{
  "id": "2408.16123",
  "version": "v1",
  "published": "2024-08-28T20:22:39.000Z",
  "updated": "2024-08-28T20:22:39.000Z",
  "title": "ChartEye: A Deep Learning Framework for Chart Information Extraction",
  "authors": [
    "Osama Mustafa",
    "Muhammad Khizer Ali",
    "Momina Moetesum",
    "Imran Siddiqi"
  ],
  "comment": "8 Pages, and 11 Figures",
  "doi": "10.1109/DICTA60407.2023.00082",
  "categories": [
    "cs.CV",
    "cs.AI",
    "cs.LG"
  ],
  "abstract": "The widespread use of charts and infographics as a means of data visualization in various domains has inspired recent research in automated chart understanding. However, information extraction from chart images is a complex multitasked process due to style variations and, as a consequence, it is challenging to design an end-to-end system. In this study, we propose a deep learning-based framework that provides a solution for key steps in the chart information extraction pipeline. The proposed framework utilizes hierarchal vision transformers for the tasks of chart-type and text-role classification, while YOLOv7 for text detection. The detected text is then enhanced using Super Resolution Generative Adversarial Networks to improve the recognition output of the OCR. Experimental results on a benchmark dataset show that our proposed framework achieves excellent performance at every stage with F1-scores of 0.97 for chart-type classification, 0.91 for text-role classification, and a mean Average Precision of 0.95 for text detection.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-08-28T20:22:39.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep learning framework",
      "framework utilizes hierarchal vision transformers",
      "text detection",
      "super resolution generative adversarial networks",
      "chart information extraction pipeline"
    ],
    "tags": [
      "journal article"
    ],
    "publication": {
      "publisher": "IEEE"
    },
    "note": {
      "typesetting": "TeX",
      "pages": 8,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}