A new neural network based algorithm for identifying handwritten mathematical equations

Identification of handwritten digits, letters, mathematical symbols and complex structure expressions have captured a lot of concentration in the field of pattern recognition. Accuracy has been improved by considering the features like skew, entropy, kurtosis, standard deviation. In segmentation binarization, edge detection, morphological operation has been considered. The equations under various categories have been considered for experiment and achieved significant results. Latency, throughput and accuracy have been improved by using feed forward back propagation neural network with gradient descent with momentum algorithm and adaptive learning.