Image Selection Device Using Blink Detection for Group Photos

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image selection systems for digital cameras, which rely on determining whether all individuals in a group photo have their eyes open, often fail to select a suitable image due to complexity and inaccuracies in eye detection, especially in group settings where not all individuals may have open eyes.

Innovation Solution

An image selection device and method that includes a face detector, eye detector, blink detector, and image selecting unit, which detect human faces, calculate estimated blink values, and select images based on the status of eyes being open or closed, using a threshold calculation module to ensure a suitable image is chosen even in group photos.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If image selection is based on determining whether all people in the group have their eyes open, then the selection criterion is simple, but no suitable photo can be selected when not all people have their eyes open

Engineering Contradiction:
Improveselection criterion simplicityVSAvoidsuitable photo selection rate
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent applies partial action by relaxing the selection criterion from requiring all eyes to be open to requiring only a predetermined number of eyes to be open. This allows the system to select suitable photos even when not all subjects have their eyes open, thereby improving the selection rate while maintaining operational simplicity.

Inventive Principle:
Principle #16Partial or excessive action

2Quantity of substance

If the number of images increases through rapid shooting, then more images are available for selection, but the operation complexity increases for the user

Engineering Contradiction:
Improvenumber of imagesVSAvoidselection operation complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The patent implements self-service by enabling the system to automatically select images based on eye detection algorithms without requiring manual user intervention. The system autonomously evaluates multiple captured images and selects those meeting the predetermined criteria, thereby handling the increased image quantity without increasing user operational complexity.

Inventive Principle:
Principle #25Self-service

3Extent of automation

If eye detection is used to determine suitable group photos, then the selection becomes automated, but detection inaccuracies occur in group settings

Engineering Contradiction:
Improveselection automationVSAvoideye detection accuracy
Core Design Contradiction:
Extent of automationVSMeasurement precision

Solution Approach 1:

The patent applies partial action by requiring detection of only a predetermined number of open eyes rather than all eyes in the group. This relaxed criterion improves detection robustness in group settings where complete eye detection is challenging, while still maintaining meaningful automation for selecting suitable photos.

Inventive Principle:
Principle #16Partial or excessive action

4Manufacturing precision

If a strict criterion requiring all eyes open is used, then the selection standard is clear, but no image can be selected in many practical scenarios

Engineering Contradiction:
Improveselection standard precisionVSAvoidimage selection success rate
Core Design Contradiction:
Manufacturing precisionVSReliability

Solution Approach 1:

The patent resolves this contradiction by changing the selection standard from requiring all eyes to be open to requiring only a predetermined number of eyes to be open. This partial requirement maintains sufficient selection precision while dramatically improving the success rate in practical scenarios where not all subjects can keep their eyes open.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP2237551B1Image selection device and method for selecting image
Publication Date: 2019.08.14 CASIO COMPUTER CO LTD
  • EP2237551B1 patent drawingFigure 1
  • EP2237551B1 patent drawingFigure 2
  • EP2237551B1 patent drawingFigure 3

AI summary

An image selection device including: a reception unit that receives a plurality of captured images obtained by rapid shooting one or more people as subjects; a face detection unit that detects human faces included in the captured images received by the reception unit; an eye detection unit that detects eyes in the human faces detected by the face detection unit; a blink detection unit that detects blink degrees of each of the eyes detected by the eye detection unit; an estimation unit that estimates statuses of the human faces based on the blink degrees detected by the blink detection unit; and a selecting unit that selects at least one of the captured images to be recorded on a recording medium from among the captured images received by the reception unit, based on the statuses of the human faces estimated by the estimation unit.