caa a22 4500 605541205 CHVBK 20210128100915.0 cr unu---uuuuu 210128e20150501xx s 000 0 eng 10.1007/s00371-014-0988-4 doi (NATIONALLICENCE)springer-10.1007/s00371-014-0988-4 Restoring images of ancient color postcards [Elektronische Daten] [Edward Roe, Carlos de Mello] This paper proposes an automatic system for the restoration of digital images of vintage colored postcards, employing the combined techniques of image equalization, background segmentation based on edge detection (using an extension of the standard difference of Gaussians filter), color enhancement, and noisy spots removal. Equalization and background segmentation are used to facilitate background spot removal. To enhance colors, the overall document degradation is regarded as an illumination problem, thereby allowing the use of color constancy algorithms. The methodology was applied to a set of postcards dating from the end of the nineteenth century, and satisfactory visual results were achieved. Springer-Verlag Berlin Heidelberg, 2014 Color image processing nationallicence Color restoration nationallicence Color constancy nationallicence Image restoration nationallicence Edge detection nationallicence Difference of Gaussians nationallicence Roe Edward Centro de Informática, Unversidade Federal de Pernambuco, Recife, Brazil aut de Mello Carlos Centro de Informática, Unversidade Federal de Pernambuco, Recife, Brazil aut The Visual Computer Springer Berlin Heidelberg 31/5(2015-05-01), 627-641 0178-2789 31:5<627 2015 31 371 https://doi.org/10.1007/s00371-014-0988-4 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00371-014-0988-4 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Roe Edward Centro de Informática, Unversidade Federal de Pernambuco, Recife, Brazil aut NATIONALLICENCE 700 1- de Mello Carlos Centro de Informática, Unversidade Federal de Pernambuco, Recife, Brazil aut NATIONALLICENCE 773 0- The Visual Computer Springer Berlin Heidelberg 31/5(2015-05-01), 627-641 0178-2789 31:5<627 2015 31 371