Method for sliced inpainting

• US 9,053,530 B2
• Filed: 11/27/2007
• Issued: 06/09/2015
• Est. Priority Date: 11/27/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Kokemohr, Nils
• Primary Examiner(s): LE, BRIAN Q
• Application Number:
  US11/946,005
• Publication Number:
  US 20080170807A1
• Time in Patent Office: 2,751 Days
• Field of Search: 382/181, 382190-195, 382/198, 382/199, 382/205, 382/209, 382/254, 382/255, 382/260, 382/263, 382/266, 382/274, 382/275, 382/283, 382/293, 382295-298
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/20192 Edge enhancement; Edge preservation
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• CPC Class Codes: G06T 5/20 using local operators
• CPC Class Codes: G06T 5/77 Retouching; Inpainting; Scratch removal
• CPC Class Codes: G06T 5/80 Geometric correction
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/90 Determination of colour characteristics

Abstract

A method for replacing image data in a destination region that is divided into sub-pieces along one or more cutting paths, which start and end at two different points on the border, and finding replacement data for the sub-pieces. The cutting paths may be determined as a function of the type of image structured at the start and the end points. The cutting paths may also be determined as a function of the area of the sub-pieces and the lengths of the cutting paths. Optionally, the destination region may be determined by a spot detection algorithm. Further optionally, the spot detection algorithm may comprise calculation of a high pass filter, or detection of areas of luminosity and border-to-volume ratios. A method for moving an image element within an image is also provided.

Claims

1. A method comprising:

dividing the destination region having image data into sub-pieces along one or more cutting paths, wherein the cutting paths start and end at two different points on the border of the destination region;

finding replacement data for the sub-pieces found elsewhere in the image; and

adapting the replacement data to fit in the destination region, wherein the adapting comprises adjusting an illumination of pixels, and wherein the adjusting comprises multiplying an illumination of the replacement data from a source region by a predetermined factor that is based on the illumination function, wherein the illumination function is based on an illumination of the destination region and an illumination of the source region, and wherein the source region contains the replacement data.

2. The method of claim 1, wherein the cutting paths are determined as a function of the type of image structured at the start and the end point of the cutting path.

3. The method of claim 1, wherein the cutting paths are determined as a function of the area of the sub-pieces and the lengths of the cutting paths.

4. The method of claim 1, wherein the destination region is the product of a rotation, a perspective correction, a lens distortion correction, or a creative image distortion.

5. The method of claim 1, wherein the illumination function is based on ill(D)/ill(S), wherein ill(D) is an illumination of the destination region, and wherein ill(S) is an illumination of the source region.

6. The method of claim 5, wherein the adapting of the replacement data comprises:

copying the replacement data from the source region to a separate region in a separate bitmap in memory;

applying a correction matrix to adapt the replacement data in the separate region; and

copying the replacement data from the separate region to the destination region.

7. The method of claim 5, wherein the destination region is determined by a spot detection algorithm, wherein the spot detection algorithm detects areas of luminosity and border-pixel-to-total-pixel ratios, and wherein the spot detection algorithm detects a border-pixel-to-total-pixel ratio below a predetermined ratio.

8. A non-transitory computer readable medium is provided having contents for causing a computer-based information handling system to perform the method of claim 1.