Design method of neural network for image definition discrimination
A technology of image clarity and neural network, applied in the field of image processing, can solve the problem of few complete networks and achieve good fusion effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0021] Below in conjunction with the accompanying drawings and specific embodiments, the present invention will be further clarified. It should be understood that these embodiments are only used to illustrate the present invention and not to limit the scope of the present invention. Modifications of equivalent forms all fall within the scope defined by the appended claims of this application.
[0022] The present invention provides a method for designing a neural network for image sharpness discrimination, comprising the following steps:
[0023] Step 1: For the binary convolutional neural network designed for clear and blurred image sub-blocks, it is implemented by borrowing a simple structure similar to LeNet-5. Considering the relatively small size of the sub-blocks, we choose to discard the pooling layer and modify the output of the scoring layer to be a 2-class scoring value. The network structure includes: input layer, several consecutive convolutional layers (C1~m), sc...
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