Combination of Hough Transform and Neural Network on recognizing mathematical symbols
Nabil Aouadi · 2021
Offline printed mathematical symbol recognition is a particularly difficult task. Recognizing mathematical symbols is one stage within the overall system for recognition of mathematical documents. We describe many experiments using MultiLayer Perceptron (MLP), Hough Transform (HT), k Nearest Neighbors (kNN) and structural Freeman chain code, to enhance symbol recognition of printed mathematics. First, we investigate the use of a MLP based method. Second, we compare the performance of a proposal neural structural method, named HT-MLPs, on symbols that initial MLP usually confuses. The inclusion of HT in MLP reduces symbol confusion rate by 21% and improves recognition rates from 72% to 93%. To improve the efficiency of the proposed method, we compare it to KNN then to Freeman code based methods, commonly used in pattern recognition. While analyzing results, we show that HT-MLP always gives a lower mean confusion and rejection and higher success rates than the others solutions.