Palm print verification based deep learning

Abstract

In this paper, we consider a palm print characteristic which has taken wide attentions in recent studies. We focused on palm print verification problem by designing a deep network called a palm convolutional neural network (PCNN). This network is adapted to deal with two-dimensional palm print images. It is carefully designed and implemented for palm print data. Palm prints from the Hong Kong Polytechnic University Contact-free (PolyUC) 3D/2D hand images dataset are applied and evaluated. The results have reached the accuracy of 97.67%, this performance is superior and it shows that our proposed method is efficient.

Interpreting arabic sign alphabet by using the deep learning

“…Table 3 shows the comparison between the testing accuracies of various DL network architectures. The state-of-the-art network architectures that have been considered for the comparison are the Deep Fingerprint Classification Network (DFCN) [11], X Axis Classification Model (XCM) [16][17], Y Axis Classification Model (YCM) [16][17], Z Axis Classification Model (ZCM) [16][17] and Palm Convolutional Neural Network (PCNN) [12]. From Table 3, it is noted that all the compared networks have not obtained satisfactory accuracies.…”

“…Many academic subjects including image recognitions, analyses and classifications have recently benefited from the Deep Learning (DL) techniques as in [8] [9][10] [11] [12][13] [14] [15] [16] [17] [18]. There are two types of methods that can be applied to the SL recognition: the first type is by using sensors and the second type is based on images [19].…”