Offline Identity Authentication Using Cascaded PCA and SVM

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional identity authentication methods rely on the face database of the Ministry of Public Security, making it difficult to determine whether the chip image, surface image, and holder image of an ID card are consistent, especially in cases of fake ID cards with genuine chips and fake surfaces, leading to increased burden and potential false or missed detections.

Innovation Solution

An offline identity authentication method using cascaded PCA convolutions and deep convolutional neural networks to extract feature vectors from multiple images, fuse information through a score fusion strategy with a supervisory signal, and input the fusion vector into a pre-trained SVM classifier to determine consistency between the chip, surface, and live face images, eliminating the need for a face database and providing an automated authentication result.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If online authentication method is used to check identity, then authentication can be performed with Ministry of Public Security face database, but application places are limited and fake ID cards with genuine chips cannot be automatically identified

Engineering Contradiction:
Improveauthentication accuracyVSAvoidapplication places
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent introduces an offline authentication system that acts as an intermediary between ID card verification and identity confirmation. This system uses local databases and algorithms to authenticate identities without requiring connection to the Ministry of Public Security database, thereby enabling authentication in locations where online access is unavailable while maintaining reliability through multiple verification mechanisms including face recognition and chip authentication.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The authentication process is segmented into multiple independent verification components: chip authentication, face recognition, and database verification. This segmentation allows the system to perform partial authentication offline using local algorithms and databases, then complete the verification process when online access is available, thus improving both adaptability and reliability.

Inventive Principle:
Principle #1Segmentation

2Reliability

If visual inspection is used to check consistency among chip image, surface image and holder image, then fake ID cards can be identified, but burden on checker increases and false detection or missed detection occurs

Engineering Contradiction:
Improvefake ID card identificationVSAvoidchecker burden
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The system implements automated image consistency verification that performs self-service authentication by comparing chip images, surface images, and holder images using local algorithms. The system automatically detects inconsistencies and flags potential fake ID cards without requiring manual visual inspection by checkers, thereby reducing operational burden while maintaining high reliability through automated pattern recognition and comparison algorithms.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual visual inspection with automated computer vision and image processing algorithms. The system uses digital image analysis, feature extraction, and pattern matching to verify consistency among multiple images, substituting human visual inspection with mechanical/algorithmic processes that are more reliable and less burdensome.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If manual visual inspection is used to verify image consistency, then authentication can be performed offline, but authentication efficiency decreases due to increased checker burden

Engineering Contradiction:
Improveoffline authentication capabilityVSAvoidauthentication efficiency
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The system replaces manual visual inspection with automated image processing and pattern recognition algorithms that can perform offline authentication. The automated system extracts features from chip images, surface images, and holder images, then compares them using local databases and algorithms, enabling offline verification without requiring human checkers to manually inspect images, thus maintaining adaptability while dramatically improving authentication efficiency.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an automated verification system that acts as an intermediary between image capture and authentication decision. This system uses local databases and algorithms to perform offline verification, providing automated feedback to checkers and enabling high-speed authentication even without network connectivity to central databases.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3471023B1Offline identity authentication method and apparatus
Publication Date: 2021.09.15 GRG BANKING EQUIPMENT CO LTD
  • EP3471023B1 patent drawingFigure 1
  • EP3471023B1 patent drawingFigure 2
  • EP3471023B1 patent drawingFigure 3

AI summary

Disclosed are an offline identity authentication method and an apparatus which are used to solve the problem that the prior art relies on a human face database provided by the Ministry of Public Security and that it is difficult to identify a three-way consistency of a chip avatar, a document surface avatar and a certificate holder image. The method comprises: acquiring two or more images for identify authentication to construct a to-be-authenticated multivariate image group (101); extracting a cascaded PCA convolution feature for each image in the to-be-authenticated multivariate image group to obtain a corresponding eigenvector (102); merging the image information of the to-be-authenticated multivariate image group according to the eigenvector and a fractional fusion strategy with a supervised signal to obtain a corresponding merged vector (103); and sending the merged vector to an SVM classifier which has been preliminarily trained to determine the consistency of the image in the to-be-authenticated multivariate image group, so as to obtain an identity authentication result (104).