Handwritten mathematical formula identification method, system and device and storage medium
The invention provides a handwritten mathematical formula identification method, system and device and a storage medium. The method comprises the following steps: carrying out graying processing on a handwritten mathematical formula image; the convolutional neural network carries out coding processi...
Gespeichert in:
Hauptverfasser: | , |
---|---|
Format: | Patent |
Sprache: | chi ; eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | The invention provides a handwritten mathematical formula identification method, system and device and a storage medium. The method comprises the following steps: carrying out graying processing on a handwritten mathematical formula image; the convolutional neural network carries out coding processing on the grayed picture; and the BIGRU-Attention model is used for carrying out decoding processing on the coded data. According to the method, the convolutional neural network and the BIGRU-Attention model are adopted, so that feature extraction is enhanced, gradient propagation is promoted, the working efficiency is improved, the recognition rate is greatly improved, and the accuracy is improved; when image feature extraction is carried out on an input data set, unimportant features of an image are discarded, important image features are reserved, and encoding and decoding time is shortened; and the extraction rate of the features and the identification efficiency of the mathematical expressions are improved.
本发 |
---|