Git Product home page Git Product logo

biometric-fingerprint-classification's Introduction

Biometric-Fingerprint-Classification

Built fingerprint classifier by developing a own RBF kernel based support vector machine. Developed SVM in order to make a multi-class prediction model and obtained accuracy of 90% in Python. ACCURACY The accuracy score on the testA evaluation is 80.95%

This is a multi class classifier of the RBF kernel. In order to train the dataset which has 21 classes we used one vs all strategy. In this strategy we take one class as positive and the remaining classes as negatives and do the classification and it should be done with all the 21 classes thus we train the dataset with support vector machine. We used inbuilt functions for the classification of the dataset and training.

METHODS FOR IMPROVEMENT

There are different parameters for which the accuracy will be increased.

  1. It depends on the feature size of the fingerprints that can be reduced by trimming the blank parts of the fingerprints, if the feature size is big it slows down the training and predicting process that decreases accuracy. The accuracy depends on how many rows and columns we trim for the fingerprints to remove blank parts around them
  2. It also depends on the darkness variance i.e normalization.
  3. Other parameters in the svm function like the penalty parameter(C), gamma(kernel coefficient for rbf), tolerance for stopping criterion value will change the accuracy.

CHALLENGES

The main challenges we faced were

  1. Preprocessing of the fingerprints where we have to trim the columns and rows to remove blank parts and also darkness variance and creating the matrix for the fingerprints
  2. We tried to implement our own multi-class classifier using one vs all strategy but we couldn’t do is as we find it difficult to do it for all the classes given so we later came up with in built functions.
  3. For the checker algorithm we tried to do it with single image as a test set and do the prediction. These are some of the challenges we faced while development of this project

biometric-fingerprint-classification's People

Contributors

ananyaveeresh1726 avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.