OFFLINE SIGNATURE VERIFICATION

In the era of growing technology, security is the major concern to avoid fake and forgeries. It is also one of the most easily forgeable biometric identity when compared to other biometric features like thumb impression, face recognition etc. Now a day's Signature verification is one of the most important features for checking the authenticity of a person. The classification of the feature utilizes statistical features. Our proposed model has three stages: image pre-processing, feature extraction and classification and verification. Scanned signatures are introduced into the computer, our proposed method modifies their quality by image enhancement and noise reduction, to be followed by feature extraction in which we extract threshold, mean of bounding box, perimeter, total pixel count, ratio of height and width, area out of which threshold is efficient and combination of those properties leads in better results and finally used Euclidean distance model for classification of signature either genuine or forgery.