Paper
14 March 2013 Vehicle recognition based on positive feature
Author Affiliations +
Proceedings Volume 8768, International Conference on Graphic and Image Processing (ICGIP 2012); 87680X (2013) https://doi.org/10.1117/12.2010662
Event: 2012 International Conference on Graphic and Image Processing, 2012, Singapore, Singapore
Abstract
The existing chief methods of vehicle recognition is introduced in this paper, a new approach is presented to solve the shortcoming based on the actual situation of criminal technology. We first detect the edge with improved PCNN, and then the four coefficients are designed to represent the feature image. Finally, a BP neural network is constructed to classify the car types automatically. Expermiental results show that the proposed vehicle recognition is fast, simple and effective.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Feng Xu "Vehicle recognition based on positive feature", Proc. SPIE 8768, International Conference on Graphic and Image Processing (ICGIP 2012), 87680X (14 March 2013); https://doi.org/10.1117/12.2010662
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image processing

Neural networks

Edge detection

Neurons

Forensic science

Headlamps

Mathematical modeling

Back to Top