# US 12,008,829 B2 · System and method for improved OCR efficacy through image segmentation

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

- Number: US 12,008,829 B2
- Document ID: US12008829B2
- Status: Granted
- Kind: B2
- Application number: 17/672,944
- Filed: 2022-02-16
- Published: 2023-08-17
- Granted: 2024-06-11
- Earliest claimed: 2022-02-16
- Assignees: Vastec, Inc.
- Applicants: Vastec, Inc.
- Inventors: Willem H. Reinpoldt, III
- Web page: https://patentgrep.com/patent/US12008829B2

## CPC

- G06V 30/414: Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
- G06V 30/146: Aligning or centring of the image pick-up or image-field
- G06V 30/158: {using character size, text spacings or pitch estimation}
- G06V 30/412: Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method to improve the efficacy of optical character recognition (OCR) includes scanning an electronically stored representation of a whole or partial document, identifying an image having text in the electronically stored representation of a whole or partial document, identifying the text within the image, and generating a plurality of bounding boxes around the identified text using blob detection. The method also includes grouping together certain text bounding boxes of the plurality of text bounding boxes that are vertically aligned with each other to generate a plurality of aligned text bounding boxes and performing OCR on the aligned text bounding boxes to generate a plurality of OCR groups of text. In addition, the method includes generating a resultant representation of a whole or partial document electronically using the plurality of OCR groups of text and saving the resultant representation of a whole or partial document electronically.

## Claims

### Claim 1

A system to increase accuracy of optical character recognition (OCR) software, the system comprising:
a processor; and
a memory coupled to the processor, the processor configured to
scan an electronically stored representation of a whole or partial document;
identify an image having text in the electronically stored representation of a whole or partial document;
identify text within the image;
generate a plurality of bounding boxes around the identified text using blob detection;
group together certain identified text of the plurality of identified text whose bounding boxes are vertically aligned with each other to generate a plurality of aligned text;
perform OCR on text whose bounding boxes are vertically aligned to generate a plurality of OCR groups of text;
generate a resultant representation of a whole or partial document electronically using the plurality of OCR groups of text; and
save the resultant representation of a whole or partial document electronically;
wherein the processor is configured to create one or more images or image layers of identified text whose bounding boxes are vertically aligned; and
wherein additional identified text is added to the image or image layer having bounding boxes vertically aligned with the identified text or, failing to find a suitable image or image layer, to create one or more new images or image layers for the additional identified text.

### Claim 2 (depends on 1)

The system of claim 1, wherein the processor is configured to OCR the one or more images or image layers of text separately from the other images or image layers to generate the plurality of OCR groups of text.

### Claim 3 (depends on 1)

The system of claim 1, wherein the processor is configured to create an array of one or more groups of identified text whose bounding boxes are vertically aligned.

### Claim 4 (depends on 3)

The system of claim 3, wherein additional identified text is added to the array group having bounding boxes vertically aligned with the additional identified text or, failing to find a suitable array group, to create one or more new array groups for the additional identified text.

### Claim 5 (depends on 4)

The system of claim 4, wherein the processor is configured to OCR the one or more array groups of text separately from the one or more new array groups to generate the plurality of OCR groups of text.

### Claim 6 (depends on 1)

The system of claim 1, wherein the plurality of aligned bounding boxes each includes a top, bottom, left, right and baseline.

### Claim 7

A non-transitory processor readable medium for operating a processor to increase accuracy of optical character recognition (OCR) software, and with the non-transitory computer readable medium having a plurality of computer executable instructions to cause the processor coupled to a memory to:
scan an electronically stored representation of a whole or partial document;
identify an image having text in the electronically stored representation of a whole or partial document;
identify text identified within the image;
generate a plurality of bounding boxes around the identified text using blob detection;
group together certain identified text of the plurality of identified text whose bounding boxes are vertically aligned with each other to generate a plurality of aligned text;
perform OCR on text whose bounding boxes are vertically aligned to generate a plurality of OCR groups of text;
generate a resultant representation of a whole or partial document electronically using the plurality of OCR groups of text; and
save the resultant representation of a whole or partial document electronically;
wherein the processor is configured to create one or more images or image layers of identified text whose bounding boxes share similar vertical alignment; and
wherein additional identified text is added to that image or image layer having bounding boxes vertically aligned with the additional identified text or, failing to find a suitable image or image layer, to create one or more new images or image layers for the additional identified text.

### Claim 8 (depends on 7)

The non-transitory computer readable medium of claim 7, wherein the processor is configured to OCR the one or more images or image layers of text separately from the other images or image layers to generate the plurality of OCR groups of text.

### Claim 9 (depends on 7)

The non-transitory computer readable medium of claim 7, wherein the processor is configured to create an array of one or more groups of identified text whose bounding boxes share similar vertical alignment.

### Claim 10 (depends on 9)

The non-transitory computer readable medium of claim 9, wherein additional identified text is added to that array group having bounding boxes vertically aligned with the additional identified text or, failing to find a suitable array group, to create one or more new array groups for the additional identified text.

### Claim 11 (depends on 10)

The non-transitory computer readable medium of claim 10, wherein the processor is configured to OCR the one or more array groups of text separately form the other array groups to generate the plurality of OCR groups of text.

### Claim 12 (depends on 7)

The non-transitory computer readable medium of claim 7, wherein the plurality of aligned bounding boxes each includes a top, bottom, left, right and baseline.