Optical Recognition of Handwritten Logic Formulas Using Neural Networks

Abstract

In this paper, we present a handwritten character recognition (HCR) system that aims to recognize first-order logic handwritten formulas and create editable text files of the recognized formulas. Dense feedforward neural networks (NNs) are utilized, and their performance is examined under various training conditions and methods. More specifically, after three training algorithms (backpropagation, resilient propagation and stochastic gradient descent) had been tested, we created and trained an NN with the stochastic gradient descent algorithm, optimized by the Adam update rule, which was proved to be the best, using a trainset of 16,750 handwritten image samples of 28 × 28 each and a testset of 7947 samples. The final accuracy achieved is 90.13%. The general methodology followed consists of two stages: the image processing and the NN design and training. Finally, an application has been created that implements the methodology and automatically recognizes handwritten logic formulas. An interesting feature of the application is that it allows for creating new, user-oriented training sets and parameter settings, and thus new NN models.

Feature Selection and Fusion in Cantonese Speech Emotion Analysis

“…Batch Normalization: Batch normalization (BN) is commonly used to standardize data at the input layer for ease of training. It stabilizes the numerical distribution of activation functions and improves model performance [17]. To alleviate overfitting, we added a dropout of 0.2 after the BN layer.…”