Financial bill seal erasing method based on attention mechanism and generative adversarial network
An attention and seal technology, applied in the field of graph convolutional neural network, can solve problems such as difficulty in identifying financial bills, and achieve the effect of reducing the amount of calculation and running time, solving identification difficulties, and improving accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0020] First of all, it needs to be explained that the concept of the present invention is to receive the original picture of the financial bill; use the feature extraction module in the convolutional neural network to determine its first feature map according to the original picture; use the convolutional neural network according to The first feature map extracts the background color map of the original picture and the attention heat map of the position distribution of the reaction seal on the original picture respectively; and, using the convolutional neural network according to the original picture, background color The second feature map spliced by the graph and the attention heat map in the channel direction generates a picture after erasing the seal of the original picture through a generation confrontation method; the convolutional neural network is trained using a generation confrontation method.
[0021] refer to figure 1 In one embodiment of the present invention, ...
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