System and method for rotation invariant fingerprint recognition

Machine readable and non-transitory medium having information recorded thereon for biometric authentication, wherein the information, when read by the machine, causes the machine to perform the following steps:

• generating rotation invariant (RI) training data with rotation invariant characteristics based on a plurality of training samples, each of which includes an image capturing biometric information of a person, a feature vector extracted from the image, and a label indicative of an identity of the person;
• conducting machine learning based on the RI training data to learn weights of each of rotation covariant (RC) convolution kernels for each of a plurality of convolution layers;
• receiving an input image with fingerprint information captured therein related to a person to be authenticated;
• preprocessing the input image to obtain an initial feature map;
• at each of the plurality of convolution layers, processing a feature map based on the RC convolution kernels for the layer to output an RC feature map, wherein the feature map is one of the initial feature map and an output RC feature map from a previous one of the plurality of convolution layers, and the RC feature map output by the last one of the plurality of convolution layers corresponds to a feature vector representing fingerprint features of the person in a rotation invariant manner;
• and
• authenticating the person based on the feature vector.

A system for biometric authentication, comprising:

• a multilevel rotation invariant (MRI) based model learning unit implemented using a processor and configured for:
• generating rotation invariant (RI) training data with rotation invariant characteristics based on a plurality of training samples, each of which includes an image capturing biometric information of a person, a feature vector extracted from the image, and a label indicative of an identity of the person, and
• conducting machine learning based on the RI training data to learn weights of each of rotation covariant (RC) convolution kernels for each of a plurality of convolution layers;
• an imaging unit implemented using a processor and configured for receiving an input image with fingerprint information captured therein related to a person to be authenticated;
• an image preprocessing unit implemented using a processor and configured for preprocessing the input image to obtain an initial feature map;
• an MRI feature extractor implemented using a processor and configured for processing, at each of the plurality of convolution layers, a feature map based on the RC convolution kernels for the layer to output an RC feature map, wherein the feature map is one of the initial feature map and an output RC feature map from a previous one of the plurality of convolution layers, and the RC feature map output by the last one of the plurality of convolution layers corresponds to a feature vector representing fingerprint features of the person in a rotation invariant manner;
• and
• an MRI recognition unit implemented using a processor and configured for authenticating the person based on the feature vector.