Fingerprint Block Analysis for Low-Compute Biometric Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing biometric feature extraction methods require sophisticated neural networks and computationally expensive pre-processing steps like Gabor filtering, orientation maps, and segmentation masks, leading to high resource consumption.

Innovation Solution

A computer-implemented method that processes images into blocks of uniform size, using a neural network to identify biometric features, reducing the need for trained orientation maps and segmentation masks, and providing a binary decision on feature presence and type, with optional additional information on quality, position, and orientation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If sophisticated neural networks and pre-processing steps (Gabor filtering, orientation maps, segmentation masks) are used to extract biometric features, then measurement precision of biometric features is improved, but use of energy and computational resources increases significantly

Engineering Contradiction:
Improvebiometric feature identification accuracyVSAvoidcomputational resource consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent divides the fingerprint image into multiple blocks of identical size, processing each block independently to identify biometric features. This segmentation approach reduces the computational complexity of processing the entire image at once, allowing for efficient resource utilization while maintaining feature detection accuracy through localized analysis of each block

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts only the essential biometric feature information from fingerprint blocks without requiring complex pre-processing steps like Gabor filtering or orientation maps. By directly analyzing pixel intensity values and gradients in each block, the system extracts minutiae features (ridge endings, bifurcations) with reduced computational overhead, eliminating unnecessary processing steps that consume energy

Inventive Principle:
Principle #2Taking out (Extraction)

2Reliability

If traditional biometric processing methods with multiple pre-processing steps are employed, then reliability of biometric information is improved, but device complexity increases

Engineering Contradiction:
Improvebiometric information reliabilityVSAvoidprocessing system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple traditional processing steps into a single integrated block-based analysis approach. Instead of sequentially applying Gabor filtering, orientation estimation, and segmentation masks, the system performs all necessary analyses directly on divided image blocks, merging these functions into a unified processing pipeline that reduces system complexity while maintaining detection reliability

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

Each image block processes its own pixel data independently to identify biometric features within that block, without requiring external orientation maps or segmentation masks from other processing stages. This self-contained approach allows blocks to autonomously detect minutiae features based on local pixel intensity variations and gradients, reducing inter-dependency and simplifying the overall system architecture

Inventive Principle:
Principle #25Self-service

3Measurement precision

If comprehensive biometric feature analysis is performed, then measurement precision is improved, but loss of time in processing increases

Engineering Contradiction:
Improvebiometric feature detection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent processes fingerprint image blocks in a systematic periodic manner, analyzing each block independently and in sequence. This periodic processing approach allows for efficient parallelization and optimization, where each block undergoes the same standardized analysis routine, enabling rapid processing while maintaining consistent detection accuracy across the entire fingerprint image

Inventive Principle:
Principle #19Periodic action

Data Source

PatentEP4668238A1Computer-implemented method for obtaining information on bio-metric features of a user
Publication Date: 2025.12.24 IDENTY INC
  • EP4668238A1 patent drawingFigure 1
  • EP4668238A1 patent drawingFigure 2
  • EP4668238A1 patent drawingFigure 3

AI summary

A computer-implemented method for obtaining information on biometric features of a fingerprint of a user, the method comprising: - obtaining an image comprising an object carrying one or more biometric features of a user, the image having a size of NxM pixels - processing the image and determining information indicative at least of a presence of a biometric feature in the block and a kind of the biometric feature to obtain a result - outputting the result identifying the information wherein the result has a form of n x m blocks of identical size and the result associates information indicative at least of a presence of a biometric feature and a kind of the biometric feature with each block, wherein N is an integer multiple of n and M is an integer multiple of m.