Robust partitioning and indexing for iris biometric database based on local features

Abstract

Explosive growth in the volume of stored biometric data has resulted in classification and indexing becoming important operations in image database systems. Consequently, researchers are focused on finding suitable features of images that can be used as indexes. Stored templates have to be classified and indexed based on these extracted features in a manner that enables access to and retrieval of those data by efficient search processes. This paper proposes a method that extracts the most relevant features of iris images to facilitate minimisation of the indexing time and the search area of the biometric database. The proposed method combines three transformation methods DCT, DWT and SVD to analyse iris images and extract their local features. Further, the scalable K-means++ algorithm is used for partitioning and classification processes, and an efficient parallel technique that divides the features groups causing the formation of two b-trees based on index keys is applied for search and retrieval. Moreover, search within a group is achieved using a proposed half search algorithm. Experimental results on three different publicly iris databases indicate that the proposed method results in a significant performance improvement in terms of bin miss rate and penetration rate compared with conventional methods.

Stereoscopic Image Feature Indexing Based on Hybrid Grid Multiple Suffix Tree and Hierarchical Clustering

“…The operation of the structures often inconvenient, especially the deletion is more complex, and the utilization rate of memory space is relatively low. The index based on data partition usually has balanced hierarchical trees, such as B-tree, B+-tree, and R-tree formed from B-tree extended to space [15]. The improved tree structures also have R * -tree, X-tree, SS-tree, SR-tree and so on based on classic R-tree [16], and classic suffix tree [17], [18].…”

Security Clustering Algorithm Based on Integrated Trust Value for Unmanned Aerial Vehicles Network

“…The k-means++ algorithm [26] calculates the positional data of all nodes before selecting the initial center, so that the distance between the selected initial centers is longest, and the iterative process of the clustering algorithm is therefore reduced.…”

Computational workload in biometric identification systems: an overview

“…[111, 114, 115, 122]), b or b + trees (e.g. [112, 113, 124, 125]), other tree‐like search structures (e.g. [35, 92, 110, 116, 121, 123]), and forests thereof (e.g.…”