Offline Handwritten Mathematical Expression Recognition using CNN and Xception

Mathematical expressions generally play a requisite role in scientific communications. They are not just used for numerical calculations, on the other hand, also employed fetching information with less ambiguity, and facilitate researchers to exactly outline formalize target problems. It takes far longer manually enter mathematical formulas into computer than it does write them down paper using pen. Recently, we proposed deep learning methods that can identify images of trigonometric from 2dimensional layouts 1dimensional strings order solve this issue. As densely connected convolutional neural networks (CNN) boost accuracy, utilize CNN improve results study. In compare performance, Transfer Learning framework Exception is employed, which obtains 90% accuracy when recognizing handwritten expressions. provides 98% regard. Therefore, model created has higher rating Xception