# US 2013/0279748 A1 · Object identification using optical code reading and object recognition

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

- Number: US 2013/0279748 A1
- Document ID: US20130279748A1
- Status: Published application
- Kind: A1
- Application number: 13/831,025
- Filed: 2013-03-14
- Published: 2013-10-24
- Earliest claimed: 2012-04-20
- Assignees: Datalogic ADC, Inc.
- Inventors: Robert D. Hastings
- Web page: https://patentgrep.com/patent/US20130279748A1

## CPC

- G06V 10/768: {using context analysis, e.g. recognition aided by known co-occurring patterns}
- G06V 2201/10: Recognition assisted with metadata
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An object identification system comprises an optical code reader that scans an optical code of an object and decodes a portion of the optical code. Using the decoded portion of the optical code, a database filter unit generates a filtered subset of feature models from a set of feature models of known objects stored in a database. An image capture device captures an image of the object, and a feature detector unit detects visual features in the image. A comparison unit compares the detected visual features to the filtered subset of feature models to identify a match between the object and a known object.

## Claims

### Claim 1

A method of identifying an object in a system that includes a database of feature models of known objects having known optical code information associated therewith, comprising:
attempting to read an optical code on an object;
decoding a portion of the optical code to obtain decoded information that is less than all information encoded in the optical code;
generating a filtered subset of feature models from the database of feature models based on the decoded information, each feature model of the filtered subset of feature models corresponding to a known object whose associated known optical code information includes the decoded information;
capturing an image that includes a representation of the object;
extracting visual features from the image; and
comparing the extracted visual features to the feature models of the filtered subset of feature models to identify a match between the object and a known object.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
detecting an exception event in which less than all of the optical code is decoded; and
generating the filtered subset of feature models in response to detecting the exception event.

### Claim 3 (depends on 1)

The method of claim 1, wherein the decoded information includes a check digit, and wherein each feature model of the filtered subset of feature models includes a known check digit equal to that of the decoded information.

### Claim 4 (depends on 1)

The method of claim 1, wherein the decoded information includes a manufacturer identification, and wherein each feature model of the filtered subset of feature models includes a known manufacturer identification equal to that of the decoded information.

### Claim 5 (depends on 1)

The method of claim 1 wherein attempting to read the optical code on the object comprises reading a representation of the optical code from the image.

### Claim 6

An object identification system, comprising:
an optical code reader configured to decode a portion of an optical code on an object;
an image capture device configured to capture an image of the object;
a feature detector unit configured to detect visual features in the image captured by the image capture device;
a database configured to store feature models of known objects having known optical code information associated therewith;
a database filter unit in communication with the optical code reader and the database, the database filter unit configured to, in response to the optical code reader decoding a portion of the optical code to obtain decoded information that is less than all information encoded in the optical code, generate a filtered subset of feature models based on the decoded information; and
a comparison unit in communication with the feature detector unit and the database filter unit, the comparison unit configured to compare the detected visual features and the feature models of the filtered subset of feature models to identify a match between the object and a known object.

### Claim 7 (depends on 6)

The object identification system of claim 6, wherein the feature detector unit, the database filter unit, and the comparison unit are implemented in a processor.

### Claim 8 (depends on 6)

The object identification system of claim 6, wherein the optical code reader includes an image capture device.

### Claim 9 (depends on 8)

The object identification system of claim 8, wherein the image capture device of the optical code reader is the image capture device configured to capture an image of the object.

### Claim 10 (depends on 6)

The object identification system of claim 6, wherein the database is configured to store the known optical code information associated with the known objects.

### Claim 11 (depends on 6)

The object identification system of claim 6, wherein the optical code reader is further configured to generate an exception event indicating that the optical code reader is unable to decode all of the optical code, and the database filter unit is further configured to generate the filtered subset of feature models in response to the exception event.

### Claim 12 (depends on 6)

The object identification system of claim 6, wherein the database filter unit is configured to generate the filtered subset of feature models by identifying feature models in the database that correspond to known objects whose associated known optical code information includes the decoded information.

### Claim 13

A method for reducing a search space of a database including feature models used in visual object recognition, the method comprising:
obtaining an item-filter parameter corresponding to a portion of information encoded in an optical code of an unknown item, the portion of information being less than all information encoded in the optical code; and
determining a subset of feature models based on the item-filter parameter, wherein feature models of the subset correspond to a known item having known optical code information that includes the portion of information encoded in the optical code of the unknown item.

### Claim 14 (depends on 13)

The method of claim 13, wherein the item-filter parameter is a decoded value of a check digit of the optical code of the unknown item.

### Claim 15 (depends on 13)

The method of claim 13, wherein the item-filter parameter is a decoded value of a manufacturer identification number of the optical code of the unknown item.

### Claim 16 (depends on 13)

The method of claim 13, further comprising:
obtaining a visual feature of the unknown item; and
identifying the unknown item by matching the visual feature to a feature model of the subset of feature models.

### Claim 17 (depends on 16)

The method of claim 16, further comprising:
performing the step of identifying the unknown item in response to an unsuccessful decode of the optical code of the unknown item.

### Claim 18 (depends on 16)

The method of claim 16, wherein the visual feature is a scale-invariant feature transform (SIFT) feature.

### Claim 19 (depends on 16)

The method of claim 16, wherein the visual feature includes multiple scale-invariant features that define a spatial relationship between the multiple scale-invariant features.
