Handwritten Signature Verification System using machine Learning Approach- A Review of Literature
Pooja Gaikwad, Kashaf Pathan, Purva Prakash Patil, Laxmi Pagare, ranjana dahake · International journal of advance research and innovative ideas in education · 2021
ABSTRACT Abstract- This system proposes a feasible solution to verify handwritten signatures using various machine learning approaches. The scope has been scaling down to offline signatures which contains static inputs and outputs. Several classification methods such as Multinomial Naive Bayes Classifier (MNBC), Bernoulli Naive Bayes Classifier (BNBC), Logistic Regression Classifier (LRC), Stochastic Gradient Descent Classifier (SGDC), and Random Forest Classifier (RFC) were implemented to identify the most suitable classifier to verify handwritten signatures. The classifiers were pre-trained and tested using a handwritten signature database available for public use available on the Kaggle website. The best performance was obtained from RFC with and accuracy score of more than 0.6. For average, the framework made has been successful in verifying handwritten signature images provided with an extensive precision level.