Vehicle type recognition method based on deep Fisher network
A car model recognition, Fisher's technology, applied in the direction of character and pattern recognition, instruments, computer parts, etc., can solve problems such as the difficulty of optimizing the initial value, achieve the effect of reducing memory consumption, speeding up recognition speed, and improving recognition rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0034] In order to describe the technical content, structural features, achieved goals and effects of the present invention in detail, the following will be described in detail in conjunction with the embodiments and accompanying drawings.
[0035] This patent proposes a car model recognition method based on a deep Fisher network, which achieves good results in car model recognition. The schematic diagram of the whole algorithm is shown in figure 1 shown, including steps:
[0036] Step 1: Perform SIFT feature extraction on the image of the vehicle model database as the 0th layer of the Fisher network, as shown in the schematic diagram figure 2 (0);
[0037] SIFT is a local feature descriptor proposed by David Lowe, which has been developed rapidly and widely used. Since the SIFT feature points are extracted by extremum detection in the scale space, they have translation scale invariance; at the same time, a main direction is assigned to each feature point, so the rotation ...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap