Summary of Charteye: a Deep Learning Framework For Chart Information Extraction, by Osama Mustafa et al.
ChartEye: A Deep Learning Framework for Chart Information Extraction
by Osama Mustafa, Muhammad Khizer Ali, Momina Moetesum, Imran Siddiqi
First submitted to arxiv on: 28 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed deep learning-based framework offers a solution for the complex task of information extraction from chart images by breaking it down into key steps. The system utilizes hierarchal vision transformers for chart-type and text-role classification, YOLOv7 for text detection, and Super Resolution Generative Adversarial Networks to enhance detected text for improved OCR recognition. By leveraging these techniques, the framework achieves excellent performance on a benchmark dataset, with F1-scores of 0.97 for chart-type classification, 0.91 for text-role classification, and mean Average Precision of 0.95 for text detection. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers developed a way to automatically understand charts and graphs by breaking down the process into smaller tasks. They used special types of computer vision models called transformers to figure out what type of chart it is and what role different pieces of text play in it. Another model, YOLOv7, helps find the text in the first place. Once the text is found, they use a special technique called Super Resolution Generative Adversarial Networks to make sure the computer can read it correctly. They tested their system on some charts and it worked really well. |
Keywords
» Artificial intelligence » Classification » Deep learning » Mean average precision » Super resolution
