Supercharge Your Innovation With Domain-Expert AI Agents!

Method and system for generating enhanced images

A technology for image enhancement and image generation, applied in image enhancement, image analysis, image data processing, etc.

Active Publication Date: 2013-02-06
APPLE INC
View PDF6 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, by definition, a global transformation cannot change the spatial structure of an image

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and system for generating enhanced images
  • Method and system for generating enhanced images
  • Method and system for generating enhanced images

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0128] Example 1: Remove Vignette

[0129] exist Figure 5 In (a), we show high-frequency grayscale targets. exist Figure 5 The effect of strong vignetting is shown in (b). To remove vignetting, we apply (11), in which case we use the perfect graph image as output and the warped counterpart as input, to find the calibration function ψ. In this example, we find an approximation function that best maps the natural logarithm of the input image to the natural logarithm of the output image. Apply the function again to the Figure 5 (b) (we apply to Figure 5 (b) and exponentiating the result), we obtain the rectified image 5(c). Now that we have the approximate function, we consider the vignetted image 5(d) and correct it to remove the vignette 5(e) (the undistorted image of the parrot is one of the Kodak test images http: / / r0k.us / graphics / kodak / ). We repeat this experiment, but now find the approximate function ψ using the 16th resolution calibration image (also performi...

example 2

[0130] Example 2: Dynamic Range Compression

[0131] exist Figure 6In (a), we show an underexposed parrot image. Dynamic range compression (DRC) algorithms attempt to map a large luminance input range to a smaller luminance range (eg, the luminance range of a display device). One of the simplest DRC algorithms is to divide the original image by the local average of nearby pixels. This operation is usually performed in logarithmic space. That is, we take an image, and calculate the logarithm of the pixel value. Then, by convolution, we compute local averages. In this example, we convolve using an inverse exponential filter with a standard deviation that is 1 / 8 the size of the horizontal dimension of the image. In logarithmic space, division becomes subtraction. Therefore, we subtract the local average from each logarithmic pixel value. Now we exponentiate. We then divide the image by the global maximum (in this case defined as the 99% quantile) for display. This last ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A method of generating an image enhancement function for enhancing an input image comprising a plurality of pixels to form an enhanced output image. The method includes receiving a reference image comprising a plurality of pixels; receiving an enhanced image derived from the reference image comprising a corresponding plurality of pixels; calculating a plurality of lookup tables, each of which maps a first plurality of pixel values to a second plurality of pixel values; and generating the image enhancement function comprising a spatially varying function of the lookup tables which when applied to the reference image generates an approximation to the enhanced image.

Description

technical field [0001] The present invention relates to methods and systems for generating enhanced images. Background technique [0002] Typically, one starts with an image X and processes the image in some way (such as dynamic range compression, contrast extension, or tone mapping) to enhance the image in some sense, giving an image Y=f(X). Usually the enhancement function is local varying and computationally expensive. Furthermore, augmentation may improve some image features at the cost of introducing some spatial artefacts. As an example, in dynamic range compression, a large input signal range is mapped to a smaller range (where all image detail is made prominent), often introducing a "halo" or "halo" at high-contrast edges. "ringing" artifacts. [0003] One way to avoid spatial artifacts is to process the image spatially, computing Y=f spatial (X), and then find the f global (X)=Y's global mapping function f global (). f global () refers to the function that m...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/40
CPCG06T2207/20012G06T5/009G06T5/40G06T5/92
Inventor 格雷汉姆·芬利森
Owner APPLE INC
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com