US 11,756,244 B1
System and method for handwriting generation
Ankan Kumar Bhunia, Abu Dhabi (AE); Salman Khan, Abu Dhabi (AE); Hisham Cholakkal, Abu Dhabi (AE); Rao Muhammad Anwer, Abu Dhabi (AE); and Fahad Khan, Abu Dhabi (AE)
Assigned to Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi (AE)
Filed by Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi (AE)
Filed on Jul. 19, 2022, as Appl. No. 17/868,140.
Claims priority of provisional application 63/324,847, filed on Mar. 29, 2022.
Int. Cl. G06F 3/048 (2013.01); G06T 11/20 (2006.01); G06F 3/04886 (2022.01); G06V 30/22 (2022.01)
CPC G06T 11/203 (2013.01) [G06F 3/04886 (2013.01); G06V 30/22 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A system for automated handwriting generation, comprising:
a text input device for inputting a text query having at least one textual word string;
an image input device for inputting a handwriting sample with characters in a writing style of a user;
a computer implemented deep learning transformer model including an encoder network and a decoder network in which each are a hybrid of a convolution network and a multi-head self-attention network having a plurality of attention heads,
wherein the encoder produces a sequence of style feature embeddings from the input handwriting sample,
wherein the decoder takes the sequence of style feature embeddings to convert the at least one textual word string into a generated handwritten image having substantially same writing style as the handwriting sample; and
an output device to output a generated handwriting image.