This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
||||||||
|
Paper Details
Paper Title
A Survey on Text Detection in Natural Images
Authors
  Amritha S Nadarajan,  Thamizharasi A
Abstract
In natural images, some documents are embedded. Text detection is identifies text from natural images. Basic digital image processing techniques are used to detect text from the images. This includes preprocessing, extraction or text localization, classification and character detection. The different classification methods used are SVM, AdaBoost, CNN; Text-CNN etc. This paper provides a detailed study of evolution of text detection in natural images. It compares, analyzes and also discusses the different methods to overcome existing challenges in text detection. This paper presents the different types of datasets which are used to identify text from natural images and comparative study of different text detection methods. The comparative study proves that CNN is a better technique to detect text in natural images.
Keywords- Text detection, survey, natural image, SVM, CNN, Ada Boost
Publication Details
Unique Identification Number - IJEDR1801011Page Number(s) - 60-66Pubished in - Volume 6 | Issue 1 | January 2018DOI (Digital Object Identifier) -    Publisher - IJEDR (ISSN - 2321-9939)
Cite this Article
  Amritha S Nadarajan,  Thamizharasi A,   "A Survey on Text Detection in Natural Images", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.6, Issue 1, pp.60-66, January 2018, Available at :http://www.ijedr.org/papers/IJEDR1801011.pdf
Article Preview
|
|
||||||
|