Knowledge-based numeric open caption recognition for live sportscast

Abstract

Knowledge-based numeric open caption recognition is proposed that can recognize numeric captions generated by a character generator (CG) and automatically superimpose a modified caption using the recognized text only when a valid numeric caption appears in the aimed specific region of a live sportscast scene produced by other broadcasting stations. In the proposed method, mesh features are extracted from an enhanced binary image as feature vectors, then valuable information is recovered from a numeric image by perceiving the character using a multilayer perceptron (MLP) network. The result is verified using a knowledge-based rule set designed for a more stable and reliable output and then the modified information is displayed on a screen by CG. MLB EyeCaption based on the proposed algorithm has already been used for regular Major League Baseball (MLB) programs broadcast live over a Korean nationwide TV network and has produced a favorable response from Korean viewers.