An Enhanced Neural Network Approach With Hybrid Feature Extraction Technique for Recognition of Offline Handwritten Mathematical Equations
Recognition of handwritten digits, characters, mathematical symbols and equations is an intricate task due to its 2
dimensional layout, variation in writing style, different font, shapes, complex semantics, and spatial structure. Extracting
mathematical equations from the scan document is more complex. The proposed recognition system completes the task by
using feed forward back propagation neural network and hybrid feature extraction technique. The experiment has been
carried out for different types of handwritten mathematical equations. The system verifies its accuracy. By using neural
network with scaled conjugate gradient training, the accuracy increases with enhancing the speed of recognition.
Index terms- Offline recognition, Neural network, Math equations, Complex semantics, Hybrid feature