Automatic Parameter Determination in Machine Vision Object Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Machine vision systems require users to manually specify parameters for object recognition, which is cumbersome and inflexible, especially in industrial settings where conditions change frequently, leading to time-consuming adaptations and potential production interruptions.

Innovation Solution

Automatically determining key parameters such as contrast, minimum object size, model point reduction, minimum contrast of image structures, and discretization step lengths based solely on a single model image, using methods like edge amplitude thresholding, cumulative histogram analysis, and similarity measure evaluation to enhance system flexibility and robustness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If manual parameter specification is used, then system flexibility and adaptability are improved, but ease of operation deteriorates and time consumption increases

Engineering Contradiction:

Improvesystem flexibilityVSAvoidease of operation

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system automatically determines parameter values using image analysis algorithms. The computer calculates optimal parameters (such as threshold values, region of interest boundaries, and feature extraction parameters) directly from the input image without requiring manual user specification, enabling the system to serve itself in parameter configuration

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary image analysis to pre-determine parameter values before the main object recognition process. By analyzing image characteristics, noise levels, and structural features in advance, the system prepares optimal parameter settings that are then used during recognition, eliminating the need for manual parameter tuning during operation

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If multiple parameters are specified manually, then measurement precision and manufacturing precision are improved, but device complexity increases and ease of operation deteriorates

Engineering Contradiction:

Improveparameter determination precisionVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The parameter determination process is divided into separate modular steps: noise analysis, edge detection parameter determination, region of interest identification, and feature extraction parameter setting. Each module handles a specific aspect of parameter determination independently, making the complex process manageable and systematic while maintaining high precision

Inventive Principle:

Principle #1Segmentation

3Adaptability or versatility

If manual parameter adaptation is performed, then adaptability to changing conditions is improved, but productivity deteriorates due to production interruptions

Engineering Contradiction:

Improveadaptability to changing conditionsVSAvoidproductivity

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The automatic parameter determination system operates continuously without interrupting the production process. Parameters are recalculated and updated in real-time based on changing image conditions, allowing the system to adapt to varying lighting, object positions, and environmental factors while maintaining uninterrupted production flow and high productivity

Inventive Principle:

Principle #20Continuity of useful action

4Ease of operation

If automatic parameter determination is implemented, then ease of operation and productivity are improved, but measurement precision may deteriorate without expert knowledge

Engineering Contradiction:

Improveease of operationVSAvoidparameter determination precision

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system incorporates feedback mechanisms where parameter determination results are evaluated against recognition performance metrics. The algorithms adjust parameters based on feedback from the recognition process, iteratively improving precision. Image analysis feedback provides information about actual image characteristics that guides optimal parameter selection, ensuring high measurement precision even without expert user knowledge

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS7953290B2System and methods for automatic parameter determination in machine vision

Publication Date: 2011.05.31 MVTEC SOFTWARE

AI summary

The present invention provides a system and methods for automatic parameter determination in machine vision in general, and in object recognition in particular. Many machine vision systems use algorithms that demand the user to specify one or more parameters in order to adapt the behavior of the algorithm in dependence of the current application. This is not desirable because the complexity of the algorithm should be hidden from the user and a manual parameter determination is contrary to a desirable high degree of automation. The present invention provides a method to automatically determine the most frequently used parameters in machine vision solely based on the input image itself. The method is explained in detail using an object recognition system as an example. In particular, the model generation process based on a model image of the object is explained. However, also other systems that use edge extraction algorithms, for example, can benefit from the present invention.