IP Library Granted Patent US 12,106,450
Granted Patent B2
US 12,106,450 · App. 17/514,054 · Granted Oct 1, 2024

Methods and devices for generating a blurred image

Inventor: Peng Yu (Montreal, CA)
Assignee: Shopify Inc.
G06T5/70G06F40/143G06F40/166G06T3/40G06T5/10G06T5/20G06T9/00G06T2207/20052
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,106,450
App. No.
17/514,054
Granted
Oct 1, 2024
Kind
B2
Abstract

A computer-implemented method and system for generating a blurred image from an original image. The method and system generate the blurred image using a process that enables fast efficient decoding of the compact encoded blurred image by a client device. The method may include transforming an original image to a block of coefficients in a frequency domain, low-pass filtering the block of coefficients in the frequency domain to produce a block of filtered coefficients, inverse transforming the block of filtered coefficients to produce a blurred image in a pixel domain, encoding the blurred image using a lossy-compression image encoder to produce an encoded blurred image, and transmitting the encoded blurred image to a client device for reconstruction and display by the client device.

Claims (38)

1. A computer-implemented method, comprising:

transforming an original image to a block of coefficients in a frequency domain using a spectral transform, wherein the spectral transform is selected to be a same spectral transform used in a particular lossy-compression image encoding;

low-pass filtering the block of coefficients in the frequency domain to produce a block of filtered coefficients;

inverse transforming the block of filtered coefficients to produce a blurred image in a pixel domain using an inverse transform to the spectral transform;

encoding the blurred image using the particular lossy-compression image encoding to produce an encoded blurred image, wherein the particular lossy-compression image encoding includes transforming the blurred image using the same spectral transform; and

transmitting the encoded blurred image to a client device for reconstruction and display by the client device.

2. The method of claim 1 , wherein the spectral transform is a two-dimensional discrete-cosine transform (DCT).

3. The method of claim 2 , wherein the original image is of size N×M pixels and the two-dimensional DCT is an N×M DCT operation.

4. The method of claim 2 , wherein the particular lossy-compression image encoding is JPEG.

5. The method of claim 2 , wherein the encoded blurred image is in JFIF, EXIF, or PJP format.

6. The method of claim 1 , wherein the low-pass filtering includes applying a mask to the block of coefficients whereby coefficients outside a selected subset defined by the mask are set to zero.

7. The method of claim 6 , wherein the selected subset includes a DC coefficient in an upper left corner of the block of coefficients and a plurality of coefficients adjacent to the DC coefficient.

8. The method of claim 7 , wherein the selected subset includes a quarter or fewer of the coefficients in the block of coefficients.

9. The method of claim 7 , wherein the selected subset includes a sub-block smaller than the block of coefficients and positioned in the upper left corner of the block of coefficients.

10. The method of claim 1 , further comprising first down-scaling a full-size image in the pixel domain to obtain the original image.

11. The method of claim 1 , wherein encoding includes outputting the encoded blurred image, and wherein transmitting includes encoding the encoded blurred image as a string and inserting the string in a markup language document transmitted to the client device.

12. The method of claim 11 , wherein the markup language document includes a webpage.

13. The method of claim 12 , wherein the webpage further includes x and y dimensions associated with the string, and a scaling factor for upscaling a reconstructed blurred image from the string based on the dimensions.

14. The method of claim 13 , wherein the webpage further includes a reference to a high resolution image file corresponding to the original image, and instructions to replace display of the reconstructed blurred image with a reconstructed high resolution image obtained by decoding the high resolution image file once available, the x and y dimensions corresponding to dimensions of the high resolution image file.

15. A computing system, comprising:

a processor; and

a memory storing computer-executable instructions that, when executed by the processor, are to cause the processor to:

transform an original image to a block of coefficients in a frequency domain using a spectral transform, wherein the spectral transform is selected to be a same spectral transform used in a particular lossy-compression image encoding;

low-pass filter the block of coefficients in the frequency domain to produce a block of filtered coefficients;

inverse transform the block of filtered coefficients to produce a blurred image in a pixel domain using an inverse transform to the spectral transform;

encode the blurred image using the particular lossy-compression image encoding to produce an encoded blurred image, wherein the particular lossy-compression image encoding includes transforming the blurred image using the same spectral transform; and

transmit the encoded blurred image to a client device for reconstruction and display by the client device.

16. The computing system of claim 15 , wherein the spectral transform is a two-dimensional discrete-cosine transform (DCT), and wherein the original image is of size N×M pixels and the two-dimensional DCT is an N×M DCT operation.

17. The computing system of claim 15 , wherein the instructions, when executed, are to cause the processor to low-pass filter by applying a mask to the block of coefficients whereby coefficients outside a selected subset defined by the mask are set to zero.

18. The computing system of claim 17 , wherein the selected subset includes a DC coefficient in an upper left corner of the block of coefficients and a plurality of coefficients adjacent to the DC coefficient.

19. The computing system of claim 15 , wherein the instructions, when executed, are to further cause the processor to first down-scale a full-size image in the pixel domain to obtain the original image.

20. The computing system of claim 15 , wherein the instructions, when executed, are to cause the processor to encode by outputting the encoded blurred image, and to transmit by encoding the encoded blurred image as a string and inserting the string in a markup language document transmitted to the client device.

21. A non-transitory, computer-readable medium storing computer-executable instructions that, when executed by a processor, are to cause the processor to:

transform an original image to a block of coefficients in a frequency domain using a spectral transform, wherein the spectral transform is selected to be a same spectral transform used in a particular lossy-compression image encoding;

low-pass filter the block of coefficients in the frequency domain to produce a block of filtered coefficients;

inverse transform the block of filtered coefficients to produce a blurred image in a pixel domain using an inverse transform to the spectral transform;

encode the blurred image using the particular lossy-compression image encoding to produce an encoded blurred image, wherein the particular lossy-compression image encoding includes transforming the blurred image using the same spectral transform; and

transmit the encoded blurred image to a client device for reconstruction and display by the client device.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 2, 2021
From: YU, PENG
To: SHOPIFY INC.
Reel/Frame 057991/0386 →
Continuity (1)
Related Publication 20230140051A1 · May 4, 2023