|
|
Real-time Recognition of Typed Letters
Hámorník, Juraj ; Toropila, Daniel (advisor) ; Jančík, Pavel (referee)
Tablet PC devices are becoming more and more popular these days. These devices rarely have a hardware keyboard. Users input a text in two major ways. First one is a virtual keyboard, where users type each character individually and second one is handwrite recognition, where users write the whole words. Our method combines chars input method and handwriting. Hand written character that can contain multiple strokes, is converted into sequences of numbers. Based on this sequence we evaluate a written character. When we compare the default input method on operating system Windows 8 we can figure, that for advanced users, and for some languages our method could be a challange.
|
|
|
Signature-based User Authentication
Hámorník, Juraj ; Jančík, Pavel (advisor) ; Moško, Juraj (referee)
This work aims on missing handwritten signature authentication in Windows. Result of this work is standalone software that allow users to log into Windows by writing signature. We focus on security of signature authentification and best overall user experience. We implemented signature authentification service that accept signature and return user access token if signature is genuine. Signature authentification is done by comparing given signature to signature patterns by their similarity. Signatures similarity is calculated by dynamic time warp on dynamic signature features such as speed, acceleration and pressure. User access token is used by our Windows login plugin called signature credential provider to decrypt user credentials and perform log in. Result of this work is solution that allow user log to windows by handwritten signatures, with equal error rate of 4.17\%.
|
|
|
Signature-based User Authentication
Hámorník, Juraj ; Jančík, Pavel (advisor) ; Moško, Juraj (referee)
This work aims on missing handwritten signature authentication in Windows. Result of this work is standalone software that allow users to log into Windows by writing signature. We focus on security of signature authentification and best overall user experience. We implemented signature authentification service that accept signature and return user access token if signature is genuine. Signature authentification is done by comparing given signature to signature patterns by their similarity. Signatures similarity is calculated by dynamic time warp on dynamic signature features such as speed, acceleration and pressure. User access token is used by our Windows login plugin called signature credential provider to decrypt user credentials and perform log in. Result of this work is solution that allow user log to windows by handwritten signatures, with equal error rate of 4.17\%.
|
|
|
Real-time Recognition of Typed Letters
Hámorník, Juraj ; Toropila, Daniel (advisor) ; Jančík, Pavel (referee)
Tablet PC devices are becoming more and more popular these days. These devices rarely have a hardware keyboard. Users input a text in two major ways. First one is a virtual keyboard, where users type each character individually and second one is handwrite recognition, where users write the whole words. Our method combines chars input method and handwriting. Hand written character that can contain multiple strokes, is converted into sequences of numbers. Based on this sequence we evaluate a written character. When we compare the default input method on operating system Windows 8 we can figure, that for advanced users, and for some languages our method could be a challange.
|
guest ::
