Pattern-Based Waste Container Identification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current waste sorting methods, particularly those relying on colored bags, face challenges in accuracy and user compliance due to the potential for incorrect sorting and lack of transparency, which can lead to contamination in biogas production and inefficient waste handling.

Innovation Solution

A method utilizing image analysis to identify and sort waste containers based on a pattern's characteristics such as shade, color, shape, size, and surface area, allowing for precise classification and sorting, even in transparent bags, and enabling visual inspection to ensure accurate waste separation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If waste containers are colored to indicate waste type, then users can easily identify and sort waste, but sorting accuracy decreases due to potential color misidentification and user error

Engineering Contradiction:
Improveuser identification of waste typeVSAvoidsorting accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent uses patterned containers with specific color combinations and pattern types (e.g., green with white dots for organic waste, blue with white dots for paper waste) to encode waste type information. The image analysis system detects both color and pattern characteristics to identify waste type, providing more reliable identification than color alone while maintaining ease of use for users.

Inventive Principle:
Principle #32Color changes

2Measurement precision

If transparent bags are used to allow visual inspection of contents, then sorting accuracy improves, but users cannot easily identify the intended waste type without additional markings

Engineering Contradiction:
Improvevisual inspection capabilityVSAvoiduser identification of waste type
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent applies color-coded patterns on transparent containers to maintain both transparency and identifiability. The patterns (such as colored dots or shapes) are visible through the transparent material, allowing users to quickly identify waste type while still being able to visually inspect contents. The image analysis system detects these patterns to confirm waste type classification.

Inventive Principle:
Principle #32Color changes

3Measurement precision

If multiple identification characteristics are analyzed (color, shade, pattern type, size), then sorting accuracy increases, but system complexity increases

Engineering Contradiction:
Improvesorting accuracyVSAvoidimage analysis system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the identification task into multiple independent characteristic analysis steps: color detection, shade measurement, pattern type recognition, and size measurement. Each characteristic is analyzed separately using specific image processing techniques, and the results are combined to determine waste type. This segmentation allows the system to handle complex identification through modular processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The image analysis system is designed to detect multiple identification characteristics simultaneously using a single imaging device and processing system. The same camera and software can analyze color, shade, pattern type, and size of patterns on containers, making the system multi-functional and reducing overall complexity compared to using separate detection devices for each characteristic.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enhances sorting precision and accuracy, reduces user error, and allows for the use of transparent bags, improving the efficiency and reliability of waste sorting processes, particularly in biogas production by ensuring the correct separation of waste fractions.

Implementation Method 1

analyzing the image by determining following characteristics: a shade and/or color of the pattern; a type of the pattern arranged on the container; a size of the individual object; and a surface area of the pattern

Methodology Applied
Scientific EffectImage analysis: Image Processing

Data Source

PatentEP2694223B1Method and system for identifying waste containers based on pattern
Publication Date: 2021.01.27 EHNVAK AB
  • EP2694223B1 patent drawingFigure 1a~1b
  • EP2694223B1 patent drawingFigure 1c~1d
  • EP2694223B1 patent drawingFigure 2

AI summary

There is provided a method for identifying and sorting randomly distributed waste containers (1) containing different types of refuse sorted at source, wherein the identification is based on an image analysis of a pattern (2) arranged on each container (1). The method for identifying and sorting comprises the following steps: capturing at least one image of each container (1), analyzing the image by determining following characteristics: a shade and/or color of the pattern; a type of the pattern arranged on the container; calculating a sorting value based on the determined characteristics; comparing the calculated sorting value to a predetermined limit value or predetermined range of sorting values in order to classify the type of refuse contained in the container for sorting thereof.