Multi-modal image registration method based on deep learning
A multi-modal image and deep learning technology, which is applied in image analysis, image data processing, character and pattern recognition, etc., can solve the problem that the gray value is very different, the image similarity cannot be calculated correctly, and two images cannot be aligned, etc. problem, achieve high precision, small error, and facilitate image registration
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0034]The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.
[0035] see Figure 1-Figure 3 , the multimodal image registration method based on deep learning of the present invention comprises the following steps:
[0036] (S1), use cameras of different imaging modes to shoot the registration subject, and put a group of captured images of different modalities into the image set A;
[0037] (S2), the image set A is used as the input of the Net neural network, and the image set B after semantic segmentation is obtained;
[0038] (S3), each image in the image set B is multiplied pixel by pixel with the corresponding image in the image set A, to obtain a registration image set C;
[0039] (S4), select an image in the image set C as a fixed image, and use the rest of the images as deformed images, and use a grayscale-based image regist...
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