Camera Image Evaluation With Reference Images for Storage Reduction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Amateur photographers face challenges in capturing high-quality images that require significant storage space due to the need to take multiple shots and later select the best ones, leading to increased storage requirements.

Innovation Solution

A computer-implemented method for evaluating camera images by comparing image features with a group of reference images, determining an evaluation parameter, and providing real-time feedback or instructions to improve or discard images based on predefined thresholds, thereby reducing the number of captured images and storage needs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If multiple camera shots are taken to ensure high-quality images, then image quality is improved, but storage space requirements increase

Engineering Contradiction:
Improveimage qualityVSAvoidstorage space
Core Design Contradiction:
Manufacturing precisionVSQuantity of substance

Solution Approach 1:

The system performs preliminary evaluation of camera images using AI/ML models to predict quality metrics before the user reviews or stores the images. This preliminary quality assessment allows the system to identify and retain only high-quality images, eliminating the need to store multiple mediocre shots while ensuring at least one excellent image is captured and saved.

Inventive Principle:
Principle #10Preliminary action

2Manufacturing precision

If multiple camera shots are taken to select the best image, then image quality is improved, but the number of captured images increases

Engineering Contradiction:
Improveimage qualityVSAvoidnumber of captured images
Core Design Contradiction:
Manufacturing precisionVSProductivity

Solution Approach 1:

The system implements feedback loops where AI/ML models continuously evaluate captured images against quality criteria and provide real-time feedback on image quality metrics. This feedback mechanism enables the camera to automatically determine when a sufficient quality image has been captured, reducing the need to take excessive numbers of shots while maintaining high image quality standards.

Inventive Principle:
Principle #23Feedback

3Manufacturing precision

If manual selection of best images is performed, then image quality is improved, but time consumption increases

Engineering Contradiction:
Improveimage qualityVSAvoidtime consumption
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The system employs self-service automation through AI/ML-based quality assessment that automatically evaluates and ranks captured images without requiring manual user intervention. The system independently determines which images meet quality criteria and should be retained, freeing the user from time-consuming manual review while ensuring high-quality image selection.

Inventive Principle:
Principle #25Self-service

4Reliability

If all captured images are stored, then no quality filtering is lost, but storage efficiency decreases

Engineering Contradiction:
Improvequality assuranceVSAvoidstorage efficiency
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The system changes the evaluation parameter from binary (keep/delete) to a quality score spectrum, where images are assessed on multiple dimensions (composition, lighting, subject recognition, etc.). This parameter transformation enables nuanced quality filtering that retains only images meeting specific quality thresholds, improving storage efficiency while maintaining reliability through multi-criteria assessment.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4492805B1Computer-implemented method for evaluating a camera image
Publication Date: 2025.07.02 DEUTSCHE TELEKOM AG
  • EP4492805B1 patent drawingFigure 1
  • EP4492805B1 patent drawingFigure 2

AI summary

A computer-implemented method for evaluating a camera image, comprising the following steps: providing the camera image, identifying at least one image feature of the camera image, determining a group of reference images based on the image feature, using at least one reference image feature for the group of reference images, comparing the image feature and the reference image feature, and calculating an evaluation parameter for the camera image based on the comparison between the image feature and the reference image feature.