loading page

Pattern Recognition Spiking Neural Network for Chinese Characters Classification
  • +1
  • Nicola Russo ,
  • Thomas Madsen ,
  • Konstantin Nikolic ,
  • Wan Yuzhong
Nicola Russo
University of West London, University of West London

Corresponding Author:[email protected]

Author Profile
Thomas Madsen
Author Profile
Konstantin Nikolic
Author Profile
Wan Yuzhong
Author Profile


In recent years, artificial neural networks (ANNs) have completely changed the field of machine learning, especially computer vision. The Spike Neural Network (SNN) is biologically more realistic than ANN. It is more hardware-friendly and energy-efficient, and suitable for running on portable devices with weak computing performance. In this paper we aim to classify several Chinese character images based on SNN. The input image is preprocessed by traditional methods (OpenCV) and then it is input into the trained spike neural network to classify the characters. Different hyperparameters configurations are tested reaching an optimal configuration and a classification accuracy rate of 93%.