Feature Fusion Methods for Indexing and Retrieval of Biometric Data: Application to Face Recognition With Privacy Protection

  title={Feature Fusion Methods for Indexing and Retrieval of Biometric Data: Application to Face Recognition With Privacy Protection},
  author={Pawel Drozdowski and Fabian Stockhardt and Christian Rathgeb and Daile Osorio-Roig and Christoph Busch},
  journal={IEEE Access},
Computationally efficient, accurate, and privacy-preserving data storage and retrieval are among the key challenges faced by practical deployments of biometric identification systems worldwide. In this work, a method of protected indexing of biometric data is presented. By utilising feature-level fusion of intelligently paired templates, a multi-stage search structure is created. During retrieval, the list of potential candidate identities is successively pre-filtered, thereby reducing the… Expand
Biometric Template Protection for Neural-Network-based Face Recognition Systems: A Survey of Methods and Evaluation Techniques
A survey of biometric template protection (BTP) methods proposed for securing face “templates” in neural-network-based face recognition systems, with a greater focus on empirical evaluation strategies to provide more concrete insights into the irreversibility and renewability/unlinkability of face BTP methods in practice. Expand


Signal-level Fusion for Indexing and Retrieval of Facial Biometric Data
This work presents a method of indexing biometric databases, which relies on signal-level fusion of facial images (morphing) to create a multi-stage data-structure and retrieval protocol, which makes it possible to reduce the necessary number of biometric template comparisons to complete a biometric identification transaction. Expand
Cancelable Permutation-Based Indexing for Secure and Efficient Biometric Identification
This paper transforms a permutation-based index, which is the state-of-the-art index in the field of similarity search, and performs a query search without recovering the original index, and proposes a method to artificially generate biometric features necessary to generate an index based on GANs. Expand
A coding scheme for indexing multimodal biometric databases
  • A. Gyaourova, A. Ross
  • Computer Science
  • 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
  • 2009
This work describes a method for indexing large-scale multimodal biometric databases based on the generation of an index code for each enrolled identity, and suggests that indexing has the potential to substantially improve the response time of multimodals biometric systems without compromising the accuracy of identification. Expand
Multi-Biometric Identification With Cascading Database Filtering
This article presents a biometric identification system which relies on a successive pre-filtering of the potential candidate list using multiple biometric modalities, coupled with a weighted score-level information fusion. Expand
Bloom filter-based search structures for indexing and retrieving iris-codes
This work presents an iris indexing scheme based on Bloom filters and binary search trees that is shown to be theoretically scalable for arbitrarily many enrollees and defines several prerequisites necessary for a transparent and comprehensive methodology of biometric workload reduction results dissemination. Expand
Index Codes for Multibiometric Pattern Retrieval
  • A. Gyaourova, A. Ross
  • Computer Science
  • IEEE Transactions on Information Forensics and Security
  • 2012
The proposed indexing scheme has the potential to substantially reduce the response time without compromising the accuracy of identification and can be easily extended to retrieve pertinent identities from multimodal databases. Expand
Privacy-Preserving Indexing of Iris-Codes with Cancelable Bloom Filter-based Search Structures
This paper presents a, best to the authors' knowledge, first method in the scientific literature for indexing protected iris templates, based on applying random permutations to Iris-Code rows, and subsequent indexing using Bloom filters and binary search trees. Expand
Template Protection based on Homomorphic Encryption: Computationally Efficient Application to Iris-Biometric Verification and Identification
To solve the problem of the computational overload linked to the encryption scheme, the most consistent bits of the iris-code are moved to the beginning of the template, thereby reducing the execution time and the resulting system grants template protection in a computationally efficient way. Expand
Open-set face identification with index-of-max hashing by learning
This paper addresses the large-scale open-set face identification problem with a compact facial representation that is based on the index-of-maximum (IoM) hashing, which was designed for biometric template protection. Expand
Face biometrics with renewable templates
This paper integrates the helper-data system based on reliable component selection with face biometrics such that a system in which the templates are privacy protected, and multiple templates can be derived from the same facial image for the purpose of template renewability is achieved. Expand