G06V 10/30
Definition
Diese Klassifikationsstelle umfasst:(Für diese Definition ist die deutsche Übersetzung noch nicht abgeschlossen)
Techniques for noise removal or filtering such as thresholding in the frequency domain (e.g. after a Fourier or wavelet transform), edge-preserving smoothing techniques such as anisotropic diffusion (also called Perona-Malik diffusion), or deep learning approaches to image denoising, e.g. using convolutional neural networks (CNN’s).
Linear smoothing filters (e.g. for convolving the original image with a low-pass filter such as a Gaussian kernel matrix or applying a Wiener filter) and non-linear filtering such as median filtering or bilateral filtering (see also group G06V 10/36), when applied for the purpose of noise removal.
Noise estimation techniques based on a reference image, wherein the reference image may be:
- a previously captured image which was obtained with the same camera set-up;
- a previously captured image which was obtained with an optical system of higher quality, potentially downscaled or otherwise converted to match the expected performance parameters of a lower-quality system;
- artificially generated patterns, obtained e.g. by blurring or smoothing the original image or by means of computer graphics techniques (e.g. rendered from a 3D model of an object).
Estimation of noise parameters based on different noise models, e.g. additive white Gaussian noise, speckle noise, etc.
Detection of blur or defocusing of the image pattern.
Examples
Face image denoising
Face denoising using an autoencoder convolutional neural network architecture (above), followed by face recognition using a discriminator architecture (below)
Querverweise
Informative Querverweise
| Aligning, centring, orientation detection or correction for image or video recognition or understanding | G06V 10/24 |
| Segmentation of patterns in the image field | G06V 10/26 |
| Local image operators for image or video recognition or understanding, e.g. median filtering | G06V 10/36 |
| Enhancement or restoration for general image processing | G06T 5/00 |
Glossar
| DCT | discrete cosine transform |
| FFT | fast Fourier transform |
| PDF | probability density function |
| SNR | signal to noise ratio |
G06V 10/30
Definition Statement
This place covers:Techniques for noise removal or filtering such as thresholding in the frequency domain (e.g. after a Fourier or wavelet transform), edge-preserving smoothing techniques such as anisotropic diffusion (also called Perona-Malik diffusion), or deep learning approaches to image denoising, e.g. using convolutional neural networks (CNN’s).
Linear smoothing filters (e.g. for convolving the original image with a low-pass filter such as a Gaussian kernel matrix or applying a Wiener filter) and non-linear filtering such as median filtering or bilateral filtering (see also group G06V 10/36), when applied for the purpose of noise removal.
Noise estimation techniques based on a reference image, wherein the reference image may be:
- a previously captured image which was obtained with the same camera set-up;
- a previously captured image which was obtained with an optical system of higher quality, potentially downscaled or otherwise converted to match the expected performance parameters of a lower-quality system;
- artificially generated patterns, obtained e.g. by blurring or smoothing the original image or by means of computer graphics techniques (e.g. rendered from a 3D model of an object).
Estimation of noise parameters based on different noise models, e.g. additive white Gaussian noise, speckle noise, etc.
Detection of blur or defocusing of the image pattern.
Examples
Face image denoising
Face denoising using an autoencoder convolutional neural network architecture (above), followed by face recognition using a discriminator architecture (below)
References
Informative references
| Aligning, centring, orientation detection or correction for image or video recognition or understanding | G06V 10/24 |
| Segmentation of patterns in the image field | G06V 10/26 |
| Local image operators for image or video recognition or understanding, e.g. median filtering | G06V 10/36 |
| Enhancement or restoration for general image processing | G06T 5/00 |
Glossary
| DCT | discrete cosine transform |
| FFT | fast Fourier transform |
| PDF | probability density function |
| SNR | signal to noise ratio |