# US 2025/0147726 A1 · Methods for and devices thereof for generating a denoised data set

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0147726 A1
- Document ID: US20250147726A1
- Status: Published application
- Kind: A1
- Application number: 18/936,580
- Filed: 2024-11-04
- Published: 2025-05-08
- Earliest claimed: 2023-11-03
- Applicants: Curia IP Holdings, LLC
- Inventors: Richard B. McClurg
- Web page: https://patentgrep.com/patent/US20250147726A1

## CPC

- G06F 7/50: Adding; Subtracting (G06F7/483 - G06F7/491, G06F7/544 - G06F7/556 take precedence)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method for generating a denoised data set from a data set comprising a signal and Poisson noise is disclosed. The method includes applying, by a data set denoising computing device, a Haar transform to the data set to generate a Haar transformed data set. The Haar transformed data set is denoised using a thresholding rule based on the Haar transformed data set to remove the Poisson noise from the signal. A reverse Haar transform is applied to the denoised Haar transformed data set to generate the denoised data set. A data set denoising computing device and non-transitory computer readable medium for performing the method are also disclosed.

## Claims

### Claim 1

A method for generating a denoised data set from a data set comprising a signal and Poisson noise, the method comprising:
applying, by a data set denoising computing device, a Haar wavelet transform to the data set to generate a wavelet transformed data set comprising a plurality of sum values for consecutive pairs of intensities and a second data subset comprising a plurality of difference values for consecutive pairs of intensities;
denoising, by the data set denoising computing device, the wavelet transformed data set using a thresholding rule based on comparing each of the difference values to corresponding sum values, to determine if the difference values are statistically significant based on the corresponding sum values, to remove the Poisson noise from the signal; and
applying, by the data set denoising computing device, a reverse Haar wavelet transform to the denoised wavelet transformed data set to generate the denoised data set.

### Claim 2 (depends on 1)

The method of claim 1, wherein the wavelet transformation is un-normalized.

### Claim 3 (depends on 1)

The method of claim 1 further comprising:
applying, by the data set denoising computing device, the wavelet transform iteratively to a series of data sets based on the data set to generate a plurality of wavelet transformed data sets;
denoising, by the data set denoising computing device, each of the plurality of wavelet transformed data set using the thresholding rule; and
applying, by the data set denoising computing device, the reverse wavelet transform iteratively to each of the denoised wavelet transformed data sets to generate the denoised data set.

### Claim 4 (depends on 3)

The method of claim 3 further comprising:
applying, by the data denoising computing device, a cycle spinning process to form the denoised data set.

### Claim 5 (depends on 4)

The method of claim 4, wherein a depth of the cycle spinning is based on a longest plateau length after a first iteration.

### Claim 6 (depends on 1)

The method of claim 1 further comprising:
providing, by the data set denoising computing device, the denoised data set for display on a user interface.

### Claim 7 (depends on 1)

The method of claim 1, wherein the denoising comprises comparing an absolute value of the difference value to a square root of the corresponding sum value.

### Claim 8 (depends on 7)

The method of claim 7, wherein the thresholding rule is a hard thresholding rule.

### Claim 9 (depends on 7)

The method of claim 7, wherein the thresholding rule is a soft thresholding rule.

### Claim 10 (depends on 1)

The method of claim 1, wherein the denoising comprises comparing a square of the difference value to the corresponding sum value.

### Claim 11 (depends on 10)

The method of claim 10, wherein the thresholding rule is a hard thresholding rule.

### Claim 12 (depends on 10)

The method of claim 10, wherein the thresholding rule is a soft thresholding rule.

### Claim 13 (depends on 1)

The method of claim 1, wherein the signal comprises a powder diffraction pattern.

### Claim 14 (depends on 13)

The method of claim 13, wherein the powder diffraction pattern is an x-ray, neutron, or electron diffraction pattern.

### Claim 15 (depends on 1)

The method of claim 1, wherein the signal comprises two-dimensional image data.

### Claim 16

A data set denoising computing device, comprising memory comprising programmed instructions stored thereon and one or more processors configured to execute the stored programmed instructions to:
apply a Haar wavelet transform to the data set to generate a wavelet transformed data set comprising a plurality of sum values for consecutive pairs of intensities and a second data subset comprising a plurality of difference values for consecutive pairs of intensities;
denoise the wavelet transformed data set using a thresholding rule based on comparing each of the difference values to corresponding sum values, to determine if the difference values are statistically significant based on the corresponding sum values, to remove the Poisson noise from the signal; and
apply a reverse Haar wavelet transform to the denoised wavelet transformed data set to generate the denoised data set.

### Claim 17 (depends on 16)

The data denoising computing device of claim 16, wherein the memory further comprises additional programmed instructions stored thereon that when executed by the one or more processors cause the one or more processors to:
apply the wavelet transform iteratively to a series of data sets based on the data set to generate a plurality of wavelet transformed data sets;
denoise each of the plurality of wavelet transformed data set using the thresholding rule; and
apply the reverse wavelet transform iteratively to each of the denoised wavelet transformed data sets to generate the denoised data set.

### Claim 18 (depends on 17)

The data denoising computing device of claim 17, wherein the memory further comprises additional programmed instructions stored thereon that when executed by the one or more processors cause the one or more processors to:
apply a cycle spinning process to form the denoised data set.

### Claim 19 (depends on 17)

The data denoising computing device of claim 17, wherein the memory further comprises additional programmed instructions stored thereon that when executed by the one or more processors cause the one or more processors to:
provide the denoised data set for display on a user interface.

### Claim 20

A non-transitory computer readable medium having stored thereon instructions for denoising a data set comprising executable code that, when executed by one or more processors, causes the processors to:
apply a Haar wavelet transform to the data set to generate a wavelet transformed data set comprising a plurality of sum values for consecutive pairs of intensities and a second data subset comprising a plurality of difference values for consecutive pairs of intensities;
denoise the wavelet transformed data set using a thresholding rule based on comparing each of the difference values to corresponding sum values, to determine if the difference values are statistically significant based on the corresponding sum values, to remove the Poisson noise from the signal; and
apply a reverse Haar wavelet transform to the denoised wavelet transformed data set to generate the denoised data set.
