Pattern Vector Object Detection Under Changing Illumination

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for object detection in digital images under varying illumination conditions are slow and unreliable, particularly when objects appear light against a dark background or dark against a light background.

Innovation Solution

A method involving a pattern vector that assigns each characteristic pixel a first and second direction, determining intensity overall values in these directions, and calculating a success value based on the difference or ratio of these values to reliably detect the object's position and orientation, especially for banknote security elements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional object detection methods (e.g., Viola-Jones) are used, then object detection can be performed, but detection speed is slow and reliability is poor under changing illumination conditions

Engineering Contradiction:
Improvedetection reliabilityVSAvoiddetection speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent segments the object detection problem by identifying and tracking only characteristic pixels (edge pixels and high-frequency pixels) rather than processing all pixels. The pattern vector contains only these characteristic pixel coordinates, enabling fast comparison while maintaining detection reliability under varying illumination conditions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts only the essential features (characteristic pixels with their coordinates and directions) from the complete image data. By removing redundant pixel information and keeping only the discriminative characteristic pixels, the method achieves both speed and reliability in object detection.

Inventive Principle:
Principle #2Taking out (Extraction)

2Measurement precision

If complete image data is processed for object detection, then detection accuracy is maintained, but processing time increases

Engineering Contradiction:
Improvedetection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent divides the image processing task by focusing only on characteristic pixels (edge and high-frequency pixels) rather than processing the entire image. This segmentation maintains detection accuracy by preserving critical features while dramatically reducing processing time through selective pixel analysis.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes the parameter representation from complete pixel intensity data to a simplified pattern vector containing only characteristic pixel coordinates and directions. This parameter transformation maintains essential object information while reducing data dimensionality and processing requirements.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS12620196B2Method for detecting an object in a search image, method for generating a pattern vector, and use of a method for determining a position and/or orientation of a security element of a banknote
Publication Date: 2026.05.05 GIESECKE & DEVRIENT CURRENCY TECHNOLOGY GMBH
  • US12620196B2 patent drawing
  • US12620196B2 patent drawing
  • US12620196B2 patent drawing

AI summary

A method for detecting an object in a search image, includes: a) providing a pattern vector which describes the object by means of coordinates of characteristic pixels; b) shifting the pattern vector over different positions of the search image; c) determining a success value at each of the different positions; and d) detecting the object at the position on the basis of the success value, wherein each characteristic pixel is assigned a first direction and a second direction that differs from the first direction. The first and second overall intensity values of one-dimensionally arranged pixels are determined in the first and second directions, respectively. A difference value between the first and second overall intensity values is determined in each case, and the success value is determined on the basis of the respective difference values.