Rastogi, PrakharSingh, KaranveerSreevalsan-Nair, JayaVangorp, PeterHunter, David2023-09-122023-09-122023978-3-03868-231-8https://doi.org/10.2312/cgvc.20231200https://diglib.eg.org:443/handle/10.2312/cgvc20231200Data extraction from visualization is a challenging problem in computer vision owing to the huge ''design space of possible vis idioms.'' Different visualizations pose different challenges in automated data extraction from their images, which is needed in document analysis. In the case of sunburst charts for hierarchical data, the extracted data has to be also correctly organized as a tree data structure. Overall, data extraction has to consider different components of a chart image, such as text, annular sectors, levels, etc., and their ordering. We propose an end-to-end algorithm, SunburstChartAnalyzer, for data extraction from sunburst charts. The algorithm includes chart classification, component extraction, and hierarchical data organization. We further propose a composite metric to evaluate the correctness of SunburstChartAnalyzer. Our experimental results show that our proposed method works for trees of all sizes, and particularly well for shallow and medium-depth trees.Attribution 4.0 International LicenseCCS Concepts: Human-centered computing -> Visualization techniques; Accessibility systems and tools; Computing methodologies -> Information extraction; Image processing; Keywords: Hierarchical data, Visualization, Sunburst charts, Circle objects, Tree data structure, Optical Character Recognition, Text detection, Hough transform, GeometryHuman centered computingVisualization techniquesAccessibility systems and toolsComputing methodologiesInformation extractionImage processingKeywordsHierarchical dataVisualizationSunburst chartsCircle objectsTree data structureOptical Character RecognitionText detectionHough transformGeometry10.2312/cgvc.2023120097-1015 pages