# US 12,182,914 B2 · Image display format conversion method

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

- Number: US 12,182,914 B2
- Document ID: US12182914B2
- Status: Granted
- Kind: B2
- Application number: 18/116,147
- Filed: 2023-03-01
- Published: 2024-05-23
- Granted: 2024-12-31
- Earliest claimed: 2022-11-21
- Assignees: Hyweb Technology Co., Ltd.
- Applicants: Hyweb Technology Co., Ltd.
- Inventors: Chung-Wei Yu; Yu-Yu Lin
- Web page: https://patentgrep.com/patent/US12182914B2

## CPC

- G06T 11/60: Creating or editing images; Combining images with text
- G06T 3/40: Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06T 13/00: Animation
- G06T 13/80: Two-dimensional [2D] animation, e.g. using sprites
- G06V 10/82: using neural networks
- G06T 2210/32: Image data format
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

Disclosed is an image display format conversion method, comprising: a frame recognition step of performing a frame recognition process on a comic page image to obtain a plurality of comic frame images and frame position information; a frame sequence determination step of determining a frame viewing sequence according to a selected regional layout rule; and a frame reassembly step of reassembling and converting, based on the frame viewing sequence, the plurality of comic frame images into a digital media in an animation-like format or a scrolling-comic format.

## Claims

### Claim 1

An image display format conversion method, comprising in sequence:
a frame recognition step of utilizing a trained deep-learning artificial intelligence frame recognition unit to perform a frame recognition process on a comic page image, which is formed by a plurality of comic frames, to obtain a plurality of comic frame images within the comic page image and frame position information corresponding to the respective comic frame images;
a frame sequence determination step of utilizing an image analysis unit to determine a frame viewing sequence of the plurality of comic frame images according to a selected regional layout rule based on the frame position information of the plurality of comic frame images within the comic page image, wherein the selected regional layout rule is one selected from a plurality of regional layout rules relating to different geographical regions; and
a frame reassembly step of utilizing an image processing unit to reassemble and convert, based on the frame viewing sequence, the plurality of comic frame images into a digital media in an animation-like format or a scrolling-comic format, wherein the digital media in the animation-like format is formed by arranging the plurality of comic frame images in an animation according to an animation frame display sequence corresponding to the frame viewing sequence, the digital media in the scrolling-comic format is formed by arranging the plurality of comic frame images in a display page in the frame viewing sequence along a predetermined page scrolling direction.

### Claim 2 (depends on 1)

The image display format conversion method as claimed in claim 1, further comprising, before the frame recognition step, an image capture step of obtaining the comic page image by scanning a paper comic with a scanning unit.

### Claim 3 (depends on 1)

The image display format conversion method as claimed in claim 1, wherein in the frame recognition step, the trained deep-learning artificial intelligence frame recognition unit performs the frame recognition process by using a YOLO-based neural network object detection model.

### Claim 4 (depends on 1)

The image display format conversion method as claimed in claim 1, wherein in the frame recognition step, each of the comic frame images is a standard frame image, a broken frame image, or an out-of-frame frame image, wherein the standard frame image is the comic frame image having a complete and unbroken frame border, the broken frame image is the comic frame image having the frame border broken on at least one side thereof, and the out-of-frame frame image is the comic frame image having at least a graphical part thereof outside of the frame border.

### Claim 5 (depends on 1)

The image display format conversion method as claimed in claim 1, wherein in the frame recognition step, the frame position information is coordinate information about four corners of the comic frame image.

### Claim 6 (depends on 1)

The image display format conversion method as claimed in claim 1, wherein in the frame sequence determination step, the plurality of regional layout rules includes a European-American comic layout rule relating to European and American regions and a Japanese comic layout rule relating to Japanese region.

### Claim 7 (depends on 1)

The image display format conversion method as claimed in claim 1, further comprising, before the frame reassembly step, a frame resizing step of utilizing the image processing unit to resize each of the comic frame images to a size within a predetermined display size range.

### Claim 8 (depends on 7)

The image display format conversion method as claimed in claim 7, wherein in the frame resizing step, the plurality of comic frame images is resized to have equal width and/or equal height.

### Claim 9 (depends on 1)

The image display format conversion method as claimed in claim 1, wherein in the frame reassembly step, the predetermined page scrolling direction is a vertical direction or a horizontal direction.