FKPIndexNet: An efficient learning framework for finger-knuckle-print database indexing to boost identification

This paper addresses the problem of identification in the Finger-knuckle-print (FKP) databases. Identification determines the identity of a query of the FKP sample. It involves finding the most similar sample in the database by comparing the query FKP with all the templates stored in the database. It is a computationally expensive process that demands huge time for large databases. A technique is required that can reduce the search space and limits the number of comparisons to boost the identification process. Such a technique is called indexing. It devises a fixed size small candidate list for a given FKP sample in constant time for searching. The paper proposes FKPIndexNet that learns similarity preserving hash codes for generating an index table. It employs a specialized autoencoder network to learn feature embeddings such that they have high intra-class and low inter-class similarity. The proposed technique is examined on two publicly available FKP databases viz., PolyU-FKP and IITD-FKP. Experimental results show that the proposed method achieves 100% hit rate at a penetration rate of only 3.42% for PolyU-FKP database and 0.32% for IITD FKP database, respectively. This implies that for a query FKP sample, to get a true match with 100% confidence, only 3.42% and 0.32% of the PolyU-FKP and IITD FKP database needs to be compared, respectively. Results and analysis demonstrate the superiority of the proposed technique compared to other state-of-the-art approaches. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

This paper addresses the problem of identification in FKP databases and proposes the FKPIndexNet technique, which generates index tables using similarity preserving hash codes to achieve high identification accuracy and low search time.