3 years ago

A Survey on Text Information Extraction from Born-Digital and Scene Text Images

S. Valli, S. P. Faustina Joan


Text information extraction (TIE) from images is an open research area because of its unsolved challenges with respect to the heterogeneity in image types, mode of image capture, position of text and the clarity of text information. Currently, the number of images captured using mobile phones is voluminous. The information from such images is capable of providing valuable input to the user as well to applications that depend on the image text information. Text is the pipeline of human communication and images containing text can aid the semantic understanding of the image. Types of image text are explored along with an introduction to TIE and its applications. Text detection is emphasized and an attempt to categorize the features used by text detection is made. With a brief discussion on the onset research works, the available datasets and performance metrics are listed out. A broad summary regarding the types of text detection methods and systems under them is presented. The paper concludes with existing challenges that pave the way for more active research.

Publisher URL: https://link.springer.com/article/10.1007/s40010-017-0478-y

DOI: 10.1007/s40010-017-0478-y

You might also like
Discover & Discuss Important Research

Keeping up-to-date with research can feel impossible, with papers being published faster than you'll ever be able to read them. That's where Researcher comes in: we're simplifying discovery and making important discussions happen. With over 19,000 sources, including peer-reviewed journals, preprints, blogs, universities, podcasts and Live events across 10 research areas, you'll never miss what's important to you. It's like social media, but better. Oh, and we should mention - it's free.

  • Download from Google Play
  • Download from App Store
  • Download from AppInChina

Researcher displays publicly available abstracts and doesn’t host any full article content. If the content is open access, we will direct clicks from the abstracts to the publisher website and display the PDF copy on our platform. Clicks to view the full text will be directed to the publisher website, where only users with subscriptions or access through their institution are able to view the full article.