Apparatus, method and computer program product for biometric recognition

An apparatus, comprising:

• at least one processor;
• and
• at least one memory including computer program code, the memory and the computer program code configured to, working with the at least one processor, cause the apparatus to;
• obtain first electrocardiogram data, wherein the first electrocardiogram data is captured in a rest or relax condition or a motion or stress condition;
• determine, by a discriminative network of generative adversarial networks, whether the first electrocardiogram data is captured in the rest or relax condition or the motion or stress condition;
• generate, in response to a determination that the first electrocardiogram data is captured in the motion or stress condition, second electrocardiogram data by inputting the first electrocardiogram data to a generative network of the generative adversarial networks;
• obtain a matching result by inputting tithe first electrocardiogram data, in response to a determination that the first electrocardiogram data is captured in the rest or relax condition, or iii) the second electrocardiogram data, in response to a determination that the first electrocardiogram data is captured in the motion or stress condition, to a matching network;
• and
• determine a recognition result based on the matching result.

A non-transitory computer readable medium having encoded thereon statements and instructions to cause a processor to:

• obtain first electrocardiogram data, wherein the first electrocardiogram data is captured in a rest or relax condition or a motion or stress condition;
• determine, by a discriminative network of generative adversarial networks, whether the first electrocardiogram data is captured in the rest or relax condition or the motion or stress condition;
• generate, in response to a determination that the first electrocardiogram data is captured in the motion or stress condition, second electrocardiogram data by inputting the first electrocardiogram data to a generative network of the generative adversarial networks;
• obtain a matching result by inputting (i) the first electrocardiogram data, in response to a determination that the first electrocardiogram data is captured in the rest or relax condition, or (ii) the second electrocardiogram data, in response to a determination that the first electrocardiogram data is captured in the motion or stress condition, to a matching network;
• and
• determine a recognition result based on the matching result.