Design and Implementation of English Text Recognition System Under Robot Vision

EasyChair Preprint 3168

Abstract

The traditional methods of English letter visual recognition are machine learning and contour feature extraction. However, limited by the hardware resources such as camera and processor, it is difficult for the robot to realize fast and accurate text extraction and recognition. In this paper, median filtering method is used for image preprocessing, corner detection method for text extraction, overall framework of text recognition based on improved SOFM recognition algorithm of concentric rectangles with equal area, and based on the NAO robot platform to achieve system inspection.

Keyphrases: SOFM, character recognition, concentric matrix, robot

@booklet{EasyChair:3168,
  author    = {Gang Wang},
  title     = {Design and Implementation of English Text Recognition System Under Robot Vision},
  howpublished = {EasyChair Preprint 3168},
  year      = {EasyChair, 2020}}