Figure - uploaded by Khamis A. Zidan
Content may be subject to copyright.
Source publication
Received, 2019
Currently, Biometrics has been utilized the top five modality of face, voice, IRIs, fingerprint, and palm to identify individuals. Comparatively, these Biometrics systems need complex computation to be slow and an easy target to hack. Alternatively, this work proposes a novel biometrics system of highly secured recognition with low...
Citations
... The complete balance of the histogram was done first. This was joined by a balance of the Fuzzy histogram [23]. ...
This paper examines a collection of finger vein enhancement stages that have not only low computational complexity but also high distinguishing capacity. This proposed series of enhancement stages is based on the equalization of fuzzy histograms. A mixture of Hierarchical Centroid and Gradient Histograms was used to extract features. Both the enhancement stages were evaluated using 6 fold stratified cross validation with K Nearest Neighbor and Support Vector Machine (SVM). Experimental results show that the (KNN) algorithm is a simple, easy-to-implement supervised machine learning algorithm which can be used to solve problems of classification and regression. Calculations of KNN in the test data are highly accurate. Using stratified 6-fold analyzes on all fingers of all hands in the collected database, when selecting the right and middle fingers based on the analysis of the 106 people in the data set. Compared with SVM and related works, the algorithm proposed has optimum performance.
... K-tree decomposition structure as shown in Fig. 11 Both of SDUMLA-HMT Database Image and collected database by proposed device are evaluated with K Nearest Neighbor and Deep Neural Networks using 6 fold stratified cross validation. The more details for mechanical operation of KNN and DNN in [36], [37], [38], [39]. K-nearest neighbor classifier, also called KNN [40] is a primitive but immensely favored classification method. ...
One of the safest biometrics of today is finger vein- but this technic arises with some specific challenges, the most common one being that the vein pattern is hard to extract because finger vein images are always low in quality, significantly hampered the feature extraction and classification stages. Professional algorithms want to be considered with the conventional hardware for capturing finger-vein images is by using red Surface Mounted Diode (SMD) leds for this aim. For capturing images, Canon 750D camera with micro lens is used. For high quality images the integrated micro lens is used, and with some adjustments it can also obtain finger print. Features extraction was used by a combination of Hierarchical Centroid and Histogram of Gradients. Results were evaluated with K Nearest Neighbor and Deep Neural Networks using 6 fold stratified cross validation. Results displayed improvement as compared to three latest benchmarks in this field that used 6-fold validation and SDUMLA-HMT. The work novelty is owing to the hardware design of the sensor within the finger-vein recognition system to obtain, simultaneously, highly secured recognition with low computation time ,finger vein and finger print at low cost, unlimited users for one device and open source.
