Novel framework for handwritten digit recognition through neural networks

  • Manjot Kaur
  • Tanya Garg
  • Ritika Wason
  • Vishal Jain


Purpose: The biggest challenge for natural language processing systems is to accurately identify and classify the hand-written characters. Accurate Handwritten Character recognition is challenging task for the humans too as the style, size and other handwriting parameters may vary from human to human. Though a relatively straightforward machine vision task but improved accuracy as compared to the existing implementations is still desirable. This manuscript aims to pro- pose a novel neural network based framework for handwritten character recognition.

Methodology: The proposed neural network based frame- work, transforms the raw data set to a NumPy array to achieve image flattening and feeds the same into a pixel vector before feeding it into the network. In the neural network the activation function is applied to  transfer  the  resultant  value to the hidden layer where  it  is  further  minimized  through  the use of minimized mean square and back propagation algorithms before applying stochastic gradient on the resultant mini batches.

Findings: After detailed study, the optimal algorithm for effective handwritten character recognition was proposed. Initially the framework has been simulated only on digits through 50,000 training data samples, 10,000 validation data set and 10,000 test data set, accuracy of 96.08

Originality: This manuscript aims to give the reader an insight into how the proposed neural network based framework has been applied for handwritten digit recognition. It highlights the successful applications of the same while laying down the directions for the enhancements possible.