Rock Core Sample Image Matching for Damaged Label Recovery

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional labeling methods for rock core samples often result in damaged or lost labels, rendering the samples unusable and incurring unnecessary costs and downtime due to the inability to identify the samples accurately.

Innovation Solution

A method and system that utilizes a secondary labeling system involving a sample roller, line scan camera, and control and data acquisition system to create a digital rollout image of the sample, which is stored with a sample identifier. This system uses machine learning or deep learning image matching techniques to identify samples with compromised physical labels by comparing rollout images, allowing for the creation of a replacement primary label.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If physical primary labels are used to identify rock core samples, then sample identification is straightforward and reliable, but the labels are prone to damage or loss during handling

Engineering Contradiction:
Improvelabel durabilityVSAvoidsample identification
Core Design Contradiction:
ReliabilityVSLoss of information

Solution Approach 1:

The patent creates a digital copy (rollout image) of the physical label and stores it in a database. This digital copy serves as a backup that can be used to identify the sample if the physical label is damaged or lost, eliminating the risk of permanent information loss.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent performs label imaging and database storage as a preliminary action before the physical label can be damaged or lost. By capturing the label information in advance and storing it digitally, the system ensures that sample identification information is preserved regardless of the physical label's condition.

Inventive Principle:
Principle #10Preliminary action

2Ease of manufacture

If handwritten labels or barcodes are used on sample containers, then labeling is simple and quick, but the labels get damaged or lost during handling of heavy and bulky samples

Engineering Contradiction:
Improvelabeling simplicityVSAvoidlabel retention
Core Design Contradiction:
Ease of manufactureVSReliability

Solution Approach 1:

The system creates a digital copy of the physical label through imaging and stores it in a database. This digital replica maintains the simplicity of physical labeling while eliminating the reliability issue of label damage or loss during handling.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent introduces a digital database as an intermediary between the physical label and sample identification. This intermediary layer preserves the ease of physical labeling while protecting against label damage by providing a digital backup for identification purposes.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Device complexity

If physical labels are the sole identification method, then the system is simple, but sample identification fails when labels are compromised requiring new sample extraction

Engineering Contradiction:
Improvelabeling system complexityVSAvoidsample re-extraction time
Core Design Contradiction:
Device complexityVSLoss of time

Solution Approach 1:

By creating and storing a digital copy of the label, the system provides a backup identification method that prevents the need for sample re-extraction when physical labels are compromised, thereby eliminating time loss without significantly increasing system complexity.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent performs the imaging and database storage as a preliminary action during the initial labeling process. This advance preparation ensures that if the physical label is later compromised, identification can proceed using the pre-stored digital copy, avoiding the need for time-consuming sample re-extraction.

Inventive Principle:
Principle #10Preliminary action

4Reliability

If a secondary labeling system with image matching is implemented, then sample identification reliability improves when primary labels are compromised, but system complexity increases

Engineering Contradiction:
Improvesample identification accuracyVSAvoidlabeling system structure
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system creates a digital copy of the physical label and stores it in a database. This digital replica enables reliable sample identification through image matching without requiring complex hardware modifications, as the copying process uses standard imaging technology.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical/physical label reading system with an optical/image-based system. By substituting physical label inspection with digital image matching, the system improves reliability while avoiding the need for complex mechanical modifications to the labeling infrastructure.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12387509B2Sample labeling method using image-matching
Publication Date: 2025.08.12 SAUDI ARABIAN OIL CO
  • US12387509B2 patent drawing
  • US12387509B2 patent drawing
  • US12387509B2 patent drawing

AI summary

A method and system for labeling and identifying a sample, including a rock core sample, after determining a physical primary label has been compromised is provided. The method includes labeling the sample by placing a physical primary label on the sample or sample container, creating a first rollout image of the sample for a secondary label, and storing the first rollout image in a secondary label digital database with a sample identifier. The method continues for identifying the sample after determining the physical primary label has been compromised by creating a secondary rollout image of the sample and searching the secondary label digital database using the second rollout image to create a plurality of matching scores using a machine learning or deep learning image matching technique. The matching scores are then evaluated to determine an identify of a sample and the sample is re-labelled using a replacement primary label.