{
  "id": "1611.06779",
  "version": "v1",
  "published": "2016-11-21T13:35:15.000Z",
  "updated": "2016-11-21T13:35:15.000Z",
  "title": "TextBoxes: A Fast Text Detector with a Single Deep Neural Network",
  "authors": [
    "Minghui Liao",
    "Baoguang Shi",
    "Xiang Bai",
    "Xinggang Wang",
    "Wenyu Liu"
  ],
  "comment": "Accepted by AAAI2017",
  "categories": [
    "cs.CV"
  ],
  "abstract": "This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression. TextBoxes outperforms competing methods in terms of text localization accuracy and is much faster, taking only 0.09s per image in a fast implementation. Furthermore, combined with a text recognizer, TextBoxes significantly outperforms state-of-the-art approaches on word spotting and end-to-end text recognition tasks.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2016-11-21T13:35:15.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "single deep neural network",
      "fast text detector",
      "fast scene text detector",
      "significantly outperforms state-of-the-art approaches",
      "trainable fast scene text"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}