Yang, WenjinHe, JieZhang, XiaotongGong, HaiyanWimmer, MichaelAlliez, PierreWestermann, Rüdiger2025-11-072025-11-0720251467-8659https://doi.org/10.1111/cgf.70146https://diglib.eg.org/handle/10.1111/cgf70146In the fields of engineering and natural sciences, curve charts serve as indispensable visualization tools for scientific research, product development and engineering design, as they encapsulate crucial data necessary for comprehensive analysis. Existing methodologies for data extraction from line charts predominantly depend on single-task models, which frequently exhibit limitations in efficiency and generalization. To overcome these challenges, we propose AI-ChartParser, an end-to-end deep learning model that employs multi-task learning to concurrently execute chart element detection, pivot point detection and curve detection. This approach effectively and efficiently parses diverse chart formats within a cohesive framework. Furthermore, we introduce an Interval-Mean Space-Numerical Mapping algorithm designed to address challenges in data range extraction, thereby significantly minimizing conversion errors. We have incorporated all the methodologies discussed in this paper to develop a comprehensive data extraction tool, facilitating the automatic conversion of line charts into tabular data. Our model exhibits exceptional performance on complex real-world datasets, achieving state-of-the-art accuracy and speed across all three tasks. To facilitate further research, the source codes and pre-trained models are released at https://github.com/ywking/ChartParser.git.curve chartdata extractionimage processingmultitask learningHuman-centred computing→Visual analyticsVisualization toolkit10.1111/cgf.7014616 pages