A survey of fingerprint classification Part II: Experimental analysis and ensemble proposal

Abstract

In the first part of this paper we reviewed the fingerprint classification literature from two different perspectives: the feature extraction and the classifier learning. Aiming at answering the question of which among the reviewed methods would perform better in a real implementation we end up in a discussion which showed the difficulty in answering this question. No previous comparison exists in the literature and comparisons among papers are done with different experimental frameworks. Moreover, the difficulty in implementing published methods was stated due to the lack of details in their description, parameters and the fact that no source code is shared. For this reason, in this paper we will go through a deep experimental study following the proposed double perspective. In order to do so, we have carefully implemented some of the most relevant feature extraction methods according to the explanations found in the corresponding papers and we have tested their performance with different classifiers, including those specific proposals made by the authors. Our aim is to develop an objective experimental study in a common framework, which has not been done before and which can serve as a baseline for future works on the topic. This way, we will not only test their quality, but their reusability by other researchers and will be able to indicate which proposals could be considered for future developments. Furthermore, we will show that combining different feature extraction models in an ensemble can lead to a superior performance, significantly increasing the results obtained by individual models.

A framework for radial data comparison and its application to fingerprint analysis

“…This does not reduce the representativity of the datasets generated with SFinGe, since modern sensors for fingerprint recording produce images that are closer to those by SFinGe than to those in NIST-4. This variable behaviour has also been shown in previous studies on the topic [37]. Regarding the NIST-4 dataset, we find that TSPD-C3 is the best performer, obtaining the greatest PDP (69.90%).…”

“…For this reason, several strategies have been developed to minimize the number of comparisons to be performed. Among them, the most used one is classification [16,37,38], which consists of classifying each fingerprint according to the general structure of its ridges. In this way, when an input fingerprint has to be matched, it only need to be compared with those belonging to the same class.…”

On the use of convolutional neural networks for robust classification of multiple fingerprint captures

“…These are the databases used for the study: SFinGe: To replicate the experiments carried out in Ref. , we used the SFinGe software to generate three different databases of synthetic fingerprints with different qualities following the natural class distribution. This approach enables a meaningful comparison of the tested classifiers according to a common measure of quality of the fingerprints.…”

A Survey on Data Mining Techniques Applied to Electricity-Related Time Series Forecasting

“…Recently, ensemble models are beginning to receive attention from the research community due to the good performance obtained for classification problems [122,123]. In general, ensemble models consists in combining different models in order to improve the accuracy of the individual models.…”