Rectangular Image Region Detection for Batch Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional image processing methods require cumbersome and time-consuming steps when photographing multiple pages, involving individual image processing and correction, leading to overload and laborious tasks in electronic apparatuses.

Innovation Solution

A method and apparatus that detect rectangular image regions in multiple images, determine corresponding coordinates, and perform image processing by associating identical view angles, allowing simultaneous processing of images with matching angles using stored coordinates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If image processing is performed on each photographed image individually after completing multiple photographs, then image processing accuracy is maintained, but processing time increases and apparatus overload occurs

Engineering Contradiction:
Improveimage processing accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent detects rectangular image regions and obtains coordinates during the image reception phase itself, before all images are fully captured. This preliminary detection and storage of coordinate information eliminates the need for repeated processing after all images are taken, reducing overall processing time while maintaining accuracy through pre-computed reference data

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent merges the processing of multiple images by detecting rectangular regions in one image and reusing those detection results for other images with identical view angles. This combining approach processes multiple images simultaneously using shared coordinate data, significantly reducing total processing time and apparatus load

Inventive Principle:
Principle #5Merging (Combining)

2Reliability

If image processing is performed on each photographed image individually, then processing thoroughness is ensured, but operational complexity increases

Engineering Contradiction:
Improveprocessing thoroughnessVSAvoidoperational complexity
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent creates a copy of coordinate information from one rectangular image region detection and reuses it for multiple images with identical view angles. Instead of performing complex detection operations on each image individually, the system copies previously detected coordinates and applies them to matching images, simplifying operations while ensuring consistent processing quality

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent makes the coordinate detection process universal by detecting rectangular regions in any image and storing them as reusable reference data. This coordinate information serves multiple functions: it processes the original image accurately and simultaneously provides processing data for all other images with matching view angles, reducing operational complexity across the entire batch

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

3Measurement precision

If coordinates are detected for each image separately after photographing, then coordinate accuracy is maintained, but management burden increases

Engineering Contradiction:
Improvecoordinate accuracyVSAvoidmanagement burden
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs coordinate detection and storage during the image reception phase, before all images are completely captured and processed. By obtaining and storing coordinates preliminarily with link associations, the system creates an organized reference structure that simplifies subsequent management and reduces the burden of handling multiple images individually

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent merges coordinate management by storing coordinates from one image as shared reference data for multiple images with identical view angles. This consolidation approach reduces the total number of coordinate sets that need to be managed, as a single detected coordinate set serves multiple images, thereby reducing management burden while preserving coordinate accuracy through link associations

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3222036B1Method and apparatus for image processing
Publication Date: 2021.05.05 SAMSUNG ELECTRONICS CO LTD
  • EP3222036B1 patent drawingFigure 1~2
  • EP3222036B1 patent drawingFigure 3
  • EP3222036B1 patent drawingFigure 4

AI summary

A method for image processing is provided comprising: detecting a rectangular image region (RIR) in one of a plurality of images while the plurality of images is being received; obtaining a coordinate corresponding to the detected RIR; and storing in a memory the coordinate and a link associating the coordinate with the image in which the RIR is detected.