A Chinese scene text line identification method based on residual convolution and a recurrent neural network
A recursive neural network and convolutional neural network technology, applied in the field of text line recognition in Chinese scenes, can solve problems such as complex fonts, difficult to recognize correctly, large number of categories, etc., and achieve the effect of strong robustness and avoiding wrong recognition
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0047] In order to make the technical means, objectives, and effects of the invention easy to understand, the present invention will be further described below in conjunction with specific embodiments.
[0048] according to figure 1 , 2 , 3, the present embodiment proposes a Chinese scene text line recognition method based on residual convolution and recursive neural network, comprising the following steps:
[0049] Step 1: Collect Chinese scene text training images. The scene text training images collected in this embodiment include Chinese characters, English letters, numbers, punctuation marks and some special symbols, and there are 3624 categories in total;
[0050] Step 2: Normalize the size of the training image, first normalize the height of the text line image in the Chinese scene to H s pixels, the width is proportionally scaled, and then the standard width W is set according to the network structure s , the normalized training image size is obtained as H s ×W s ...
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