Loading...

Font recognition for Persian optical character recognition system

Eghbali, K ; Sharif University of Technology | 2018

823 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/IranianMVIP.2017.8342360
  3. Publisher: IEEE Computer Society , 2018
  4. Abstract:
  5. Font recognition is one of the pre-processing steps in optical character recognition (OCR) systems that affects on their performance. In this paper two methods are proposed for Persian font recognition. In the first method, Gabor filter is used for feature extraction from the images, then principle component analysis (PCA) applied to reduce feature dimensions and finally, a multi-layer Perceptron (MLP) neural network is used for the classification. In the second techniques, random forest is utilized for recognizing fonts. For evaluation, a dataset includes 10 popular Persian fonts is used. The proposed Gabor-PCA-MLP method has achieved 98.70% of F-measure, and random forest resulted in of 96.95% of F-measure. © 2017 IEEE
  6. Keywords:
  7. Font recognition ; Gabor filter ; Nerual network ; PCA ; Persian OCR ; Random forest ; Computer vision ; Decision trees ; Optical character recognition ; Optical data processing ; Principal component analysis ; Font recognition ; Multi layer perceptron ; Nerual networks ; Optical character recognition (OCR) ; Optical character recognition system ; Persian ocrs ; Principle component analysis ; Random forests ; Gabor filters
  8. Source: Iranian Conference on Machine Vision and Image Processing, MVIPVolume 2017-November, 19 April 2018 ; Volume 2017 -November , April , 2018 , Pages 252-257 ; 21666776 (ISSN) ; 9781538644041 (ISBN)
  9. URL: https://ieeexplore.ieee.org/document/8342360