Business Card Recognition and E-mail Delivery Based on NAO Robot
Xuewen Zhao, Qiang Gao, Shukai Shen, Zhe Wang
- Year
- 2018
- Citations
- 4
Abstract
The humanoid NAO robot is utilized to recognize the mailbox on the business card in the complex environment by computer vision in the paper. The method uses the robot's own API positioning system to locate the business card, collects the character sample through the camera. The image process includes sharpening, Gaussian blur and adaptive threshold, and then the corner detection is introduced to locate the text. Comparing to traditional BP neural network, the convolution neural network(CNN) algorithm possesses better performance in the fast and effective identification of characters. The task of sending mail to users is successfully completed. The results validate that the method has high adaptability, excellent accuracy and efficient real-time performance.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002