Published September 12, 2022 | Version v1
Journal article Open

CHARACTER RECOGNITION AND DETECTION USING CLUSTERING AND RNN METHOD FOR VISUALLY IMPAIRED

Description

Text detection in images  is an important step to achieve multimedia content retrieval. In this paper, an efficient algorithm which can automatically detect, localize and extract horizontally aligned text in images with complex backgrounds is presented. The proposed approach is based on the pre-processing, a method for edge detection, grouping of similar data using clustering and classified using the RNN classifier. The text contains vital and useful information which is embedded in various types of documents and natural scene. The extraction of text from a natural image is a challenging task. The text is detected and is extracted in this way that it readable by another person without any difficulty. In proposed a fast text localization method in which sobel edge detection and clustering method is used to localize all the possible edges in the image.After clustering Morphological process is done to identify exactly the character.After identifying the character it is segmented using basic segmentation technique.The RNN classifier is used for the comparison between the trained datasets and the segmented text.After comparison, the text been detected and the trained dataset character is obtained to be same then the corresponding audio file is been given as a output.

Files

CHARACTER RECOGNITION AND DETECTION USING CLUSTERING AND RNN METHOD FOR VISUALLY IMPAIRED.pdf

Additional details

References

  • [1] Text Detection and Removal from Image using Inpainting with Smoothing, D. R. Patil,Priyanka Delip Wagh, 2015
  • [2] Connected Component Based Approach for Text Extraction from Color Image, Tania Mallick,Kamrul Hasa Talukder, 2014.
  • [3] Automatic Text Detection Using Morphological Operations and Inpainting, Khyati Vaghela , Narendra Patel, 2014.
  • [4] SnooperText: A text detection system for automatic indexing of urban scenes Rodrigo Minetto , Nicolas Thome , Matthieu Cord , Neucimar J. Leite , Jorge Stolfi ,2013.
  • [5] Auto Scene Text Detection Based on Edge and Color Features, Xiaodong Huang, Kehua Liu, Lishang Zhu,2012.
  • [6] Word Spotting and Recognition with Embedded Attributes, Jon Almazan, Albert Gordo, Alicia Forn 'es, Ernest Valveny ,2012.
  • [7] Novel Approach for Text Extraction from Natural Images Using ISEF Edge Detection, Sanjay Shah, Chintan Modi, Manisha Patel,2011
  • [8] Robust text detection in natural images with edge-enhanced maximally stable extremal regions, Huizhong Chen1, Sam S. Tsai1, Georg Schroth, David M. Chen1, Radek Grzeszczuk ,Bernd Girod, 2011
  • [9] A Low Complexity Sign Detection and Text Localization Method for Mobile Applications, Katherine L. Bouman, Golnaz Abdollahian, Mireille Boutin,Edward J. Delp, 2011.
  • [10] Features Extraction for Text Detection and Localization,Hinde, Driss, Abdellilah,2010.