1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'97)
Deterioration detection for digital film restoration
Puerto Rico
June 17-June 19
ISBN: 0-8186-7822-4
O. Buisson, Lab. d'Inf. et d'Imagerie Ind., La Rochelle Univ., France
B. Besserer, Lab. d'Inf. et d'Imagerie Ind., La Rochelle Univ., France
S. Boukir, Lab. d'Inf. et d'Imagerie Ind., La Rochelle Univ., France
F. Helt, Lab. d'Inf. et d'Imagerie Ind., La Rochelle Univ., France
This paper presents a robust technique to detect local deteriorations of old cinematographic films. This method relies on spatio-temporal information and combines two different detectors: a morphological detector which uses spatial properties of deteriorations, and a dynamic detector based on motion estimation techniques. Our deterioration detector has been validated on several film sequences and turned out to be a powerful tool for digital film restoration.
Index Terms:
motion estimation; deterioration detection; digital film restoration; robust technique; old cinematographic films; spatio-temporal information; morphological detector; dynamic detector; motion estimation
Citation:
O. Buisson, B. Besserer, S. Boukir, F. Helt, "Deterioration detection for digital film restoration," cvpr, pp.78, 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'97), 1997