Authentication Process
As mentioned, this system can provide two kinds of operating modes. Real time identity recognition and fake signature distinguishing.
Real time identity recognition is for identifying which user is writing. This requires that test user must belong to one of the users in the training classes. The output of the prediction is the name of user that is writing. In the next section, we will demonstrate its detailed process.
Fake signature distinguishing is supposed to distinguish whether the signature is real. The output is True or False. The main difference is that test user needn’t belong to the users in training dataset. To achieve this function, the training set contains the real signature of the user and a group of fake signatures corresponded.
As mentioned, this system can provide two kinds of operating modes. Real time identity recognition and fake signature distinguishing.
Real time identity recognition is for identifying which user is writing. This requires that test user must belong to one of the users in the training classes. The output of the prediction is the name of user that is writing. In the next section, we will demonstrate its detailed process.
Fake signature distinguishing is supposed to distinguish whether the signature is real. The output is True or False. The main difference is that test user needn’t belong to the users in training dataset. To achieve this function, the training set contains the real signature of the user and a group of fake signatures corresponded.
Android app
As MetawearC transmit data by Bluetooth, We design an Android App utilizing the API from Metawear SDK. The UI design is trivial with two buttons: start collecting and stop collecting. After the MetawearC is connected with the phone by Bluetooth, when clicking start button, the MetawearC starts collecting acceleration and angular velocity and save them into RAM. When clicking stop button, MetawearC stops collecting data and POST the data into server. The length of data will be displayed by Toasts. After receiving the response from the server, the App will display the result of prediction, namely, the name of the user in real time identity recognition mode or true/flase in fake signature distinguishing mode. |