Hough Voting for SKU Size Differentiation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image recognition techniques fail to distinguish between products that have similar appearances but vary in size, making it difficult to automate the enforcement of planograms in retail environments.

Innovation Solution

A system and method that uses an image recognition application to identify products, generate regions of interest, determine pixel dimensions, calculate pixel-to-physical dimension ratios, and assign stock keeping unit identifiers based on these ratios, allowing for accurate differentiation of products with similar packaging but varying sizes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional image recognition techniques are used to identify products, then product identification can be performed, but products with similar appearances but different sizes cannot be distinguished

Engineering Contradiction:
Improveproduct size differentiation accuracyVSAvoidproduct identification accuracy
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent applies parameter changes by utilizing pixel dimension measurements as an additional distinguishing parameter beyond visual appearance. By measuring the pixel dimensions of products in the image and comparing them against known physical dimensions, the system can differentiate between products of similar appearance but different sizes, thereby resolving the contradiction between identification reliability and size differentiation precision.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If manual tracking of product location and quantity is performed, then accurate inventory data can be obtained, but the process is labor-intensive and difficult to enforce planograms

Engineering Contradiction:
Improveinventory data accuracyVSAvoidplanogram enforcement efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent replaces the manual mechanical tracking system with an automated image recognition and measurement system. By capturing images of retail shelves and automatically analyzing product locations, quantities, and dimensions through computational methods, the system eliminates labor-intensive manual tracking while maintaining accurate inventory data and enabling efficient planogram enforcement.

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

Solution Approach 2:

The system enables self-service by allowing the image recognition algorithm to automatically perform inventory tracking and planogram compliance checking without human intervention. The automated measurement and identification processes eliminate the need for manual data collection, thereby improving productivity while maintaining measurement precision.

Inventive Principle:
Principle #25Self-service

3Productivity

If automated product recognition is attempted, then productivity increases, but the ability to distinguish between similar products varies in size is lost

Engineering Contradiction:
Improveproduct recognition speedVSAvoidsize-based product differentiation
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent adds another dimension to product recognition by incorporating pixel dimension measurements alongside visual appearance analysis. This dimensional extension allows the automated system to differentiate between products of similar appearance by measuring their sizes in the image, thereby maintaining both high productivity and accurate size-based differentiation.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentEP3038013B1Distinguishing between stock keeping units using hough voting methodology
Publication Date: 2018.09.19 RICOH CO LTD
  • EP3038013B1 patent drawingFigure 1
  • EP3038013B1 patent drawingFigure 2
  • EP3038013B1 patent drawingFigure 3

AI summary

The disclosure includes a system and method for distinguishing between items of similar appearance that vary in size. An image recognition application receives an image including a plurality of items, identifies each item in the image, generates a region of interest for each identified item in the image, determines a dimension of the region of interest for each identified item in pixels, determines a plurality of pixel-to-physical dimension ratios for each identified item, identifies a selected pixel-to-physical dimension ratio among the plurality of pixel-to-physical dimension ratios, and determines a stock keeping unit identifier of each identified item in the image based on the selected pixel-to-physical dimension ratio and the dimension of the region of interest for each identified item.