Loading...

Persian handwritten digit recognition by random forest and convolutional neural networks

Zamani, Y ; Sharif University of Technology

609 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/IranianMVIP.2015.7397499
  3. Publisher: IEEE Computer Society
  4. Abstract:
  5. Persian handwritten digit recognition has attracted some interests in the research community by introduction of large Hoda dataset. In this paper, the well-known random forest (RF) and convolutional neural network (CNN) algorithms are investigated for Persian handwritten digit recognition on the Hoda dataset. Using the Hoda dataset as a standard testbed, we have performed some experiments with different preprocessing steps, feature types, and baselines. It is then shown that RFs and CNNs perform competitively with the state-of-the-art methods on this dataset, while CNNs being the fastest if appropriate hardware is available
  6. Keywords:
  7. Machine learning ; Persian digits ; Artificial intelligence ; Computer vision ; Convolution ; Decision trees ; Image processing ; Learning systems ; Neural networks ; Convolutional neural network ; Handwritten digit recognition ; Hoda dataset ; Persians ; Random forests ; Character recognition
  8. Source: 9th Iranian Conference on Machine Vision and Image Processing,18 November 2015 through 19 November 2015 ; Volume 2016-February , 2015 , Pages 37-40 ; 21666776 (ISSN) ; 9781467385398 (ISBN)
  9. URL: http://ieeexplore.ieee.org/document/7397499