Identifying the Origin of Finger Vein Samples Using Texture Descriptors

Identifying the origin of a sample image in biometric systems can be beneficial for data authentication case attacks against system and initiating sensor-specific processing pipelines sensor-heterogeneous environments. Motivated by shortcomings photo response non-uniformity (PRNU) based method context, we employ eight texture classification approaches, including frequency-, spatial-, wavelet-based methods to detect finger vein samples images’ origin. Besides, We use publicly available datasets applying all novel classical descriptors SVM suggested pipeline. A approach termed WMV demonstrated an excellent result raw more challenging region interest among mentioned employed identify sensor model. The observed results establish as effective competitors PRNU model identification.