Image invariant feature extraction based on circular trace transform
A feature extraction and circular trace technology, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve problems such as the research on invariant feature extraction methods of few different geometric texture images, and achieve the effect of good discrimination ability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0053] Such as figure 1 As shown, the flow chart of extracting image invariant texture features by Circular Trace Transform (CTT, Circular Trace Transform) method, in order to evaluate the identification ability and stability of the features obtained by this method for nearly circular or arc-shaped textures, implement The example simulation experiment uses the images in the two image databases for classification and recognition, and compares them with the trace transformation (TT, TraceTransform) results. Including the following steps:
[0054] Step 1: The images in the coil-20-process image library used in the embodiment and the randomly selected sub-images in the Brodatz image library are all grayscale images of 128×128, and the grayscale is 256. In order to prevent information loss caused by image rotation, the original grayscale image is expanded to 183*183, and all pixel values in the expanded part are 0, and the expanded grayscale image is recorded as F.
[0055] Ste...
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