Image Processing Device Selective Super-Resolution

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In production facilities, the use of fixed focal length lens units in imaging devices can result in insufficient resolution when imaging small target objects, leading to extended processing times due to the necessity of multi-frame super-resolution processing, which increases the load and cycle time of image processing.

Innovation Solution

The image processing device selectively executes super-resolution processing based on the type of target object, switching between low and high resolution data to suppress excessive processing, thereby reducing the load and time required for image processing.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If super-resolution processing is executed for all target objects, then measurement precision is improved, but processing time increases

Engineering Contradiction:
Improveimage resolutionVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system dynamically changes the processing parameter (resolution level) based on the size parameter of the target object. Small target objects trigger super-resolution processing to achieve sufficient measurement precision, while large target objects use standard resolution processing to minimize processing time. This parameter adaptation resolves the contradiction by matching processing intensity to actual needs.

Inventive Principle:
Principle #35Parameter changes

2Manufacturing precision

If super-resolution processing is executed for all image data, then manufacturing precision is improved, but productivity decreases

Engineering Contradiction:
Improverecognition accuracyVSAvoidprocessing throughput
Core Design Contradiction:
Manufacturing precisionVSProductivity

Solution Approach 1:

The system applies different processing qualities to different portions of the workload based on target object characteristics. Instead of uniformly applying super-resolution processing to all images, it selectively applies high-quality processing only to images containing small target objects that require enhanced resolution for accurate recognition. This local quality approach maintains high manufacturing precision where needed while preserving overall productivity.

Inventive Principle:
Principle #3Local quality

3Measurement precision

If a narrow camera visual field is used, then measurement precision is improved, but adaptability decreases

Engineering Contradiction:
Improveimage resolutionVSAvoidvisual field coverage
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system dynamically adjusts the effective visual field coverage by selectively processing different regions or objects at different resolution levels. When small target objects are detected, the system applies super-resolution processing to enhance detail in those specific regions. This dynamic approach allows the system to maintain narrow visual field settings (which provide high resolution) while adapting to handle various target object sizes through intelligent processing selection.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3118572B1Image processing device and substrate production system
Publication Date: 2021.08.25 FUJI CORP
  • EP3118572B1 patent drawingFigure 1
  • EP3118572B1 patent drawingFigure 2
  • EP3118572B1 patent drawingFigure 3

AI summary

An object is to provide an image processing device capable of reducing the load of image processing while shortening the time required for the image processing which uses super-resolution processing. The image processing device is provided with a process determination section which determines an execution necessity of the super-resolution processing in relation to image data during execution of a production process for every type of target object, a super-resolution processing section which executes the super-resolution processing which uses a plurality of items of the image data according to determination results of the process determination section to generate high resolution data, and a state recognition section which recognizes a state of the target object based on, of the image data and the high resolution data, the one corresponding to the determination results of the process determination section.