Image Processing Apparatus Highlighting Search Results

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current image processing systems struggle to effectively highlight and identify non-character objects such as pictures, graphics, and tables in document images during keyword searches, as existing highlight methods are not effective due to color and shape differences, and compressing objects separately leads to larger data sizes and merged search results, making it difficult to distinguish target objects.

Innovation Solution

An image processing apparatus and method that generates electronic document data by integrating objects and background as a single image, using vector path descriptions and transparent frames for highlighting, allowing users to easily recognize search results without relying on object shape or compression state, and reducing data size by compressing all objects together.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If objects are compressed separately, then individual object processing is simplified, but data size increases and search results become merged

Engineering Contradiction:
Improveobject processing simplicityVSAvoiddata size
Core Design Contradiction:
Ease of manufactureVSQuantity of substance

Solution Approach 1:

The patent merges all objects into a single composite image for compression rather than compressing each object separately. This approach reduces overall data size by eliminating redundant compression overhead while maintaining the ability to perform object searches through metadata associations.

Inventive Principle:
Principle #5Merging (Combining)

2Manufacturing precision

If objects are compressed separately, then individual object quality is maintained, but search results cannot be distinguished from background

Engineering Contradiction:
Improveobject qualityVSAvoidsearch result identification
Core Design Contradiction:
Manufacturing precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent applies color or transparency changes to highlight search result objects within the composite image. By modifying the visual properties of identified objects through coloring or transparency adjustments, the system enables users to easily distinguish search results from the background and non-matching objects.

Inventive Principle:
Principle #32Color changes

3Quantity of substance

If objects are integrated into a single image, then data size is reduced, but individual object processing becomes difficult

Engineering Contradiction:
Improvedata sizeVSAvoidprocessing complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The patent segments the composite image into individual object regions through image processing techniques before compression. This segmentation allows the system to maintain simplified compression by treating the entire document as one image while still enabling individual object identification and processing through region separation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces metadata as an intermediary layer that associates objects with their identifiers and search keywords. This metadata mediation enables individual object processing and search functionality without requiring complex separate compression of each object, thus reducing data size while maintaining processing capability.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP2224359B1Image processing apparatus, image processing method, and computer program
Publication Date: 2019.11.13 CANON KK
  • EP2224359B1 patent drawingFigure 1
  • EP2224359B1 patent drawingFigure 2
  • EP2224359B1 patent drawingFigure 3

AI summary

An image processing apparatus extracts an object area (e.g., character, picture, line drawing, and table) from an input image and acquires a metadata to be associated with the object. The image processing apparatus generates a transparent graphics description for an object area having an attribute that requires generation of the transparent graphics description, and generates an electronic document while associating the transparent graphics description with the metadata. As transparent graphics description, an arbitrary shape of graphics can be used. Accordingly, the image processing apparatus can generate electronic document data suitable for a highlight expression, which is easy for users to recognize in a search operation using a keyword to search an object included in an electronic document.