Outer Packing Change Detection for Retail Shelf Goods

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems fail to accurately detect changes in the outer packaging of goods displayed on shelves, leading to degradation in recognition accuracy when using image recognition technology.

Innovation Solution

An information processing system that detects changes in the outer packaging of goods by receiving image information from a display shelf, and using an outer packing change detection processing unit to identify changes in the packaging without altering the goods themselves.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If image recognition technology is used to identify goods on display shelves, then goods identification is automated, but recognition accuracy degrades when outer packaging changes

Engineering Contradiction:
Improveautomated goods identificationVSAvoidrecognition accuracy
Core Design Contradiction:
Extent of automationVSMeasurement precision

Solution Approach 1:

The system segments the identification process into two stages: first identifying the goods type using stable features (JAN code, goods name), then separately detecting outer packaging changes by comparing image information. This segmentation allows the system to maintain high recognition accuracy for goods identity while also detecting packaging variations.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary detection of outer packaging changes by comparing current image information with stored sample images before finalizing goods identification. This preliminary action enables the system to adapt to packaging changes proactively, maintaining recognition accuracy without requiring complete relearning.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If sample images are updated or relearning is performed to adapt to packaging changes, then recognition accuracy is maintained, but processing time and system complexity increase

Engineering Contradiction:
Improverecognition accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

Instead of performing complete relearning whenever packaging changes occur, the system applies partial updates by detecting specific outer packaging changes and updating only the necessary portions of the recognition model. This partial action maintains recognition accuracy while significantly reducing processing time and computational resources required.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system implements feedback mechanisms where detection results from comparing current images with sample images are used to trigger selective updates. When packaging changes are detected, the system feeds back this information to update the recognition model appropriately, maintaining accuracy without requiring continuous full-scale relearning.

Inventive Principle:
Principle #23Feedback

3Measurement precision

If comprehensive image analysis is performed to detect packaging changes, then packaging change detection accuracy improves, but system complexity and computational load increase

Engineering Contradiction:
Improvepackaging change detection accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system extracts and focuses specifically on outer packaging features for change detection, separating this task from the general goods identification process. By taking out the packaging detection function as a distinct analysis stream, the system achieves high packaging change detection accuracy while managing complexity through modular design.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The image recognition system is designed with multi-functionality, simultaneously performing goods identification, outer packaging change detection, and adaptive learning. This universal approach consolidates multiple functions into a single integrated system, improving packaging change detection accuracy without proportionally increasing system complexity.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250053919A1Information processing system
Publication Date: 2025.02.13 MARKETVISION CO LTD
  • US20250053919A1 patent drawing
  • US20250053919A1 patent drawing
  • US20250053919A1 patent drawing

AI summary

An information processing system that detects a change in outer packing of goods displayed on a display shelf, and the information processing system includes: an image information input receipt processing unit configured to receive an input of image information obtained by imaging the display shelf; and an outer packing change detection processing unit configured to detect the change in the outer packing of the goods that appears in the image information, in which the outer packing change detection processing unit determines whether there is a change of the goods displayed on the display shelf between a current time and before the current time, and in a case where there is no change in the goods displayed, determines whether there is the change in the outer packing of the goods that appears in the image information between the current time and before the current time.