# US 12,223,750 B1 · System and method for determining backfinned loins

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

- Number: US 12,223,750 B1
- Document ID: US12223750B1
- Status: Granted
- Kind: B1
- Application number: 18/422,651
- Filed: 2024-01-25
- Granted: 2025-02-11
- Earliest claimed: 2023-02-03
- Assignees: Triumph Foods, LLC
- Applicants: Triumph Foods, LLC
- Inventors: Nicholas Huffman; Matthew England; David McCulloch
- Web page: https://patentgrep.com/patent/US12223750B1

## CPC

- G06V 20/68: Food, e.g. fruit or vegetables
- A22B 5/007: {Non-invasive scanning of carcasses, e.g. using image recognition, tomography, X-rays, ultrasound (analysing meat, e.g. search for foreign embedded objects G01N33/12; image analysis G06T7/00)}
- A22C 17/0073: {using visual recognition, X-rays, ultrasounds, or other contactless means to determine quality or size of portioned meat}
- G06V 10/40: Extraction of image or video features
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/776: Validation; Performance evaluation
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- A22B: SLAUGHTERING
- A22C: PROCESSING MEAT, POULTRY, OR FISH (preserving A23B; obtaining protein compositions for foodstuffs A23J1/00; fish, meat or poultry preparations A23L; disintegrating, e.g. chopping meat, B02C18/00; preparation of proteins C07K1/00)

## Abstract

The disclosure relates to a system and method for identifying one or more features in a meat sample. In one embodiment, the system and method disclosed herein uses automated methods to identify a backfinned pork loin and a non-backfinned pork loin. The system and method disclosed herein comprises imaging a meat sample with an imaging device to obtain one or more images; and using an iteratively trained feature detection model to detect and identify one or more features, including the presence or absence of the features in the images of the meat sample.

## Claims

### Claim 1

A feature detection system configured to analyze a portion of a pork carcass that contains a pork loin, the system comprising:
a data capture device provided in a form of an image capture device;
a transport system with the portion of the pork carcass that contains the pork loin positioned in a field of view of the image capture device;
a feature detection model including a processor configured to:
process a plurality of data elements received from the data capture device to determine whether there is backfinning in the pork loin; and
generate an output that indicates whether there is backfinning in the pork loin;
an ejector configured to:
sort the pork loin into a backfinned loin processing line when the output indicates that there is backfinning in the pork loin; and
sort the pork loin into a bone-in loin processing line when the output indicates that there is not backfinning in the pork loin.

### Claim 2 (depends on 1)

The system of claim 1 further comprising a notification system designed to generate a notification provided in the form of an identification of the one or more features of the pork loin.

### Claim 3 (depends on 2)

The system of claim 2 wherein the identification includes a presence or an absence of backfinning in the pork loin.

### Claim 4 (depends on 1)

The system of claim 1 wherein the feature detection model includes an iteratively trained machine learning model.

### Claim 5 (depends on 1)

The system of claim 1 wherein the feature detection model includes a training model, a validation model, and a trained model.

### Claim 6 (depends on 5)

The system of claim 5 wherein the validation model comprises applying one or more detection models to a validation sample set to quantify the accuracy of the one or more detection models.

### Claim 7 (depends on 6)

The system of claim 6 wherein the validation sample set can include images with associated known attributes.

### Claim 8 (depends on 1)

The system of claim 1 wherein the plurality of data elements are provided in the form of high-resolution images.

### Claim 9 (depends on 1)

The system of claim 1 wherein the image capture device is a camera.

### Claim 10

A method for determining a feature of a portion of a pork carcass that contains a pork loin, the method comprising the steps of:
capturing a data element provided in a form of an image of the portion of the pork carcass that contains the pork loin;
extracting a feature parameter from the image of the pork loin;
processing the feature parameter using an iteratively trained feature detection training model;
determining, based on the processing of the feature parameter, whether there is backfinning in the pork loin;
responsive to determining that there is backfinning in the pork loin, generating a first signal to an ejector to sort the pork loin into a backfinned processing line; and
responsive to determining there is not backfinning in the pork loin, generating a second signal to the ejector to sort the pork loin into a bone-in loin processing line.

### Claim 11 (depends on 10)

The method of claim 10 wherein the feature parameter includes an input vector.

### Claim 12 (depends on 10)

The method of claim 10 wherein capturing the data element comprises triggering a camera when the meat sample comes within a visual field of the camera.

### Claim 13 (depends on 10)

The method of claim 10 wherein capturing the data element comprises obtaining a photo of a visual field of a camera at an interval based on frames per second.