摘要
An efficient method to recognize caption area in MPEG compressed video waspresented, by making use of the contrast of I-framc to distinguish caption area with background. Wedefine texture energy, intensity of boundary, distance of background, and texture correlation torecognize caption area and caption frame. The benefit of only analyzing I-frame is that we can makeuse of DOT coefficients directly without losing information. We have experimented with outalgorithm, and the result of experiment indicates that the performance of the algorithm isefficient.
An efficient method to recognize caption area in MPEG compressed video waspresented, by making use of the contrast of I-framc to distinguish caption area with background. Wedefine texture energy, intensity of boundary, distance of background, and texture correlation torecognize caption area and caption frame. The benefit of only analyzing I-frame is that we can makeuse of DOT coefficients directly without losing information. We have experimented with outalgorithm, and the result of experiment indicates that the performance of the algorithm isefficient.
基金
Supported by the Natural Science Foundation of Hubei Province(2004ABA174)
