Caption detection and removal in a TV scene

Authors:
JongBae Kim;KyoungKwan Ahn
Affiliations:
Research Center for Machine Parts and Material Processing, University of Ulsan, Ulsan, S.Korea;Department of Mechanical and Automotive Engineering, University of Ulsan, S.Korea
Venue:
AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
Year:
2004

Citing 5
Cited 0

Constrained Restoration and the Recovery of Discontinuities

IEEE Transactions on Pattern Analysis and Machine Intelligence
Image Sequence Analysis via Partial Differential Equations

Journal of Mathematical Imaging and Vision
Neural network-based text location in color images

Pattern Recognition Letters
Isophotes: The Key to Tractable Local Shading Analysis

CAIP '95 Proceedings of the 6th International Conference on Computer Analysis of Images and Patterns
Region removal and restoration using a genetic algorithm with isophote constraint

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a caption detection and removal technique for reuse of TV scenes using the Multilayer Perceptrons (MLPs) and Genetic algorithms (GAs) The technique first detects the captions in a TV scene using the MLP-based caption detector, and then removes the detected captions using the GA-based region remover In our technique, the caption removal problem is modeled as an optimization problem, which in our case, is solved by a cost function with isophote constraint that is minimized using a GA The technique creates an optimal connection of all pairs of isophote disconnected by caption regions To connect the disconnected isophote, we estimate the value of the smoothness, given by the best chromosome of the GA, and project this value in the isophote direction Experimental results show a great possibility for automatic removal of captions in TV advertisement scenes.