# US 10,503,994 B2 · Device and method for performing optical character recognition

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

- Number: US 10,503,994 B2
- Document ID: US10503994B2
- Status: Granted
- Kind: B2
- Application number: 16/195,394
- Filed: 2018-11-19
- Published: 2019-05-23
- Granted: 2019-12-10
- Earliest claimed: 2014-07-10
- Assignees: Sanofi-Aventis Deutschland GmbH
- Applicants: Sanofi-Aventis Deutschland GmbH
- Inventors: Dietmar Hammen
- Web page: https://patentgrep.com/patent/US10503994B2

## CPC

- G06V 30/1423: {the instrument generating sequences of position coordinates corresponding to handwriting (preprocessing or recognising digital ink G06V30/32)}
- G06V 30/15: {Cutting or merging image elements, e.g. region growing, watershed or clustering-based techniques}
- G06V 30/10: Character recognition
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method of performing character isolation in an optical character recognition process, the method comprising receiving image data representing one or more character columns, determining a number of black pixels in each column of the image data, defining a vertical separation threshold which is a maximum number of black pixels in a column, dividing the columns into different pixel groups and groups of excluded columns by excluding any columns with a number of black pixels below the vertical separation threshold, identifying the pixel group representing the left most character column in the image data, determining whether there are one or two pixel groups representing character columns in the image data and, if it is determined that there are two pixel groups representing character columns, using a predetermined width value for a right most character column in order to identify a right hand boundary of the right most character column.

## Claims

### Claim 1

A method of performing character isolation in an optical character recognition process, the method comprising:
receiving image data representing one or more character columns;
determining a respective number of black pixels in each column in the one or more character columns of the image data;
defining a vertical separation threshold which is a maximum number of black pixels in a column;
dividing the character columns into different pixel groups and groups of excluded columns by excluding any column with the respective number of black pixels below the vertical separation threshold; and
identifying the pixel group representing a left most character column in the image data, further comprising:
identifying a left most group of excluded columns;
determining that a pixel group immediately to a right side of the left most group of excluded columns is below a minimum digit width threshold; and
excluding the pixel group immediately to the right side of the left most group of excluded columns.

### Claim 2 (depends on 1)

The method according to claim 1, comprising defining a second pixel group to the right side of the left most group of excluded columns as the left most character column in the image data.

### Claim 3 (depends on 1)

The method according to claim 1, comprising determining whether there are one or two pixel groups representing character columns in the image data.

### Claim 4 (depends on 3)

The method according to claim 3, wherein determining whether there are one or two pixel groups representing character columns in the image data comprises determining a width of the left most group of excluded columns.

### Claim 5 (depends on 4)

The method according to claim 4, wherein in response to determining that the width of the left most group of excluded columns is below a maximum left margin threshold value, determining that there are two pixel groups representing character columns in the image data.

### Claim 6 (depends on 1)

The method according to claim 1, the method further comprising determining a width of the left most character column in the image data.

### Claim 7 (depends on 6)

The method according to claim 6, the method further comprising using the determined width of the left most character column in the image data to determine whether the left most character column comprises exclusively narrow numbers or includes wide numbers.

### Claim 8 (depends on 7)

The method according to claim 7, wherein if it is determined that the left most character column comprises exclusively narrow numbers, setting a maximum valid dose result to “19”.

### Claim 9 (depends on 1)

The method according to claim 1, the method further comprising excluding any pixel group touching a left hand border of the image.

### Claim 10 (depends on 1)

The method according to claim 1, the method further comprising identifying a left hand boundary of a right most character column by identifying a group of excluded columns located between the left most character column and the right most character columns.

### Claim 11 (depends on 1)

The method according to claim 1, the method further comprising determining that the left most character column is wider than a maximum digit width threshold value and, in response, determining that numbers in the image data are in a range of 8 to 10.

### Claim 12

A processor for performing character isolation in an optical character recognition process, the processor configured to:
receive image data representing one or more character columns;
determine a respective number of black pixels in each column in the one or more character columns of the image data;
define a vertical separation threshold which is a maximum number of black pixels in a column;
divide the character columns into different pixel groups and groups of excluded columns by excluding any column with the respective number of black pixels below the vertical separation threshold; and
identify the pixel group representing a left most character column in the image data by:
identifying a left most group of excluded columns;
determining that a pixel group immediately to a right side of the left most group of excluded columns is below a minimum digit width threshold; and
excluding the pixel group immediately to the right side of the left most group of excluded columns.

### Claim 13 (depends on 12)

The processor according to claim 12, wherein the processor is configured to define a second pixel group to the right side of the left most group of excluded columns as the left most character column in the image data.

### Claim 14 (depends on 12)

The processor according to claim 12, wherein the processor is configured to determine whether there are one or two pixel groups representing character columns in the image data.

### Claim 15 (depends on 14)

The processor according to claim 14, wherein the processor is configured to determine whether there are one or two pixel groups representing character columns in the image data by determining a width of the left most group of excluded columns.

### Claim 16 (depends on 15)

The processor according to claim 15, wherein in response to determining that the width of the left most group of excluded columns is below a maximum left margin threshold value, determining that there are two pixel groups representing character columns in the image data.

### Claim 17

A supplemental device for attachment to an injection device, the supplemental device comprising:
an optical sensor configured to capture an image of one or more numbers present on a moveable component of the injection device; and
a processor configured to:
receive image data representing one or more character columns;
determine a respective number of black pixels in each column in the one or more character columns of the image data;
define a vertical separation threshold which is a maximum number of black pixels in a column;
divide the character columns into different pixel groups and groups of excluded columns by excluding any column with the respective number of black pixels below the vertical separation threshold; and
identify the pixel group representing a left most character column in the image data by:
identifying a left most group of excluded columns;
determining that a pixel group immediately to a right side of the left most group of excluded columns is below a minimum digit width threshold; and
excluding the pixel group immediately to the right side of the left most group of excluded columns.

### Claim 18 (depends on 17)

The supplemental device according to claim 17, wherein the processor is configured to define a second pixel group to the right side of the left most group of excluded columns as the left most character column in the image data.

### Claim 19 (depends on 17)

The supplemental device according to claim 17, wherein the processor is configured to determine whether there are one or two pixel groups representing character columns in the image data.

### Claim 20 (depends on 17)

The supplemental device according to claim 17, wherein the processor is configured to determine whether there are one or two pixel groups representing character columns in the image data by determining a width of the left most group of excluded columns.