Handwritten character recognition method and system and medium
A handwritten character and recognition method technology, applied in the field of image processing, can solve the problems of recognition errors, low recognition accuracy, slow stroke extraction methods, etc., and achieve the effects of improving accuracy, recognition accuracy, and accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0065] The embodiment of the present invention provides a handwritten character recognition method, please refer to figure 1 , including the following steps:
[0066] S100. Acquire handwritten character image data, and perform image preprocessing on data samples in the handwritten character image data to obtain a first handwritten character image data set;
[0067] The specific steps of S100 are: connecting the handwritten character image data set and collecting the handwritten character image data through the network. The handwritten character image data set includes HCL2000, CASIA Chinese handwritten data set, CASIA English handwritten data set, DBRHD and MNIST;
[0068] From the above handwritten character image data set, it can be seen that the types of handwritten character image data sets include various forms, Chinese character type handwritten image data set, English type handwritten image data set and digital type handwritten image data set, through different The typ...
Embodiment 2
[0107] The embodiment of the present invention also provides a handwritten character recognition system, please refer to figure 2 , including: image preprocessing module, model training and verification module, image segmentation module, handwritten character verification module and recombination module;
[0108] The image preprocessing module is used to obtain handwritten character image data, and image preprocessing is performed on the handwritten character image data to obtain the first handwritten character image data set;
[0109] Model training verification module is used for setting performance parameter threshold value, carries out model training verification operation by described performance parameter threshold value, described first handwritten character image data set and neural network training model, obtains handwritten single-character character recognition model;
[0110] The image segmentation module is used to segment the image of the handwritten character t...
Embodiment 3
[0114] The present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program for executing the above method when executed by a processor, so as to realize the steps of the above-mentioned handwritten character recognition method.
[0115] Finally, it should be noted that those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct relevant hardware to complete. When the program is executed, it can include the implementation of the above methods. example process. Wherein, the storage medium of the program may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), and the like. The foregoing computer program embodiments can achieve the same or similar effects as any of the foregoing method embodiments corresponding thereto.
[0116] In addition, the method ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More