Recent Patents in Signal Processing (June 2015) – Image Inpainting

You are here

Inside Signal Processing Newsletter Home Page

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

News and Resources for Members of the IEEE Signal Processing Society

Recent Patents in Signal Processing (June 2015) – Image Inpainting

For our June 2015 issue, we cover recent patents dealing with various applications of image inpainting. The section below covers patents granted recently for image segmentation, image enhancement, mobile authentication, texture analysis and image compression.

In patent no. 9,042,649 a method for separating foreground and background contents in a document image is provided. The method first computes a pixel-wise map of maximal local features (e.g., local variance, local contrast, etc.), which is binarized to generate a mask for potential foreground. In order to utilize color information effectively, the local feature map is computed using all color channels of the image. Then the background image is obtained by inpainting the mask regions from the non-mask regions of the original document image. Adaptive thresholding is applied to the difference between the original document image and the background image to obtain the binary foreground image. Post-processing of the binary foreground image can further remove undesirable elements. Finally, a more accurate background image can be obtained by inpainting the original document image using the binary foreground image as a mask.

In patent no. 9,014,474 various embodiments are disclosed for performing inpainting. One embodiment is a method for editing a digital image in an image editing device. The method comprises obtaining an inpainting region in the digital image, determining a target resolution for scaling a resolution of the digital image based on an original resolution of the digital image, and determining an intermediate resolution level for scaling a resolution of the digital image based on the target resolution. The method further comprises scaling the resolution of the digital image to the intermediate resolution level, performing partial inpainting of the inpainting region at the intermediate resolution, and performing inpainting on a remainder portion in the inpainting region at a final target resolution.

In patent no. 8,887,255, a method of authenticating is described. The method may include sending first repair parameters representing one or more first repair operations applied to a first marked image to generate a first repaired image to a first entity. The method may also include receiving, from the first entity, a second repaired image. The method may also include authenticating the first entity when the second repaired image received from the first entity matches the first repaired image.

Various embodiments are disclosed in patent no. 8,867,794 for performing image inpainting. One embodiment is a method for editing a digital image in an image editing device. The method comprises obtaining a restoration region in the digital image and determining texture information corresponding to the restoration region. Based on the texture information, a texture strength map is generated corresponding to the restoration region. Based on the texture strength map, an inpainting operation is applied to pixels in the restoration region.

Systems and methods in patent no. 8,774,531 provide image compression based on parameter-assisted inpainting. In one implementation of an encoder, an image is partitioned into blocks and the blocks classified as smooth or unsmooth, based on the degree of visual edge content and chromatic variation in each block. Image content of the unsmooth blocks is compressed, while image content of the smooth blocks is summarized by parameters, but not compressed. The parameters, once obtained, may also be compressed. At a decoder, the compressed image content of the unsmooth blocks and the compressed parameters of the smooth blocks are each decompressed. Each smooth block is then reconstructed by inpainting, guided by the parameters in order to impart visual detail from the original image that cannot be implied from the image content of neighboring blocks that have been decoded.

If you have an interesting patent to share when we next feature patents related to inpainting techniques, or if you are especially interested in a signal processing research field that you would want to be highlighted in this section, please send email to Csaba Benedek (benedek.csaba AT sztaki DOT mta DOT hu).


Number: 9,042,649
Title: Color document image segmentation and binarization using automatic inpainting
Inventors: Y. Tian
Issued:  May 26, 2015

Number: 9,014,474
Title: Systems and methods for multi-resolution inpainting
Inventors: H-P. Hung and H-C. Huang
Issued:  April 21, 2015
Assignee:  Cyberlink Corp. (Shindian, Taipei, TW)

Number: 8,887,255
Title: Mobile authentication by image inpainting
Inventors: H. Hirose
Issued:  November 11, 2014
Assignee: Empire Technology Development LLC (Wilmington, DE)

Number: 8,867,794
Title: Systems and methods for performing image inpainting based on texture analysis
Inventors: P-Y. Huang, C-C. Kuo and H-C. Huang
Issued: October 21, 2014
Assignee: Cyberlink Corp. (Shindian, Taipei, TW)

Number: 8,774,531
Title: Image compression based on parameter-assisted inpainting
Inventors: X. Sun, Z. Xiong, F. Wu and S. Li
Issued:  July 8, 2014
Assignee: Microsoft Corporation (Redmond, WA)

Table of Contents:


IEEE SPS Educational Resources

IEEE SPS Resource Center

IEEE SPS YouTube Channel