Rapid Computational Technique for Inpainting of High Contrast Images
- Technology Benefits
- Reduced processing time. Results equivalent to existing models.
- Technology Application
- The technique can be integrated into commercial applications for document and image processing. Ideal applications range from inpainting of obscured road in an aerial satellite image to the recovery of damaged images.
- Detailed Technology Description
- Researchers studying image processing at the UCLA has devised a robust technique for high-contrast images that overcomes the time-consuming aspect of existing inpainting models. The simplicity of the UCLA model allows it to compute the missing pieces efficiently with significantly less processing time. Furthermore, the simplified model is capable of generating an image comparable to that produced by traditional image processing algorithms. The technique has been compared to the existing models on an assortment of images, including printed text and aerial photographs. Quantitative data demonstrates marked improvement in calculation time, as depicted in the following table. Testing was conducted on two examples-inpainting a circle, and inpainting a disconnected stripe. The speed made possible by this innovation will allow rapid computation of large datasets. Method Inpainting Time (seconds) Circle Stripe Curvature Driven Diffusion >5,400 >5,400 Euler's Elastica >18,000 >18,000 Mumford-Shah-Euler 45 24 UCLA Model 24 6
- Supplementary Information
- Patent Number: US7840086B2
Application Number: US2006543011A
Inventor: Bertozzi, Andrea L. | Esedoglu, Selim | Gillette, Alan E.
Priority Date: 12 Oct 2005
Priority Number: US7840086B2
Application Date: 3 Oct 2006
Publication Date: 23 Nov 2010
IPC Current: G06K000940
US Class: 382254 | 382274 | 382275
Assignee Applicant: The Regents of the University of California
Title: Method for inpainting of images
Usefulness: Method for inpainting of images
Summary: Used for filling in of damaged or missing region of an image (claimed) e.g. color image or greyscale image such as high-contrast or binary image, using information from surrounding areas, that is utilized for inpainting the image.
Novelty: Image`s e.g. color image, damaged or missing region filling method for inpainting image, involves solving differential equation related to image function, where equation has fidelity term and parameter to measure transition region
- Industry
- Electronics
- Sub Category
- Computer System
- Application No.
- 7840086
- Others
-
State of Development
The invention has been tested on test patterns, including aerial maps and text. The invention will be tested on documents obtained in the field, and the inventors will continue to refine the model for use on aerial photographs. Bertozzi, A.L., Esedoglu, S., Gillettem A. Inpainting of Binary Images Using the Cahn-Hilliard Equation. IEEE Transactions in Image Processing. August 16, 2006. Available from: http://www.math.ucla.edu/~bertozzi/papers/CHIEEE.pdf
Background
Inpainting has been practiced by art curators for many years to repair damaged paintings, where the visible patterns are used to make assumptions on how to fill in the missing pieces. In recent years, the advent of digitization gave rise to various mathematical models that would automate the task of interpreting patterns on a digital image for filling in the empty spaces. Common applications of inpainting include sharpening of blurry images, as well as the reduction of noise (i.e. scratches and speckles) in an image. Existing mathematical models involve complex computations requiring extensive time to approximate the complete image, which creates interest for a faster method that does not sacrifice image quality.
Additional Technologies by these Inventors
Tech ID/UC Case
20280/2006-202-0
Related Cases
2006-202-0
- *Abstract
-
A mathematical model has been developed at UCLA that performs inpainting of high contrast images with considerable decrease in processing time. The results produced by this model are comparable to existing methods, making this technique ideal for document and image processing.
- *IP Issue Date
- Nov 23, 2010
- *Principal Investigator
-
Name: Andrea Bertozzi
Department:
Name: Selim Esedoglu
Department:
Name: Alan Gillette
Department:
- Country/Region
- USA
