Vehicle type recognition algorithm based on S-SIFT features and SVM training device
A car model recognition and trainer technology, applied in the field of computer vision, can solve problems such as inconsistent vehicle entry and exit angles, difficulty in car model recognition, low resolution, etc., to achieve real-time performance, reduced time complexity, and good recognition.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0037] Now in conjunction with accompanying drawing, the present invention is described in further detail, the specific content of the embodiment of the present invention is a kind of vehicle identification algorithm based on S-SIFT feature and SVM trainer, and this vehicle identification algorithm comprises the following steps:
[0038] S1 license plate positioning;
[0039] S1.1 Training license plate sample feature extraction and feature organization;
[0040] S1.1.1 Manually extract any normal national standard license plate;
[0041] S1.1.2 Carry out integral channel feature extraction on the extracted license plate image;
[0042] The integral channel feature was proposed by Dollár P et al. in 2009. It is usually used for pedestrian detection at the earliest. It is a detection operator with better evaluation effect at present. Transformation, many common features of images, such as local summation, histogram, Haar and their variants, can be calculated quickly and effic...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


