Shelf Label Recognition for Product Count and Position Checks

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing systems fail to maintain the consistency between the number and positional relationship of shelf labels and products on store shelves, leading to incorrect product information recognition by customers due to misplacement or omission of shelf labels.

Innovation Solution

An information processing apparatus with a product recognition unit, shelf label recognition unit, and determination unit to identify errors in the number and positional relationship between products and shelf labels, enabling correction of misarrangements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If manual arrangement of shelf labels is performed, then flexibility in product lineup changes is achieved, but consistency between shelf labels and products cannot be ensured

Engineering Contradiction:

Improveflexibility in product lineup changesVSAvoidconsistency between shelf labels and products

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The system captures images of shelf labels and products, automatically recognizes and compares their positions and relationships, then provides feedback by determining whether errors exist in their correspondence. This closed-loop feedback mechanism ensures consistency without requiring manual verification, resolving the contradiction between manual flexibility and automated accuracy.

Inventive Principle:

Principle #23Feedback

2Productivity

If automated recognition system is implemented, then checking efficiency is improved, but system complexity increases

Engineering Contradiction:

Improvechecking efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The information processing apparatus performs multiple functions including image capture, shelf label recognition, product recognition, positional relationship determination, and error detection using a single integrated system. This multi-functional approach improves checking efficiency while avoiding the complexity of multiple separate systems working together.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Reliability

If frequent manual inspection is performed, then arrangement errors are detected early, but time consumption increases

Engineering Contradiction:

Improveerror detection accuracyVSAvoidtime consumption for inspection

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system replaces manual mechanical inspection with automated image-based recognition and analysis. The information processing apparatus automatically captures images, recognizes shelf labels and products, determines their positional relationships, and detects errors without human intervention, thereby eliminating time consumption while maintaining high error detection accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250322353A1Information processing apparatus, control method, and program

Publication Date: 2025.10.16 NEC CORP

AI summary

An information processing apparatus (2000) includes a product recognition unit (2020), a shelf label recognition unit (2040), and a determination unit (2060). The product recognition unit (2020) recognizes the number of types of products or positions of each type of products from a target image. The shelf label recognition unit (2040) recognizes the number or positions of shelf labels indicating information of the products from the target image. The determination unit (2060) determines whether or not there is an error in a relationship between the recognized number of types of products and the recognized number of shelf labels or in a relationship between the recognized positions of each type of products and the recognized positions of the shelf labels.