# US 2020/0304678 A1 · Semi-Transparent Embedded Watermarks

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

- Number: US 2020/0304678 A1
- Document ID: US20200304678A1
- Status: Published application
- Kind: A1
- Application number: 16/840,909
- Filed: 2020-04-06
- Published: 2020-09-24
- Earliest claimed: 2017-03-14
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Abdullah Hassan Gharaibeh; Michal Dabrowski; Ryan Matthew Haggarty; Igor Foox-Rapoport; Wan Wang; Duncan Geoffrey Hector Wood; Dany Kuminov; Matthew Young-Lai; Bhavin Vyas; George Jacob Levitte; Jean Semere
- Web page: https://patentgrep.com/patent/US20200304678A1

## CPC

- H04N 1/32331: {Fragile embedding or watermarking}
- G06F 21/16: Program or content traceability, e.g. by watermarking
- G06T 1/0021: {Image watermarking}
- G06T 1/0028: {Adaptive watermarking, e.g. Human Visual System [HVS]-based watermarking}
- H04N 1/32203: {Spatial or amplitude domain methods (H04N1/32309 takes precedence)}
- H04N 1/32208: {involving changing the magnitude of selected pixels, e.g. overlay of information or super-imposition (H04N1/32219, H04N1/32224 take precedence)}
- H04N 1/32229: {with selective or adaptive application of the additional information, e.g. in selected regions of the image (H04N1/32213 takes precedence)}
- H04N 1/32251: {in multilevel data, e.g. greyscale or continuous tone data}
- H04N 1/32293: {Repeating the additional information in a regular pattern}
- H04N 1/32309: {in colour image data}
- H04N 19/423: characterised by memory arrangements (H04N19/433 takes precedence)
- H04N 19/467: characterised by the embedded information being invisible, e.g. watermarking
- H04N 19/65: using error resilience
- H04N 21/42684: {Client identification by a unique number or address, e.g. serial number, MAC address, socket ID (network arrangements, protocols or services for addressing or naming H04L61/00)}
- H04N 21/8358: involving watermark {(protecting executable software by watermarking G06F21/16; image watermarking in general G06T1/0021; watermarks inserted in still images for transmission purposes H04N1/32144; inserting watermarks during video coding H04N19/467)}
- G06T 2201/0051: Embedding of the watermark in the spatial domain
- G06T 2201/0083: whereby only watermarked image required at decoder, e.g. source-based, blind, oblivious
- H04N 2201/3233: of authentication information, e.g. digital signature, watermark
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A watermark image may be generated that includes a first set of encoded pixels each of which is assigned a first transparency value and a second set of encoded pixels each of which is assigned a second transparency value, the second transparency level being different from the first transparency level. The encoded pixels may be distributed among a set of blank pixels such that each encoded pixel neighbors one or more blank pixels in the watermark image, and in particular at least two blank pixels in the watermark image. Herein, each blank pixel may be assigned the second transparency value. The watermark image may be overlaid and blended over a background source image to create an encoded source image. A decoder system may recover encoded information from the encoded source image.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A method, comprising:
receiving an encoded image at a computing system, wherein the encoded image includes a set of encoded pixels, and each encoded pixel is associated with a respective set of one or more non-encoded pixels located at pre-defined positions of the encoded image relative to the encoded pixel;
for each encoded pixel in the set of encoded pixels, decoding a value represented by the encoded pixel by comparing a color of the encoded pixel to colors of the respective set of non-encoded pixels located in the pre-defined positions relative to the encoded pixel; and
using the values decoded from the set of encoded pixels to recover a message that was encoded in the encoded image.

### Claim 22 (depends on 21)

The method of claim 21, wherein the encoded image results from blending a semi-transparent watermark image over a background source image, wherein the semi-transparent watermark image contains an initial set of encoded pixels and an initial set of non-encoded pixels.

### Claim 23 (depends on 22)

The method of claim 22, wherein:
the initial set of encoded pixels in the semi-transparent watermark image each encodes one of a first value or a second value;
pixels from the initial set of encoded pixels that are encoded with the first value are assigned a first transparency value;
pixels from the initial set of encoded pixels that are encoded with the second value are assigned a second transparency value; and
pixels from the initial set of non-encoded pixels are assigned the second transparency value.

### Claim 24 (depends on 23)

The method of claim 23, wherein:
pixels from the initial set of encoded pixels that are encoded with the first value are colored a first color; and
pixels from the initial set of encoded pixels that are encoded with the second value are colored a second color.

### Claim 25 (depends on 24)

The method of claim 24, wherein the first color is black, the first transparency value is a semi-transparent value, and the second transparency value is a fully transparent value.

### Claim 26 (depends on 21)

The method of claim 21, wherein the respective set of non-encoded pixels for each encoded pixel in the encoded image are located adjacent to the encoded pixel.

### Claim 27 (depends on 21)

The method of claim 21, wherein using the values decoded from the set of encoded pixels to recover the message that was encoded in the encoded image comprises recovering a watermark from the encoded image.

### Claim 28 (depends on 21)

The method of claim 21, wherein decoding the value represented by the encoded pixel by comparing a color of the encoded pixel to colors of the respective set of non-encoded pixels located in the pre-defined positions relative to the encoded pixel comprises (i) assigning a first decoded value to the encoded pixel if the color of the encoded pixel is determined to be within a defined tolerance of the colors of the respective set of non-encoded pixels, or (ii) assigning a second decoded value to the encoded pixel if the color of the encoded pixel is determined not to be within the defined tolerance of the colors of the respective set of non-encoded pixels.

### Claim 29 (depends on 21)

The method of claim 21, wherein decoding the value represented by the encoded pixel by comparing a color of the encoded pixel to colors of the respective set of non-encoded pixels located in the pre-defined positions relative to the encoded pixel comprises:
determining an average of the colors of the respective set of non-encoded pixels; and
comparing the color of the encoded pixel to the average of the colors of the respective set of non-encoded pixels.

### Claim 30 (depends on 21)

The method of claim 21, wherein decoding the value represented by the encoded pixel by comparing a color of the encoded pixel to colors of the respective set of non-encoded pixels located in the pre-defined positions relative to the encoded pixel comprises:
comparing the color of the encoded pixel to the respective color of each non-encoded pixel in the respective set of non-encoded pixels; and
assigning a first decoded value or a second decoded value to the encoded pixel according to whether the color of the encoded pixel is within a defined tolerance of the respective color of at least a threshold number of non-encoded pixels in the respective set of non-encoded pixels.

### Claim 31

A system, comprising:
one or more processors; and
one or more computer-readable media having instructions stored thereon that, when executed by the one or more processors, cause performance of operations comprising:
receiving an encoded image at a computing system, wherein the encoded image includes a set of encoded pixels, and each encoded pixel is associated with a respective set of one or more non-encoded pixels located at pre-defined positions of the encoded image relative to the encoded pixel;
for each encoded pixel in the set of encoded pixels, decoding a value represented by the encoded pixel by comparing a color of the encoded pixel to colors of the respective set of non-encoded pixels located in the pre-defined positions relative to the encoded pixel; and
using the values decoded from the set of encoded pixels to recover a message that was encoded in the encoded image.

### Claim 32 (depends on 31)

The system of claim 31, wherein the encoded image results from blending a semi-transparent watermark image over a background source image, wherein the semi-transparent watermark image contains an initial set of encoded pixels and an initial set of non-encoded pixels.

### Claim 33 (depends on 32)

The system of claim 32, wherein:
the initial set of encoded pixels in the semi-transparent watermark image each encodes one of a first value or a second value;
pixels from the initial set of encoded pixels that are encoded with the first value are assigned a first transparency value;
pixels from the initial set of encoded pixels that are encoded with the second value are assigned a second transparency value; and
pixels from the initial set of non-encoded pixels are assigned the second transparency value.

### Claim 34 (depends on 33)

The system of claim 33, wherein:
pixels from the initial set of encoded pixels that are encoded with the first value are colored a first color; and
pixels from the initial set of encoded pixels that are encoded with the second value are colored a second color.

### Claim 35 (depends on 34)

The system of claim 34, wherein the first color is black, the first transparency value is a semi-transparent value, and the second transparency value is a fully transparent value.

### Claim 36 (depends on 31)

The system of claim 31, wherein the respective set of non-encoded pixels for each encoded pixel in the encoded image are located adjacent to the encoded pixel.

### Claim 37 (depends on 31)

The system of claim 31, wherein using the values decoded from the set of encoded pixels to recover the message that was encoded in the encoded image comprises recovering a watermark from the encoded image.

### Claim 38 (depends on 31)

The system of claim 31, wherein decoding the value represented by the encoded pixel by comparing a color of the encoded pixel to colors of the respective set of non-encoded pixels located in the pre-defined positions relative to the encoded pixel comprises (i) assigning a first decoded value to the encoded pixel if the color of the encoded pixel is determined to be within a defined tolerance of the colors of the respective set of non-encoded pixels, or (ii) assigning a second decoded value to the encoded pixel if the color of the encoded pixel is determined not to be within the defined tolerance of the colors of the respective set of non-encoded pixels.

### Claim 39 (depends on 31)

The system of claim 31, wherein decoding the value represented by the encoded pixel by comparing a color of the encoded pixel to colors of the respective set of non-encoded pixels located in the pre-defined positions relative to the encoded pixel comprises:
determining an average of the colors of the respective set of non-encoded pixels; and
comparing the color of the encoded pixel to the average of the colors of the respective set of non-encoded pixels.

### Claim 40

One or more non-transitory computer-readable media having instructions stored thereon that, when executed by the one or more processors, cause performance of operations comprising:
receiving an encoded image at a computing system, wherein the encoded image includes a set of encoded pixels, and each encoded pixel is associated with a respective set of one or more non-encoded pixels located at pre-defined positions of the encoded image relative to the encoded pixel;
for each encoded pixel in the set of encoded pixels, decoding a value represented by the encoded pixel by comparing a color of the encoded pixel to colors of the respective set of non-encoded pixels located in the pre-defined positions relative to the encoded pixel; and
using the values decoded from the set of encoded pixels to recover a message that was encoded in the encoded image.
