Image Processing Apparatus Using Learned Model for Setting Recommendation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users with limited knowledge of image processing struggle to set appropriate settings on Multi Function Peripherals (MFPs) for generating desired image data, leading to suboptimal results.

Innovation Solution

An image processing apparatus and method that uses a learned model to classify image data and recommend setting items to users, reducing the load on users by presenting suggested settings based on the type of image data, thereby ensuring desired output.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a user interface with multiple setting items is provided for image processing, then the flexibility and control over image processing is improved, but the ease of operation deteriorates for users with poor knowledge of image processing

Engineering Contradiction:

Improveimage processing control flexibilityVSAvoiduser operation difficulty

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system automatically analyzes the input image data and selects appropriate processing settings without requiring user intervention. The processor autonomously determines processing parameters based on image characteristics, enabling the system to serve itself rather than requiring user expertise for basic processing tasks.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

An intermediary mechanism is introduced between the user and the complex image processing system. This mediator automatically bridges the gap by interpreting user input images and translating them into appropriate processing parameters, eliminating the need for users to directly interact with complex setting items.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Ease of operation

If automatic setting recommendation is implemented, then the ease of operation is improved for users with poor knowledge, but the device complexity increases due to the need for image analysis and learning models

Engineering Contradiction:

Improveuser operation difficultyVSAvoidsystem structure complexity

Core Design Contradiction:

Ease of operationVSDevice complexity

Solution Approach 1:

The system performs preliminary analysis of image data before processing begins. By pre-analyzing image characteristics and pre-determining appropriate settings, the system prepares everything needed for processing in advance, eliminating the need for complex real-time user interactions while managing system complexity through structured pre-processing steps.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Manual user selection of processing parameters is replaced with an automated mechanical system that uses image analysis algorithms and learning models. This substitution transforms the manual operation process into an automated computational process, reducing operational difficulty for users while concentrating system complexity in the form of algorithms rather than user interface complexity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11695887B2Image processing apparatus, method of controlling the same, and storage medium

Publication Date: 2023.07.04 CANON KK

AI summary

An image processing apparatus and a method of controlling the image processing apparatus are provided. The image processing apparatus holds a type of image data and a setting item of image processing corresponding to the type in association with each other, and obtains, by applying a learned learning model to image data which are input, a result of classifying the image data into the type. The image processing apparatus presents, based on the setting item input by a user and the held setting item that corresponds to the type of the obtained image, a recommended setting item corresponding to the image data to the user.