Back to Search
Start Over
Laminated paper counting algorithm based on compressive sensing and hough transform
- Source :
- Proceedings of 2nd International Conference on Information Technology and Electronic Commerce.
- Publication Year :
- 2014
- Publisher :
- IEEE, 2014.
-
Abstract
- According to the problem that conventional laminated paper counting algorithms have some unavoidable shortcomings such as high dependence on the quality of laminated paper and noise sensitivity, we propose a laminated paper counting algorithm based on compressive sensing (CS) and Hough transform (HT). In the proposed algorithm, the over-complete dictionary which is created by dispersing the Hough transform space of straight lines acts as the sparse matrix. Making use of high degree of sparse nature of the laminated paper image, we can obtain the accurate result through using CS theory. Experimental results on simulation images and laminated paper images have shown that our proposed algorithm can effectively restrain noise of the laminated paper image, and will get accurate experimental results with fewer CS measurements.
- Subjects :
- Degree (graph theory)
Computer science
business.industry
Noise (signal processing)
Iterative reconstruction
Mathematics::Geometric Topology
Hough transform
law.invention
Image (mathematics)
Compressed sensing
Signal-to-noise ratio
law
Computer Science::Computer Vision and Pattern Recognition
Computer vision
Artificial intelligence
business
Algorithm
Sparse matrix
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- Proceedings of 2nd International Conference on Information Technology and Electronic Commerce
- Accession number :
- edsair.doi...........712d6796e0cc11d4e625ea744b02d2c0