18105660. ELECTRONIC DEVICE FOR ESTIMATING CAMERA ILLUMINANT AND METHOD OF THE SAME simplified abstract (Samsung Electronics Co., Ltd.)

From WikiPatents
Jump to navigation Jump to search

ELECTRONIC DEVICE FOR ESTIMATING CAMERA ILLUMINANT AND METHOD OF THE SAME

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

Abdelrahman Abdelhamed of Toronto (CA)

Abhijith Punnappurath of Mountain View CA (US)

Michael Scott Brown of Mountain View CA (US)

ELECTRONIC DEVICE FOR ESTIMATING CAMERA ILLUMINANT AND METHOD OF THE SAME - A simplified explanation of the abstract

This abstract first appeared for US patent application 18105660 titled 'ELECTRONIC DEVICE FOR ESTIMATING CAMERA ILLUMINANT AND METHOD OF THE SAME

Simplified Explanation

The patent application describes a method for processing image data using two cameras capturing the same scene from different views. The method includes aligning the images, obtaining a color transformation matrix, estimating the illuminant color using a neural network, and performing white balance correction on the first image.

  • The method involves obtaining two images of the same scene captured by different cameras.
  • The first step is to spatially align the two images to ensure they match up properly.
  • A color transformation matrix is then calculated based on the color values of the two images.
  • The color transformation matrix is inputted into a neural network to estimate the illuminant color.
  • The neural network is trained using reference images of the same scene captured by different cameras with different spectral sensitivities.
  • Finally, a white balance correction is applied to the first image based on the estimated illuminant color, resulting in a corrected image.

Potential Applications

  • This technology can be used in various fields such as photography, computer vision, and image processing.
  • It can improve the accuracy of color reproduction in images captured by different cameras.
  • It can be applied in image editing software to automatically correct white balance and improve overall image quality.

Problems Solved

  • The method solves the problem of inconsistent color reproduction in images captured by different cameras.
  • It addresses the challenge of accurately estimating the illuminant color in order to perform white balance correction.
  • It overcomes the limitations of traditional white balance correction methods that may not account for differences in spectral sensitivities between cameras.

Benefits

  • The method provides a more accurate and reliable way to correct white balance in images.
  • It allows for consistent color reproduction across different cameras and views of the same scene.
  • The use of a neural network improves the precision of estimating the illuminant color, leading to better white balance correction.


Original Abstract Submitted

A method for processing image data may include: obtaining a first image and a second image that capture a same scene in different views, from a first camera and a second camera, respectively; spatially aligning the first image with the second image; obtaining a color transformation matrix that maps the first image to the second image based on color values of the first image and the second image; obtaining an estimated illuminant color from an output of a neural network by inputting the color transformation matrix to the neural network, wherein the neural network is trained based on a pair of reference images of a same reference scene with a color rendition chart that are captured by different cameras having different spectral sensitivities; and performing a white balance correction on the first image based on the estimated illuminant color to output a corrected first image.