# US 2019/0244383 A1 · Apparatus and method for object recognition

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

- Number: US 2019/0244383 A1
- Document ID: US20190244383A1
- Status: Published application
- Kind: A1
- Application number: 15/887,775
- Filed: 2018-02-02
- Published: 2019-08-08
- Earliest claimed: 2018-02-02
- Assignees: AIC Innovations Group, Inc.
- Applicants: AIC Innovations Group, Inc.
- Inventors: Daniel Glasner; Lei Guan; Adam Hanina; Li Zhang
- Web page: https://patentgrep.com/patent/US20190244383A1

## CPC

- G06V 10/82: using neural networks
- A61B 5/4833: {Assessment of subject's compliance to treatment}
- G06F 18/22: Matching criteria, e.g. proximity measures
- G06F 18/24133: {Distances to prototypes}
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V 10/56: relating to colour
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- G06V 30/19173: {Classification techniques}
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A system and method for recognizing an object. The system includes an imaging apparatus for capturing an image of an object and a processor for receiving the captured image of the object, and for, when it is determined that fewer than a predetermined number of objects have been previously imaged, for determining whether the image of the captured object includes one or more characteristics determined to be similar to a same characteristic in a group of previously imaged objects so that the captured image is grouped with the previously imaged objects, or whether the image of the captured object includes one or more characteristics determined to be dissimilar to a same characteristic in a group of previously imaged objects so that the captured image is not grouped with the previously imaged objects, and the image of the captured object starts another group of previously imaged objects.

## Claims

### Claim 1

A system for recognizing an object, comprising
an imaging apparatus for capturing an image of an object;
a processor configured to:
receive the captured image of the object,
determine a number of objects that have been previously imaged,
determine whether the number of objects that have been previously images is fewer than or greater than a predetermined number
responsive to determining that the number of objects that have been previously imaged is fewer than the predetermined number,
determine whether the captured image of the object includes one or more characteristics similar to a same one or more characteristics, respectively, in a group of previously imaged objects,
associate the captured image with the group of previously imaged objects when the captured image includes one or more characteristics similar to the same one or more characteristics, respectively, in the group of previously imaged objects, and
associate the captured image with a new group of imaged objects when the captured image does not include one or more characteristics similar to the same one or more characteristics, respectively, in the group of previously imaged objects, and
responsive to determining that the number of objects that have been previously imaged is greater than the predetermined number,
determine whether the captured image of the object includes one or more characteristics similar to a same one or more characteristics, respectively in a group of previously imaged objects,
associate the captured image with the group of previously imaged objects when the captured image includes one or more characteristics similar to the same one or more characteristics, respectively, in the group of previously imaged objects, and
reject the captured image when the captured image does not include one or more characteristics similar to the same one or more characteristics, respectively, in the group of previously imaged objects; and
a display for displaying a result of whether the captured image is grouped with the previously imaged objects, or whether the captured image is rejected.

### Claim 2 (depends on 1)

The system of claim 1, wherein the object is a medication pill.

### Claim 3 (depends on 1)

The system of claim 1, wherein the object is a medication liquid.

### Claim 4 (depends on 1)

The system of claim 1, wherein the object is a medical device.

### Claim 5 (depends on 1)

The system of claim 1, wherein the imaging apparatus further images an identifier from a vessel associated with the object, and wherein the identifier is associated with the group of images including the imaged object.

### Claim 6 (depends on 5)

The system of claim 5, wherein one or more images associated with the identifier are retrieved from a remote data storage location.

### Claim 7 (depends on 6)

The system of claim 6 wherein the retrieved images are included in the determination of whether greater than a predetermined number of objects have been previously imaged.

### Claim 8

A method of training a system to recognize an object, comprising:
presenting a first object to an imaging system;
capturing an image of the first object by the imaging system;
storing the image of the first object;
presenting a second object to the imaging system;
capturing an image of the second object by the imaging system;
determining whether the image of the first object and the image of the second object differ by less than a predetermined amount on one or more dimensions;
grouping together the image of the first object and the image of the second object if it is determined that they differ by less than the predetermined amount;
maintaining separately the image of the first object and the image of the second object if it is determined that they do not differ by less than the predetermined amount;
imaging subsequent additional objects until a predetermined number of objects are grouped together into a group.

### Claim 9 (depends on 8)

The method of claim 8 further comprising the steps of, after the predetermined number of objects are grouped together into a group, presenting a third object to the imaging system;
capturing an image of the third object by the imaging system;
determining whether the image of the third object and the images of the objects in the group containing more than the predetermined number of objects differ by less than a predetermined amount on one or more dimensions;
grouping together the image of the third object and the of the objects in the group containing more than the predetermined number of objects if it is determined that they differ by less than the predetermined amount;
rejecting the image of the third object if it is determined that image of the third object and the of the objects in the group containing more than the predetermined number of objects do not differ by less than the predetermined amount.

### Claim 10 (depends on 8)

The method of claim 8, wherein the object is a medication pill.

### Claim 11 (depends on 8)

The method of claim 8, wherein the object is a medication liquid.

### Claim 12 (depends on 8)

The method of claim 8, wherein the object is a medical device.

### Claim 13

A system for recognizing an object, comprising
an imaging apparatus for capturing an image of an object;
a processor configured to:
receive the captured image of the object,
obtain, for each group of a plurality of groups of previously imaged objects, a corresponding similarity function characterizing a similarity between one or more features of the captured image of the object and one or more features, respectively, of at least one image in the group of previously imaged objects,
associate the captured image with a first group of previously imaged objects when a similarity function corresponding to the first group satisfies a similarity condition,
combine at least two groups of previously imaged objects together into a single group of previously imaged objects when a similarity function corresponding to each of the at least two groups satisfies the similarity condition, and
associate the captured image with a new group of imaged objects when the similarity function for each group of the plurality of groups of previously imaged objects does not satisfy the similarity condition.

### Claim 14 (depends on 13)

The system of claim 13, wherein the object is a medication pill.

### Claim 15 (depends on 13)

The system of claim 13, wherein the object is a medication liquid.

### Claim 16 (depends on 13)

The system of claim 13, wherein the object is a medical device.

### Claim 17

A method of training a system to recognize an object, comprising:
presenting a first object to an imaging system;
capturing an image of the first object by the imaging system;
obtaining, for each group of a plurality of a group of previously captured images, a corresponding similarity function characterizing a similarity between one or more features of the captured image of the first object and one or more features, respectively, of at least one image in the group of previously imaged objects;
combining at least two groups of previously imaged objects together into a new group of previously imaged objects when a similarity function corresponding to each of the at least two groups satisfies a similarity condition, and
associating the captured image of the first object with the new group of imaged objects.

### Claim 18 (depends on 17)

The method of claim 17, wherein the first object is a medication pill.

### Claim 19 (depends on 17)

The method of claim 17, wherein the first object is a medication liquid.

### Claim 20 (depends on 17)

The method of claim 17, wherein the first object is a medical device.
