Tyre Surface Segmentation Using Statistical Image Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for inspecting tire surfaces are not sufficiently accurate for detecting defects and characteristics due to issues like black coloration, groove recesses, shadows, and contamination, leading to errors and failed identifications.

Innovation Solution

A method and equipment that segment the tire surface into 'groove' and 'non-groove' areas through statistical analysis of image regions, using almost telecentric radiation and green light to enhance defect detection accuracy, and employing pre-processing techniques like wavelet transforms for precise defect identification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional inspection methods are used to examine tire surfaces, then the inspection process is simple, but the detection accuracy is insufficient due to black coloration, groove recesses, shadows, and contamination

Engineering Contradiction:
Improvedefect detection accuracyVSAvoidinspection system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the tire surface inspection problem by dividing the image processing into distinct stages: pre-processing (noise reduction, contrast enhancement), feature extraction (edge detection, texture analysis), and defect classification. This segmentation allows each stage to be optimized independently, improving overall detection accuracy while managing system complexity through modular architecture

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies preliminary actions by performing pre-processing operations on the tire surface images before main inspection. This includes illuminating the tire surface with controlled lighting to reduce shadows, applying noise reduction filters, and enhancing contrast to compensate for black coloration and contamination, thereby preparing the data for more accurate defect detection

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If the tire surface is illuminated to reduce shadows and enhance visibility, then defect detection improves, but lighting complexity and energy consumption increase

Engineering Contradiction:
Improvesurface defect visibilityVSAvoidlighting energy consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by stationary object

Solution Approach 1:

The patent applies local quality by using region-specific lighting strategies where different areas of the tire surface receive tailored illumination. Critical inspection zones with grooves and potential defect areas receive enhanced lighting, while other areas use standard illumination, thereby improving defect visibility where needed while reducing overall energy consumption

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent employs periodic action through sequential or alternating illumination patterns during inspection. Multiple light sources are activated in sequences or alternately to capture different aspects of the tire surface, reducing the need for continuous high-energy illumination while maintaining adequate visibility for defect detection across the entire surface

Inventive Principle:
Principle #19Periodic action

3Measurement precision

If advanced pre-processing techniques like wavelet transforms are applied, then defect detection accuracy improves, but processing time and computational complexity increase

Engineering Contradiction:
Improvedefect identification accuracyVSAvoidimage processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies partial action by selectively applying advanced pre-processing techniques only to regions of the image where defects are suspected or where the tire surface characteristics require enhanced analysis. Standard processing is applied to uniform areas, while computationally intensive wavelet transforms and other advanced techniques are concentrated on critical zones, balancing accuracy improvement with processing time constraints

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent performs preliminary action by applying basic noise reduction and contrast enhancement to the entire image first, then using these pre-processed results to guide subsequent selective application of more computationally intensive techniques. This preliminary processing reduces the overall computational burden while maintaining defect detection accuracy

Inventive Principle:
Principle #10Preliminary action

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

Improves the accuracy of tire surface inspection by simplifying image processing, reducing errors, and enabling the detection of defects that were previously undetectable, thereby ensuring more reliable tire quality assessment.

Implementation Method 1

a light source for emitting light on a portion of said surface

Methodology Applied
Scientific EffectLight emission: Light

Implementation Method 2

employing pre-processing techniques like wavelet transforms for precise defect identification

Methodology Applied
Scientific EffectImage processing: Image Processing

Data Source

PatentEP2880415B1Method for segmenting the surface of a tyre and apparatus operating according to said method
Publication Date: 2020.11.18 PIRELLI TYRE SPA
  • EP2880415B1 patent drawingFigure 1
  • EP2880415B1 patent drawingFigure 2
  • EP2880415B1 patent drawingFigure 3~10c

AI summary

The present invention relates to a method for segmenting the surface (5a, 5b) of a tyre (P) including at least one groove (4). The method comprises: irradiating a portion (100) of the surface (5a, 5b) of the tyre (P) by means of electromagnetic radiation having a wavelength in the visible spectrum; acquiring an image (100a) of the irradiated portion (100) of the surface; and processing the image (100a) so as to segment it into regions (101, 102) corresponding to regions of the tyre which do or do not belong to the at least one groove (4). Additionally, processing the image (100a) so as to segment it includes: calculating a statistical quantity associated with the irradiation by electromagnetic radiation for each region (101, 102) of the image (100a); and determining whether the region (101, 102) of the image does or does not belong to the at least one groove (4) according to the value of the statistical quantity. The invention also relates to an equipment (1) for segmenting a surface (5a, 5b) of a tyre (P) including at least one groove (4).