Home /Research /Business Card Recognition and E-mail Delivery Based on NAO Robot
PERCEPTION

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

Computer scienceConvolutional neural networkArtificial intelligenceAdaptabilityIdentification (biology)RobotComputer visionArtificial neural networkHumanoid robotTask (project management)

Related papers

Browse all PERCEPTION papers