Image Content Analysis for Automatic Print Setting Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In digital reprographic businesses, a significant portion of operator time is spent on manual job preparation, such as setting print settings and previewing, which is inefficient and can be automated.

Innovation Solution

A printing system that uses a print processor to analyze image content by reducing image resolution, computing a minimum bounding box, categorizing image regions, and automatically selecting print settings based on image type, thereby streamlining the printing process and reducing operator intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual job preparation is used to assign print settings to every page, then print quality and operator control are maintained, but operator time and preparation effort increase significantly

Engineering Contradiction:
Improveprint setting accuracyVSAvoidjob preparation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs automatic image content analysis and self-categorization, enabling the printing system to automatically determine appropriate print settings without operator intervention. The processor analyzes image characteristics and assigns print parameters autonomously based on detected content types.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary image analysis and categorization before the actual printing process. By pre-analyzing image content and determining appropriate settings in advance, the system prepares print parameters automatically, eliminating the need for manual setting assignment during job preparation.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If automatic image content analysis is implemented, then job preparation time is reduced, but system complexity increases

Engineering Contradiction:
Improveprinting throughputVSAvoidprocessing system complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The automatic analysis process is divided into distinct stages: image preprocessing, feature extraction, content categorization, and print setting assignment. This segmentation allows each function to be implemented independently and simplifies the overall system architecture by breaking down complex processing into manageable modules.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary processing layer between image input and printing output. This intermediate analysis module acts as a mediator that automatically determines print settings based on image content, reducing the need for complex direct control interfaces and simplifying operator interaction.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If detailed image analysis is performed to accurately categorize content, then print setting accuracy improves, but processing time increases

Engineering Contradiction:
Improveimage categorization accuracyVSAvoidimage processing time
Core Design Contradiction:
Measurement precisionVSDuration of action of moving object

Solution Approach 1:

The system performs partial analysis by focusing on key image features and characteristics that are most relevant for categorization. Rather than analyzing every detail of the image, the processor examines sufficient features to determine content type and assign appropriate print settings, achieving good accuracy without excessive processing time.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3028439B1Analysing image content
Publication Date: 2021.06.23 HEWLETT PACKARD DEVELOPMENT COMPANY LP
  • EP3028439B1 patent drawingFigure 1~2
  • EP3028439B1 patent drawingFigure 3
  • EP3028439B1 patent drawingFigure 4

AI summary

A computer implemented method of analysing the content of a digital image, for example a page to be printed, computes (41) a boundary (302) enclosing all the non- white content of the image. The image within the boundary is then divided (43) into regions (306) based on a predetermined division rule. For each region the number of unique colours and the proportion of non- white pixels are computed (44). The image is then categorised (45) according to the result of those computations. The categorisation can be used to automatically set (51) print settings according to the content of the image.