CAJ | 학술논문

Robot navigation based on character recognition is an effective vision method for compensating the disadvantage of ultrasonic and infrared sensors. A typical example of character recognition for mobile robot navigation is the doorplate recognition system. The captured doorplate images contain unexpected noise from irregular illumination conditions, various imaging angles, different imaging distances, etc. The unexpected noise may still exist after segmentation step. In this paper, a robust segmentation method based on speculating the candidates of the characters and feeding back the classification result to the segmentation process is presented. If the candidates of doorplate characters cannot be determined at the segmentation step, a speculation according to known knowledge is executed. The threshold for character extraction from candidates is adjusted when the corresponding character is rejected after classification. The experimental results indicate that the recognition results are effectively improved with the proposed segmentation method.