2012CLEF-IP 2012: Patent and Chemical Structure BenchmarkBenchmarking lab for patent retrieval and chemical structure extraction
2012MolRec: Chemical Structure Recognition at CLEF 2012MolRec at CLEF 2012 revealing rule-based OCSR limits
2012MolRec at CLEF 2012: Rule-Based Structure RecognitionFailure analysis of MolRec on CLEF 2012 chemical structure task
2012OSRA at CLEF-IP 2012: Native TIFF Processing for PatentsNative TIFF processing outperforms external splitting tools
2020A Review of Optical Chemical Structure Recognition ToolsReview and benchmarking of 30 years of OCSR methods and tools
2022Review of OCSR Techniques and Models (Musazade 2022)OCSR evolution from rule-based systems to deep learning
2022String Representations for Chemical Image RecognitionAblation comparing SMILES, DeepSMILES, SELFIES, and InChI for OCSR
2024Benchmarking Eight OCSR Tools on Patent Images (2024)Benchmark of 8 open-access OCSR methods on 2702 patent images
2025Uni-Parser: Industrial-Grade Multi-Modal PDF Parsing (2025)Modular multi-expert PDF parsing engine with integrated OCSR
–Image-to-Sequence OCSR: A Comparative AnalysisComparative analysis of 24 image-to-sequence OCSR methods
–OCSR Methods: A Taxonomy of ApproachesTaxonomy of OCSR methods by approach type