Image processing apparatus, display control apparatus, image processing method and recording medium

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing commodity recognition systems face challenges in accurately identifying products in images due to environmental influences like lighting and angle, leading to high failure rates or false recognition, as they do not adequately account for these factors in setting recognition thresholds.

Innovation Solution

An image processing apparatus that includes recognition and detection means, utilizing store fixture information to re-recognize regions in images where products were initially missed, based on positional installation data, to improve detection precision and reduce false recognition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a higher recognition threshold is set to prevent false recognition, then false recognition rate decreases, but commodity recognition failure rate increases

Engineering Contradiction:
Improvefalse recognition rateVSAvoidcommodity recognition accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent segments the image processing into multiple stages: initial commodity recognition, detection of unrecognized regions using store fixture information, and secondary recognition focused on those specific regions. This segmentation allows different recognition thresholds to be applied at different stages, resolving the contradiction between preventing false recognition and avoiding recognition failures.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary detection of regions where commodities are likely to be present but were not recognized by the initial recognition process. By using store fixture positional information to identify these regions before secondary recognition, the system can apply appropriate recognition strategies tailored to each region, thereby reducing both false recognition and recognition failure rates.

Inventive Principle:
Principle #10Preliminary action

2Device complexity

If environmental factors like lighting and angle are not considered, then system complexity is reduced, but recognition accuracy deteriorates

Engineering Contradiction:
Improvesystem complexityVSAvoidrecognition accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent introduces store fixture information as an intermediary element that bridges the gap between simple image recognition and complex environmental analysis. By using pre-acquired positional information about store fixtures as a mediator, the system can accurately identify regions of interest without directly analyzing complex environmental factors like lighting and angle, thus maintaining low system complexity while improving recognition accuracy.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3211580B1Image processing apparatus, display control apparatus, image processing method and recording medium
Publication Date: 2021.03.03 NEC CORP
  • EP3211580B1 patent drawingFigure 1~2
  • EP3211580B1 patent drawingFigure 3
  • EP3211580B1 patent drawingFigure 4~5

AI summary

The present invention provides a function capable of detecting, with a higher degree of precision, a region that has a high probability of not having been recognized. An image processing apparatus according to the present invention is provided with: a recognition means for recognizing a product from a captured image obtained by capturing an image of a displayed product; and a detection means for detecting a region of a product that is included in the captured image but is not recognized by the recognition means, on the basis of furniture information related to furniture in which the product is displayed.