Image Processing Device Joint Model Recognition

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image processing techniques for recognizing multiple models in mixed flow production lines are inefficient due to the need for repeated search processes, leading to increased processing time as the number of models grows.

Innovation Solution

The technique involves selecting a uniform reduction ratio for multiple models, allowing joint preprocessing such as image reduction, smoothing, and feature calculation, thereby reducing computational expense and improving processing speed.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a single model recognition technique is used for each model in mixed flow production lines, then recognition accuracy is maintained, but processing time increases as the number of models grows

Engineering Contradiction:
Improverecognition accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent merges the image reduction processes for multiple models by identifying and grouping models that share the same reduction ratio. Instead of processing each model independently, the system combines preprocessing operations for models with identical reduction ratios, thereby reducing redundant computations and decreasing overall processing time while maintaining recognition accuracy for each model

Inventive Principle:
Principle #5Merging (Combining)

2Productivity

If model images are decimated to reduce memory usage and processing time, then processing efficiency improves, but the number of permutations increases when recognizing multiple models

Engineering Contradiction:
Improveprocessing efficiencyVSAvoidnumber of permutations
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent applies parameter changes by grouping models based on their reduction ratio parameters. Models are categorized into groups where each group shares the same reduction ratio parameter, allowing the system to process entire groups with a single preprocessing operation. This parameter-based grouping reduces the number of permutations from individual model processing to group-level processing, thereby decreasing computational complexity

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3118812B1Image processing device, image sensor, and image processing method
Publication Date: 2025.05.14 OMRON CORP
  • EP3118812B1 patent drawingFigure 1
  • EP3118812B1 patent drawingFigure 2
  • EP3118812B1 patent drawingFigure 3

AI summary

An image processing device is provided with a storage unit configured to store for each model among a plurality of models, a model template obtained by reducing a model image; an image reduction unit configured to reduce an input image by the reduction ratio for each model; and a search unit configured to search for the location of a model in an input image on the basis of a reduced input image and a model template. The storage unit stores model templates for at least two of the models wherein said model templates are obtained by reducing the model images by the same reduction ratio; and The image reduction unit processes the at least two models jointly. The image processing device is hereby capable of high-speed identification and recognition of a plurality of models from an input image.