Fingerprint identification represents one of the most popular methods of
verification for accessing many systems. Capturing images is pretty complex
problem, as it depends on many different factors that highly impact the
functionality of the sensor. In this thesis, we have researched this field from
the perspective of AI. Used methods will be implemented as safety system
as they prevent bad captures – they will analyse the image and give some
quality grade of the image to the final user. Used dataset, obtained from the
field experts, is used as the input for the model. Output is a binary value,
that values an image as a “good” or “bad”.
|
