An automatic recognition method of handwritten test data based on CNN and RNN model
A test data, automatic recognition technology, applied in character and pattern recognition, biological neural network models, instruments, etc., can solve the problems of cumbersome and lengthy data processing process, inability to effectively distinguish numbers and digital handwritten consecutive decimal points, etc., to increase the diversity and enhance the effect of anti-interference
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach
[0054] As a preferred embodiment of the present invention, S2 specifically includes the following steps:
[0055] S21. Perform multi-angle rotation and storage of the picture data acquired in step S1;
[0056] S22, adding noise points to the data image processed in step S21, and saving it;
[0057] S23. Perform elastic distortion processing on the data image processed in step S22, and save it.
[0058] In step S21, the picture data acquired in step S1 is stored at 15°, 30° and 45° rotations, the noise points in step S22 are black spots like snowflakes, and the elastic distortion in step S23 is processed to imitate the random shaking of hand muscles The data image is distorted. After the above measures, the original data volume is expanded by 3 times. The diversity of data is increased, and the anti-interference ability of the model is also strengthened, that is, the stability.
[0059] As a preferred embodiment of the present invention, step S3 specifically includes the fol...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap