Bottle Analysis System Using Image Recognition for Volume Tracking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing systems for monitoring milk consumption in infant feeding bottles and breast pump usage are inadequate due to fading volume markings and difficulty in distinguishing between bottle types, leading to potential overfeeding or underfeeding issues.

Innovation Solution

A bottle analysis system using image analysis to identify bottle shape and type, determining liquid volume based on pre-stored data, and tracking changes in liquid volume over time, which can be implemented on mobile devices without requiring special markers or orientation, utilizing neural networks and computer vision techniques.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If manual assessment of volume markings is used, then no additional components are needed, but the volume markings fade away making assessment difficult

Engineering Contradiction:
Improvemonitoring capabilityVSAvoidmarking visibility
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent replaces manual visual assessment of physical volume markings with an automated image analysis system using computer vision and neural networks. The system captures images of the bottle and uses digital processing to determine liquid volume, eliminating dependence on physical markings that fade over time.

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

Solution Approach 2:

The system creates a digital copy (image) of the bottle and its contents, then analyzes this copy to determine volume. This digital representation allows for accurate measurement without relying on the physical condition of the original bottle markings.

Inventive Principle:
Principle #26Copying

2Measurement precision

If additional components like weighting scales are used, then accurate volume measurement is achieved, but device complexity increases

Engineering Contradiction:
Improvevolume measurement accuracyVSAvoidsystem components
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces mechanical weighing systems with an optical-based image analysis system. Instead of using physical scales to measure bottle weight before and after feeding, the system uses computer vision to directly analyze the liquid volume in the bottle image, eliminating the need for additional mechanical components.

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

Solution Approach 2:

The system introduces an intermediary element - a camera - to capture the bottle image, which then serves as the basis for volume determination. This intermediary allows non-contact measurement and simplifies the overall system compared to mechanical weighing approaches.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If image analysis is used to identify bottle type, then the system works with multiple bottle sizes and shapes, but processing complexity increases

Engineering Contradiction:
Improvebottle type compatibilityVSAvoidimage processing requirements
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system performs preliminary classification of bottle types and sizes before conducting volume measurements. By first identifying the bottle category using image analysis, the system can then apply appropriate measurement algorithms specific to each bottle type, improving both accuracy and efficiency.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The image processing is segmented into distinct stages: bottle detection and type identification, liquid level detection, and volume calculation. This segmentation allows each stage to be optimized independently and reduces overall processing complexity.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4237031B1A bottle analysis system
Publication Date: 2024.08.21 KONINKLIJKE PHILIPS NV
  • EP4237031B1 patent drawingFigure 1
  • EP4237031B1 patent drawingFigure 2
  • EP4237031B1 patent drawingFigure 3

AI summary

A bottle analysis system receives image data of a bottle to be analyzed, and the data is processed to identify a shape of the bottle, and optionally any identifying markings. A bottle type is then determined. Image analysis is used to determine a liquid level in the bottle and thereby determine a liquid volume in the bottle.