# US 2019/0356476 A1 · Method and apparatus for generatng a cover image for steganography

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

- Number: US 2019/0356476 A1
- Document ID: US20190356476A1
- Status: Published application
- Kind: A1
- Application number: 16/482,703
- Filed: 2018-01-31
- Published: 2019-11-21
- Earliest claimed: 2017-01-31
- Assignees: Agency for Science, Technology and Research
- Applicants: Agency for Science, Technology and Research
- Inventors: Lilei ZHENG; Ying ZHANG; Vrizlynn THING
- Web page: https://patentgrep.com/patent/US20190356476A1

## CPC

- H04L 9/0662: {with particular pseudorandom sequence generator}
- G06T 1/0028: {Adaptive watermarking, e.g. Human Visual System [HVS]-based watermarking}
- G09C 5/00: Ciphering apparatus or methods not provided for in the preceding groups, e.g. involving the concealment or deformation of graphic data such as designs, written or printed messages
- H04K 1/02: by adding a second signal to make the desired signal unintelligible
- H04K 1/06: by transmitting the information or elements thereof at unnatural speeds or in jumbled order or backwards
- G06T 2201/0051: Embedding of the watermark in the spatial domain
- G06T 2201/0062: Embedding of the watermark in text images, e.g. watermarking text documents using letter skew, letter distance or row distance
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G09C: CIPHERING OR DECIPHERING APPARATUS FOR CRYPTOGRAPHIC OR OTHER PURPOSES INVOLVING THE NEED FOR SECRECY
- H04K: SECRET COMMUNICATION; JAMMING OF COMMUNICATION

## Abstract

A method and an apparatus for generating cover images for steganography are provided. The steganographic framework is designed based on an image generation system. The apparatus may encode a message to obtain a binary sequence. The apparatus may obtain a plurality of binary segments of a particular length based on the binary sequence. For each binary segment of the plurality of binary segments, the apparatus may select an image of a semantic content (e.g., a numeral digit) from a dictionary of images of random semantic contents (e.g., random numeral digits) based on the binary segment. The apparatus may combine the selected images to form at least a portion of a cover image denoting a combination of the semantic contents of the selected images (e.g., a plurality of numeral digits).

## Claims

### Claim 1

A method of generating a cover image for hiding a message, the method comprising:
encoding the message to obtain a binary sequence;
obtaining a plurality of binary segments of a particular length based on the binary sequence;
for each binary segment of the plurality of binary segments, selecting an image of a semantic content from a dictionary of images of random semantic contents based on the binary segment; and
combining the selected images to form at least a portion of the cover image denoting a combination of the semantic contents of the selected images.

### Claim 2 (depends on 1)

The method of claim 1, wherein each image in the dictionary corresponds to a binary segment of the particular length.

### Claim 3 (depends on 2)

The method of claim 2, wherein the images of random semantic contents in the dictionary is permutated based on a specified key, wherein each image in the dictionary is associated with the corresponding binary segment of the particular length according to an order of the images of random semantic contents in the dictionary after the permutation.

### Claim 4 (depends on 1)

The method of claim 1, wherein the images of random semantic contents in the dictionary have the same background so that edges of the selected images merge naturally when the selected images are combined.

### Claim 5 (depends on 1)

The method of claim 1, further comprising:
modifying the binary sequence by adding a header binary segment to a beginning of the binary sequence; and
modifying the binary sequence by adding a set of random bits to an end of the binary sequence to make a length of the modified binary sequence an exact multiple of the particular length, wherein the plurality of binary segments are obtained based on the modified binary sequence.

### Claim 6 (depends on 1)

The method of claim 1, wherein each binary segment of the plurality of binary segments is mapped to a predetermined semantic content based on a position of the binary segment in the binary sequence, wherein the selecting of the image for the binary segment comprises:
selecting an image of the predetermined semantic content from a sub-dictionary of the dictionary based on the binary segment, the sub-dictionary comprising images of the predetermined semantic content.

### Claim 7 (depends on 1)

The method of claim 1, wherein the semantic content is a numeral digit and the images of random semantic contents are images of random numeral digits, wherein the combination of the semantic contents of the selected images is a plurality of numeral digits.

### Claim 8

An apparatus for generating a cover image for hiding a message, the apparatus comprising:
a memory; and
at least one processor coupled to the memory and configured to:
encode the message to obtain a binary sequence;
obtain a plurality of binary segments of a particular length based on the binary sequence;
for each binary segment of the plurality of binary segments, select an image of a semantic content from a dictionary of images of random semantic contents based on the binary segment; and
combine the selected images to form at least a portion of the cover image denoting a combination of the semantic contents of the selected images.

### Claim 9 (depends on 8)

The apparatus of claim 8, wherein each image in the dictionary corresponds to a binary segment of the particular length.

### Claim 10 (depends on 9)

The apparatus of claim 9, wherein the images of random semantic contents in the dictionary is permutated based on a specified key, wherein each image in the dictionary is associated with the corresponding binary segment of the particular length according to an order of the images of random semantic contents in the dictionary after the permutation.

### Claim 11 (depends on 8)

The apparatus of claim 8, wherein the images of random semantic contents in the dictionary have the same background so that edges of the selected images merge naturally when the selected images are combined.

### Claim 12 (depends on 8)

The apparatus of claim 8, wherein the at least one processor is further configured to:
modify the binary sequence by adding a header binary segment to a beginning of the binary sequence; and
modify the binary sequence by adding a set of random bits to an end of the binary sequence to make a length of the modified binary sequence an exact multiple of the particular length, wherein the plurality of binary segments are obtained based on the modified binary sequence.

### Claim 13 (depends on 8)

The apparatus of claim 8, wherein each binary segment of the plurality of binary segments is mapped to a predetermined semantic content based on a position of the binary segment in the binary sequence, wherein, to select the image for the binary segment, the at least one processor is configured to:
select an image of the predetermined semantic content from a sub-dictionary of the dictionary based on the binary segment, the sub-dictionary comprising images of the predetermined semantic content.

### Claim 14 (depends on 8)

The apparatus of claim 8, wherein the semantic content is a numeral digit and the images of random semantic contents are images of random numeral digits, wherein the combination of the semantic contents of the selected images is a plurality of numeral digits.

### Claim 15

A computer-readable medium storing computer executable code, comprising instructions for:
encoding a message to obtain a binary sequence;
obtaining a plurality of binary segments of a particular length based on the binary sequence;
for each binary segment of the plurality of binary segments, selecting an image of a semantic content from a dictionary of images of random semantic contents based on the binary segment; and
combining the selected images to form at least a portion of a cover image denoting a combination of the semantic contents of the selected images.

### Claim 16 (depends on 15)

The computer-readable medium of claim 15, wherein each image in the dictionary corresponds to a binary segment of the particular length, wherein the images of random semantic contents in the dictionary is permutated based on a specified key, wherein each image in the dictionary is associated with the corresponding binary segment of the particular length according to an order of the images of random semantic contents in the dictionary after the permutation.

### Claim 17 (depends on 15)

The computer-readable medium of claim 15, wherein the images of random semantic contents in the dictionary have the same background so that edges of the selected images merge naturally when the selected images are combined.

### Claim 18 (depends on 15)

The computer-readable medium of claim 15, the computer executable code further comprises instructions for:
modifying the binary sequence by adding a header binary segment to a beginning of the binary sequence; and
modifying the binary sequence by adding a set of random bits to an end of the binary sequence to make a length of the modified binary sequence an exact multiple of the particular length, wherein the plurality of binary segments are obtained based on the modified binary sequence.

### Claim 19 (depends on 15)

The computer-readable medium of claim 15, wherein each binary segment of the plurality of binary segments is mapped to a predetermined semantic content based on a position of the binary segment in the binary sequence, wherein the instructions for selecting the image for the binary segment comprises instructions for:
selecting an image of the predetermined semantic content from a sub-dictionary of the dictionary based on the binary segment, the sub-dictionary comprising images of the predetermined semantic content.

### Claim 20 (depends on 15)

The computer-readable medium of claim 15, wherein the semantic content is a numeral digit and the images of random semantic contents are images of random numeral digits, wherein the combination of the semantic contents of the selected images is a plurality of numeral digits.