A Real-Time Biometric Encryption Scheme Based on Fuzzy Logic for IoT

Table 3

Comparison of the proposed method to some state-of-the-art methods using biometric encryption.

Reference	Key point	Accuracy
[30]	It extracted 57 geometric features from hand (lengths, areas, angles, and ratios) and used Euclidean distance for classification.	93%
[31]	It used morphological operations (e.g., thinning) in order to create the line edge map and implement the Hausdorff distance for classification. Research was performed on the own database.	95%
[32]	It implemented various features extractors (e.g., CompCode, OLOF, and RLOC) and various matching methods (e.g., SVM and kNN). Research was performed on 5 different mobile devices.	56% -81%
[33]	Lightweight verification schema based on fusion of the features presented in this work.	91%
[7]	Characteristic vectors have to be extracted from the gray scale image using filtering or transformation techniques such as oriented field flow curves (OFFC), Gabor filter, discrete wavelet transform (DWT), fast Fourier transform (FFT), discrete cosine transform (DCT), and principal component analysis (PCA).	90%
[21]	Wavelet feature extracted.	98.9%
This work	40 different features, including geometrical and unique features, are introduced for object detection (GLSM, GLCM, GLRL, GLHA, and FDIM).	99.1%