Handwritten Signature Veriﬁcation using OpenCV, Python
Handwritten Signature veriﬁcation is an important personal identiﬁcation. It is widely used in authorizing a cheque or legal documents. Signature veriﬁcation is either online (dynamic) or ofﬂine (static). A machine learning, Haar Cascade Classiﬁer (HCC) approach was introduced by Viola and Jones to achieve rapid object detection based on a boosted cascade of Haar-like features. Here, for the ﬁrst time the HCC approach was applied for the handwritten signature recognition and veriﬁcation. Two datasets were used, UTSig dataset for Persian writers which written from right to left and includes 8,280 images from 115 writers. GPDS synthetic Signature database for English writers which written from left to right. It contains data from 4,000 synthetic individuals. A classiﬁer was created for each one of the writers’ signatures after applying the preprocessing phase. Each classiﬁer was trained and tested using enormous number of signatures generated from applying artiﬁcial noises on the signature images.
There are no reviews yet.