# US 2022/0036371 A1 · Identifying and grading system and related methods for collectable items

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

- Number: US 2022/0036371 A1
- Document ID: US20220036371A1
- Status: Published application
- Kind: A1
- Application number: 17/390,751
- Filed: 2021-07-30
- Published: 2022-02-03
- Earliest claimed: 2020-07-31
- Assignees: Collectors Universe, Inc.
- Applicants: Collectors Universe, Inc.
- Inventors: Mark Frisbee; John Nelson; Imir Kalkanci
- Web page: https://patentgrep.com/patent/US20220036371A1

## CPC

- G06Q 30/018: Certifying business or products
- G06F 18/2178: {based on feedback of a supervisor}
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/082: modifying the architecture, e.g. adding, deleting or silencing nodes or connections
- G06N 3/09: Supervised learning
- G06N 3/096: Transfer learning
- G06Q 30/0278: {Product appraisal}
- G06V 10/82: using neural networks
- G06N 5/02: Knowledge representation; Symbolic representation
- G06N 20/00: Machine learning
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

An automated evaluation system for obtaining images for collectable items and using artificial intelligence (AI) to analyze different parameters of the images, such as an edge parameter, a corner parameter, and a centering parameter. The system can move the collectable items, which can be collectable cards, using a robotic arm or through manual manipulation to a working area to then obtain images of the collectable items using a camera or a scanner. The images can be saved to a database and accessible by a control computer to analyze the images with the AI model. The system can provide a first-pass grade as to the authenticity and condition of the card. The grade can be manually verified by a human grader.

## Claims

### Claim 1

An automated evaluation system for identifying and grading collectable items comprising:
at least one infeed hopper comprising a receiving a space for receiving one or more collectable items;
at least one completed hopper comprising a receiving a space for receiving one or more collectable items;
a working platform for supporting a collectable item;
a camera or a scanner spaced from the working platform for taking one or more images of a collectable item; and
a control computer comprising at least one hardware processor and a memory having stored thereon an artificial intelligence model for analyzing images of collectable items acquired by the camera or the scanner.

### Claim 2 (depends on 1)

The system of claim 1, wherein the collectable items are sleeved collectable items.

### Claim 3 (depends on 2)

The system of claim 2, further comprising a robotic arm comprising a plurality of independently movable arm segments and a robotic hand.

### Claim 4 (depends on 3)

The system of claim 3, further comprising one or more sensors for detecting sleeved collectable items located in the at least one infeed hopper and the at least one completed hopper.

### Claim 5 (depends on 3)

The system of claim 3, further comprising a housing and a light fixture mounted within the housing for providing backlight for the camera.

### Claim 6 (depends on 3)

The system of claim 3, further comprising a flipping mechanism for flipping a sleeved collectable item located on the working platform.

### Claim 7 (depends on 3)

The system of claim 3, wherein the at least one infeed hopper comprises two or more independently movable hoppers.

### Claim 8 (depends on 3)

The system of claim 3, wherein the at least one completed hopper comprises two or more independently movable hoppers.

### Claim 9 (depends on 2)

The system of claim 2, further comprising a database having a plurality of images taken by the camera or the scanner.

### Claim 10 (depends on 9)

The system of claim 9, wherein the database is stored remotely and accessible by the control computer.

### Claim 11 (depends on 9)

The system of claim 9, wherein the database is stored on the memory of the control computer.

### Claim 12 (depends on 9)

The system of claim 9, wherein the memory having stored thereon instructions that when executed by the at least one hardware processor cause the at least one hardware processor to perform steps comprising:
a) accessing a first image and a second image from the database, the first image comprising a front side image of a first sleeved collectable item and the second image comprising a back side image of the first sleeved collectable item;
b) accessing a trained convolutional neural network (CNN) from the memory, the trained CNN having been trained on collectable item images in which each of the collectable item has at least two collectable item parameters;
c) generating and outputting a score for each of the at least two collectable item parameters; and
d) generating a first-pass grade for the first sleeved collectable item based on analyses of the first image and the second image by the convolutional neural network.

### Claim 13 (depends on 12)

The system of claim 12, wherein the first sleeved collectable item is a first sleeved collectable card.

### Claim 14 (depends on 13)

The system of claim 13, further comprising generating and outputting a score for authenticity for the first sleeved collectable card.

### Claim 15 (depends on 13)

The system of claim 13, wherein the at least two parameters comprise an edge parameter and a corner parameter.

### Claim 16 (depends on 13)

The system of claim 13, wherein the at least two parameters comprise a color parameter and a surface parameter.

### Claim 17 (depends on 13)

The system of claim 13, wherein the at least two parameters comprise a sharpness parameter and a scratch parameter.

### Claim 18 (depends on 13)

The system of claim 13, wherein the at least two parameters are at least two of the following parameters: an edge parameter, a corner parameter, a color parameter, a surface parameter, a center parameter, a sharpness parameter, a print imperfection parameter, a staining parameter, a scratch parameter, a chipping parameter, and a crease parameter.

### Claim 19

A method of obtaining images of a collectable item comprising:
placing a collectable item into a first plastic sleeve to form a sleeved collectable item;
placing the sleeved collectable item into a receiving space of a hopper;
placing a barcode representative of an order into a second plastic sleeve to form a sleeved barcode order information;
placing the sleeved barcode order information on top of the sleeved collectable item;
moving the sleeved barcode order information onto a working platform; and
detecting information on the barcode with a camera.

### Claim 20 (depends on 19)

The method of claim 19, further comprising moving the sleeved collectable item with a robotic arm onto the working platform and activating the camera to take one or more images of the sleeved collectable item.

### Claim 21

A method of issuing a first pass grade for a collectable item comprising:
moving a collectable item manually onto a working platform;
activating a camera to obtain one or more images of the collectable item;
issuing a first pass grade for the collectable item based on analyzing the one or more images of the collectable item with an AI model;
issuing a first final grade for the collectable item based manual evaluation of the one or more images of the collectable item or on evaluation of the collectable item; and
wherein the first pass grade and the first final grade are the same or are different.

### Claim 22 (depends on 21)

The method of claim 21, wherein the first final grade is performed by a first grader and wherein a second final grade for the collectable item is generated based manual evaluation of the one or more images of the collectable item or on evaluation of the collectable item by a second grader if the first final grade is different from the first pass grade.
