A Novel Approach to Human Recognition Based on Finger Geometry
Maciej Szymkowski , Khalid Saeed
AbstractBiometrics is one of the most important branches of science toward computer systems safety. One of the physiological traits is finger geometry as part of hand geometry. The purpose of this paper is to introduce an algorithm that can extract significant features from finger geometry by which human recognition can be achieved. All samples were obtained with the device created by the authors. The software part of the proposed approach consists of simple image processing methods that improve image quality before feature extraction, feature vector creation and classification. A total of 150 samples from fifty users were included in the analysis of the proposed system. Identity connected with each sample can be automatically provided by the system with an accuracy of 83%. The results were calculated on the basis of k-nearest neighbors algorithm and different distance calculation metrics: Euclidean, Manhattan and Chebyshev.
|Publication size in sheets||0.6|
|Book||Rituparna Chaki, Cortesi Agostino, Saeed Khalid, Chaki Nabendu (eds.): Advanced Computing and Systems for Security, Advances in Intelligent Systems and Computing, vol. 996, no. 10, 2020, Springer, ISBN 978-981-13-8968-9, [978-981-13-8969-6 ], 111 p., DOI:10.1007/978-981-13-8969-6|
|Keywords in English||Finger geometry Human recognition Biometrics Image analysis Classification|
|Internal identifier||ROC 19-20|
|Score||= 20.0, 09-03-2020, MonographChapterAuthor|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.