Robot vision image segmentation method based on multi-scale fractal dimension and neural network
A technology of robot vision and neural network, which is applied in the field of image segmentation based on multi-scale fractal dimension and neural network, can solve the problems of image over-segmentation, missed contour detection, position deviation, etc., and achieve the effect of improving the speed of segmentation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0019] The present invention will be further described in detail below in conjunction with the drawings and specific examples.
[0020] Such as figure 1 As shown, the robot vision image segmentation method based on multi-scale fractal dimension and neural network of the present invention includes the following steps:
[0021] Step (1): Take 1000 images of the sky, roads, and trees each (more than 1000 images per image is appropriate, and 1000 images in this specific embodiment), and perform a series of preprocessing on them to form a training library for images (Such as image 3 Shown),
[0022] Preprocessing includes: grayscale, histogram equalization, and adjustment of image size to a uniform size (length and width are both 2 t , To facilitate subsequent calculations).
[0023] Step (2): Perform wavelet transformation on each image in the image training library to obtain a low-frequency approximate image and m high-frequency detail images of each image, where m is a positive integer...
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