A New Format for Representing and Encoding Images
- Technology Benefits
- Better compression rate than JPG code, requires 5X less file size It extracts image structure, which is useful for later stage image processing
- Technology Application
- Image compression, storage, and transmission Image processing techniques
- Detailed Technology Description
- Researchers at UCLA have circumvented this serial procedure and developed a method for encoding images that require a much smaller file size. Their technique is based on the development of a primal sketch which is extracted from an image based on the portion of the image with distinguishable elements. A library is generated from these elements which can then be applied to the entire image for compression. In addition, because the method is evaluative and retains key features of the original image, it benefits subsequent image processing techniques.
- Supplementary Information
- Patent Number: US7567715B1
Application Number: US2005128408A
Inventor: Zhu, Song-Chun | Guo, Cheng-en | Wu, Ying-Nian
Priority Date: 12 May 2004
Priority Number: US7567715B1
Application Date: 12 May 2005
Publication Date: 28 Jul 2009
IPC Current: G06K000936 | G06K000946 | G06K000948 | G06K000962
US Class: 382232 | 382199 | 382225 | 382243
Assignee Applicant: The Regents of the University of California
Title: System and method for representing and encoding images
Usefulness: System and method for representing and encoding images
Summary: Computer-implemented method for reconstructing an input image.
Novelty: Computer-implemented input image reconstruction method, involves automatically reconstructing image based on sketch graph of sketchable portion and statistical summaries associated with texture regions, and outputting reconstructed image
- Industry
- ICT/Telecom
- Sub Category
- Image Processing
- Application No.
- 7567715
- Others
-
Background
JPEG is a standard image compression algorithm as the method by which the digital image is stored and is commonly used in digital cameras. The compression process relies on a series of algorithms that approximate the color spectrum in predefined regions of pixels. Because, the process is serial and is performed in the same manner across the whole image, the compression rate has no optimization routine and therefore suffers.
Tech ID/UC Case
20390/2004-563-0
Related Cases
2004-563-0
- *Abstract
-
Researchers at UCLA have circumvented this serial procedure and developed a method for encoding images that require a much smaller file size. Their technique is based on the development of a primal sketch which is extracted from an image based on the portion of the image with distinguishable elements. A library is generated from these elements which can then be applied to the entire image for compression. In addition, because the method is evaluative and retains key features of the original image, it benefits subsequent image processing techniques.
- *IP Issue Date
- Jul 28, 2009
- *Principal Investigator
-
Name: Charles Guo (Cheng-en)
Department:
Name: Ying-Nian Wu
Department:
Name: Song-Chun Zhu
Department:
- Country/Region
- USA
