Natural scene text recognition method and system of multi-path parallel position association network
A technology for natural scene and text recognition, applied in neural learning methods, character and pattern recognition, biological neural network models, etc., can solve the problems of poor model robustness, misidentified edge features, complex image background, etc., to improve accuracy , the effect of improving the alignment accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0079] The technical solution of the present invention will be specifically described below in conjunction with the accompanying drawings.
[0080] Such as figure 1 , 3 Shown, the natural scene text recognition method of a kind of multi-way parallel location association network of the present invention, comprises the following steps:
[0081] Step A. Crop the image containing only text information in the natural scene picture, and mark the corresponding text and text length in the picture, and construct the training data set S;
[0082] Step B, using the training set S to train a deep learning network model G based on multi-channel parallel position association, for recognizing text information in natural scene pictures;
[0083] Step C, input the text picture cut to a fixed size into the trained deep learning network model G, and obtain the corresponding target character text information in the picture.
[0084] Described step B specifically comprises the following steps: ...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com