Image Processing Device Microcode Model Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image processing devices can only handle a single format and type of main zone, limiting their ability to precisely process main areas of different formats and models captured in the same image.

Innovation Solution

A device that identifies and decodes microcode associated with the main area, allowing it to determine the model, correct perspective effects, and apply specific processing sequences to main and secondary zones, enabling the processing of multiple main areas independently.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a single homothetic model of the main area is used, then the device complexity is reduced and the processing is simplified, but the adaptability to process main areas of different formats and models is limited

Engineering Contradiction:
Improveability to process main areas of different formats and modelsVSAvoidcomplexity of the processing device
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent applies preliminary action by pre-defining multiple models of main areas (first model, second model, etc.) with different width-to-height ratios before the actual image processing occurs. These models are stored in advance and selected based on the characteristics of the captured image, allowing the device to handle different formats without increasing operational complexity during processing.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements parameter changes by varying the width-to-height ratio parameter across different main area models. The first model has a first width-to-height ratio while the second model has a second width-to-height ratio different from the first. This parameter variation enables the device to adapt to different document formats while maintaining a structured approach to model selection.

Inventive Principle:
Principle #35Parameter changes

2Manufacturing precision

If the main area is extracted using a fixed format, then the manufacturing precision of the extraction process is improved, but the ease of operation for processing different document types is reduced

Engineering Contradiction:
Improveprecision of main area extractionVSAvoidease of processing different document formats
Core Design Contradiction:
Manufacturing precisionVSEase of operation

Solution Approach 1:

The patent applies dynamics by making the main area extraction process adaptive rather than fixed. The system dynamically selects the appropriate model (first model or second model) based on the characteristics of the captured image, allowing the extraction process to adjust its parameters (width-to-height ratio) while maintaining precision for each specific document type.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent implements universality by creating a processing device that can handle multiple document formats and types through a single unified system. The device uses multiple pre-defined models that cover different formats, enabling one device to perform the function of extracting main areas from various document types (invoices, receipts, forms, etc.) without requiring separate specialized systems.

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

3Measurement precision

If perspective correction is applied using a single model, then the processing time is reduced, but the measurement precision of the extracted main area is compromised for non-matching formats

Engineering Contradiction:
Improveaccuracy of extracted main area dimensionsVSAvoidtime for model selection and processing
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-calculating and storing multiple models with different width-to-height ratios before processing. This allows the system to quickly select the appropriate pre-prepared model that matches the document format, avoiding the need for time-consuming real-time calculations while maintaining high measurement precision for the extracted main area.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3779785B1Printed surface and device and method for processing images of such a printed surface
Publication Date: 2024.12.04 HOLDHAM
  • EP3779785B1 patent drawingFigure 1
  • EP3779785B1 patent drawingFigure 2
  • EP3779785B1 patent drawingFigure 3

AI summary

The automatic image processing device for printed surfaces (10) comprising at least one position marker (3, 4, 5, 6) of a main area (1) of a printed surface (10) of the image to be extracted, the device comprising: - means for acquiring the image of printed surfaces; - means for identifying at least one position marker in the image of printed surfaces; and - means for extracting the main area located in the plane of the image as a function of at least one position marker thus identified, - means for extracting the secondary areas located in the plane of the projected image and associated with the main area, the device further comprising means for identifying and decoding a microcode (2), associated with the main area to be extracted, in the image of the printed surfaces, the microcode being placed in a predefined manner with respect to the main area to be extracted.