SIGNATURE VERIFICATION SYSTEM USING DEEP LEARNING

    In this project, we are going to design and develop a signature verification system to verify whether the new signature provided by the user is matched with the original signature in the database. For that, we are going to use a Machine Learning model to design the model to classify the signature.
A signature database which contains images of several person’s signatures is prepared that can be used to train and test the classifier model. Once the database is arranged, we apply pre-processing techniques for the cancellation of background noise, image enhancement, image masking, etc. Later we apply a feature extraction technique on the dataset to obtain an image vector containing the features of the signature images. We have a few feature extraction techniques for computer vision provided by OpenCV-Python libraries. We test with those techniques and find a suitable feature extraction technique to obtain better feature vectors. After the feature extraction, we prepare the data for training and testing. We’ll use the Support Vector Machine (SVM) classification algorithm to classify the new signature image with original images provided in the database and check whether it matches or not. This can be used to create a trained machine learning model to test and verify the signatures from the database. Once the training is completed and the trained model is generated, we can use that model offline to test the new images provided by the user and identify the signature with higher accuracy.

Request source code for academic purpose, fill REQUEST FORM or contact +91 7904568456 by WhatsApp or sales@verilogcourseteam.com, fee applicable.

SIMULATION VIDEO DEMO                              



PREVIOUS PAGE|NEXT PAGE