A Fingerprint Retrieval System Using Bag of Features of SIFT and SURF

Authors

  • Somashekhar B. M., Sharath Kumar Y. H., Ranjith K. C., Puneeth P.

DOI:

https://doi.org/10.17762/msea.v71i4.698

Abstract

In this work, we proposed finger print classification using fusion features of robust SURF and scale and rotation invariant SIFT features. The visual vocabulary feature is created with extracted features. Here we are using Bag of Features (BoF) for generating the vocabulary. Clusters of vocabulary words are generated using k-means clustering. Using kNN, the rank of each training dataset image with query image is found and they are arranged in the order of rank. We finally display top n similar images from the order of rank as retrieved images.

Experiments are carried out on the FVC fingerprint dataset and captured image dataset to analyze the effectiveness of the proposed method. It is observed from the experiments that the retrieval results  contains more than 50% of recall value in almost all cases when concatenated features are used with BoF classifier for calculating similarity between the query and dataset images in both the kind of datasets.

Downloads

Published

2022-09-02

How to Cite

Somashekhar B. M., Sharath Kumar Y. H., Ranjith K. C., Puneeth P. (2022). A Fingerprint Retrieval System Using Bag of Features of SIFT and SURF. Mathematical Statistician and Engineering Applications, 71(4), 1772–1786. https://doi.org/10.17762/msea.v71i4.698

Issue

Section

Articles