# US 2016/0253794 A1 · Distinguishing Between Stock Keeping Units Using Marker Based Methodology

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

- Number: US 2016/0253794 A1
- Document ID: US20160253794A1
- Status: Published application
- Kind: A1
- Application number: 15/152,812
- Filed: 2016-05-12
- Published: 2016-09-01
- Earliest claimed: 2014-12-23
- Assignees: Ricoh Company, Ltd.
- Inventors: Bharathi Shekar; Sri Kaushik Pavani; Anshul Garg
- Web page: https://patentgrep.com/patent/US20160253794A1

## CPC

- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q 10/08724: {by shelf level inventory management, e.g. planograms}
- G06T 7/0008: {checking presence/absence}
- G06T 7/001: {using an image reference approach}
- G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215)
- G06T 7/194: involving foreground-background segmentation
- G06T 7/60: Analysis of geometric attributes
- G06V 10/768: {using context analysis, e.g. recognition aided by known co-occurring patterns}
- G06T 2207/30108: Industrial image inspection
- G06T 2207/30128: Food products
- G06T 2207/30204: Marker
- G06V 20/68: Food, e.g. fruit or vegetables
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The disclosure includes a system and method for distinguishing between stock keeping units of similar appearance that vary in size. An image recognition application receives an image depicting a plurality of items, the image including a reference marker with a known physical dimension. The image recognition application performs image recognition to identify an item in the image and a region of interest for the identified image. The image recognition application further determines a pixel-to-physical dimension ratio using the dimension of a region of interest of the reference marker and the known physical dimension of the reference marker. Finally, the image recognition application determines a stock keeping unit identifier of the identified item in the image based on the pixel-to-physical dimension ratio and a dimension of the region of interest of the identified item.

## Claims

### Claim 1

A method comprising:
receiving a first image including a plurality of items, the plurality of items including a reference marker with a known physical dimension;
performing image recognition to identify an item in the first image and a region of interest of the identified item in the first image;
determining a pixel-to-physical dimension ratio using a pixel dimension of a region of interest of the reference marker and the known physical dimension of the reference marker; and
determining a stock keeping unit identifier of the identified item in the first image based on the pixel-to-physical dimension ratio and a dimension of the region of interest of the identified item.

### Claim 2 (depends on 1)

The method of claim 1, wherein determining the pixel-to-physical dimension ratio further comprises:
retrieving the known physical dimension of the reference marker; and
determining the pixel-to-physical dimension ratio by dividing the dimension of the region of interest of the reference marker by the known physical dimension of the reference marker.

### Claim 3 (depends on 1)

The method of claim 1, wherein determining the stock keeping unit identifier of the identified item in the first image further comprises:
determining a physical dimension corresponding to the identified item by dividing the dimension of the region of interest of the identified item by the pixel-to-physical dimension ratio; and
determining the stock keeping unit identifier of the identified item by using the physical dimension corresponding to the identified item to look up a stock keeping unit identifier in a stock keeping unit table.

### Claim 4 (depends on 1)

The method of claim 1 further comprising:
receiving a second image of the reference marker;
cropping a background region in the second image of the reference marker;
receiving a physical dimension of the reference marker; and
storing the second image of the reference marker with the physical dimension as the known physical dimension.

### Claim 5 (depends on 1)

The method of claim 1, wherein the reference marker is one from the group of an employee identification card, a shelf label, and a Quick Response (QR) code label.

### Claim 6 (depends on 3)

The method of claim 3, wherein the physical dimension corresponding to the identified item is one from the group of: a height, a width, an area, and a diagonal length.

### Claim 7 (depends on 1)

The method of claim 1, wherein a portion of the plurality of items in the first image vary only in size.

### Claim 8 (depends on 1)

The method of claim 1, wherein the pixel-to-physical dimension ratio describes a relationship between a pixel dimension of the reference marker in the first image and the known physical dimension of the reference marker.

### Claim 9

A system comprising;
an image processor configured to:
receive a first image including a plurality of items, the plurality of items including a reference marker with a known physical dimension; and
perform image recognition to identify an item in the first image and a region of interest of the identified item in the first image;
a pixel-to-physical dimension ratio engine coupled to the image processor and configured to determine a pixel-to-physical dimension ratio using a pixel dimension of a region of interest of the reference marker and the known physical dimension of the reference marker; and
a size engine coupled to the pixel-to-physical dimension ratio engine and configured to determine a stock keeping unit identifier of the identified item in the first image based on the pixel-to-physical dimension ratio and a dimension of the region of interest of the identified item.

### Claim 10 (depends on 9)

The system of claim 9, wherein the pixel-to-physical dimension ratio engine, to determine the pixel-to-physical dimension ratio, is further configured to:
retrieve the known physical dimension of the reference marker; and
determine the pixel-to-physical dimension ratio by dividing the dimension of the region of interest of the reference marker by the known physical dimension of the reference marker.

### Claim 11 (depends on 9)

The system of claim 9, wherein the size engine, to determine the stock keeping unit identifier of the identified item in the first image, is further configured to:
determine a physical dimension corresponding to the identified item by dividing the dimension of the region of interest of the identified item by the pixel-to-physical dimension ratio; and
determine the stock keeping unit identifier of the identified item by using the physical dimension corresponding to the identified item to look up a stock keeping unit identifier in a stock keeping unit table.

### Claim 12 (depends on 9)

The system of claim 9, wherein the size engine is further configured to:
receive a second image of the reference marker;
crop a background region in the second image of the reference marker;
receive a physical dimension of the reference marker; and
store the second image of the reference marker with the physical dimension as the known physical dimension.

### Claim 13 (depends on 9)

The system of claim 9, wherein the reference marker is one from the group of an employee identification card, a shelf label, and a Quick Response (QR) code label.

### Claim 14 (depends on 11)

The system of claim 11, wherein the physical dimension corresponding to the identified item is one from the group of: a height, a width, an area, and a diagonal length.

### Claim 15 (depends on 9)

The system of claim 9, wherein a portion of the plurality of items in the first image vary only in size.

### Claim 16 (depends on 9)

The system of claim 9, wherein the pixel-to-physical dimension ratio describes a relationship between a pixel dimension of the reference marker in the first image and the known physical dimension of the reference marker.

### Claim 17

A computer program product comprising a non-transitory computer readable medium storing a computer readable program, wherein the computer readable program, when executed, causes a computer to perform operations comprising:
receiving an image including a plurality of items, the plurality of items including a reference marker with a known physical dimension;
performing image recognition to identify an item in the image and a region of interest of the identified item in the image;
determining a pixel-to-physical dimension ratio using a pixel dimension of a region of interest of the reference marker and the known physical dimension of the reference marker; and
determining a stock keeping unit identifier of the identified item in the image based on the pixel-to-physical dimension ratio and a dimension of the region of interest of the identified item.

### Claim 18 (depends on 17)

The computer program product of claim 17, wherein determining the pixel-to-physical dimension ratio further comprises:
retrieving the known physical dimension of the reference marker; and
determining the pixel-to-physical dimension ratio by dividing the dimension of the region of interest of the reference marker by the known physical dimension of the reference marker.

### Claim 19 (depends on 17)

The computer program product of claim 17 wherein determining the stock keeping unit identifier of the identified item in the image further comprises:
determining a physical dimension corresponding to the identified item by dividing the dimension of the region of interest of the identified item by the pixel-to-physical dimension ratio; and
determining the stock keeping unit identifier of the identified item by using the physical dimension corresponding to the identified item to look up a stock keeping unit identifier in a stock keeping unit table.

### Claim 20 (depends on 17)

The computer program product of claim 17 wherein the reference marker is one from the group of an employee identification card, a shelf label, and a Quick Response (QR) code label.
