Automated Statistical Self-Calibrating Detection and Removal of Blemishes in Digital Images Based on Determining Probabilities Based on Image Analysis of Single Images

• US 20080144966A1
• Filed: 02/16/2008
• Published: 06/19/2008
• Est. Priority Date: 09/30/2003
• Status: Active Grant

• Current Assignee: FotoNation Limited (Adeia Inc.)
• Original Assignee: FotoNation Vision Limited (Adeia Inc.)
• Inventors: Steinberg, Eran, Prilutsky, Yury, Zamfir, Adrian, Bigioi, Petronel, Corcoran, Peter, Buzuloiu, Vasile, Zamfir, Marta, Ursu, Danutz
• Granted Patent: US 7,536,061 B2
• Time in Patent Office: Days
• US Class Current: 382/275
• CPC Class Codes: G06T 5/77 Retouching; Inpainting; Scratch removal
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/155 Removing patterns interfering with the pattern to be recognised, such as ruled lines or underlines
• CPC Class Codes: H04N 23/811 by dust removal, e.g. from surfaces of the image sensor or processing of the image signal output by the electronic image sensor
• CPC Class Codes: H04N 25/61 the noise originating only from the lens unit, e.g. flare, shading, vignetting or "cos4"
• CPC Class Codes: H04N 25/683 by defect estimation performed on the scene signal, e.g. real time or on the fly detection

Abstract

A method of automatically correcting dust artifact within images acquired by a system including a digital camera includes determining probabilities of dust artifact regions corresponding to pixels within a digitally-acquired image based at least in part on a pixel analysis of the region in view of predetermined characteristics indicative of the presence of a dust artifact region. The dust artifact regions are associated with one or more extracted parameters relating to the optical system when the image was acquired. A statistical dust map is formed including mapped dust regions based on the dust artifact determining and associating operations. Digital data is corrected corresponding to correlated dust artifact regions within the acquired image based on the associated statistical dust map.

Claims

1. A method of automatically correcting dust artifact within images acquired by a system including a digital camera, comprising:

(a) determining probability of dust artifact regions corresponding to pixels within a digitally-acquired image based at least in part on a pixel analysis of the region in view of predetermined characteristics indicative of the presence of a dust artifact region;

(b) associating the dust artifact regions with one or more extracted parameters relating to the optical system when the image was acquired;

(c) forming a statistical dust map including mapped dust regions based on the dust artifact determining and associating operations; and

(d) correcting digital data corresponding to correlated dust artifact regions within said digitally-acquired image based on the associated statistical dust map.