A Novel Bank Check Signature Verification Model using Concentric Circle Masking Features and its Performance Analysis over Various Neural Network Training Functions

Neural Network Based Signature Verification Model for Bank Cheques with Three Specimen Signatures

“…Ashok Kumar and Dhandapani [16] used connected components labeling technique to find the number of connected components and extracting properties of each blob and found that when using fractal dimensions as one of the feature, the accuracy rate increased. They used neural networks for training the feature set and the same authors [17] …”