Project Domain: Image processing and Machine learning

Project Title: Digit Recognition

DESCRIPTION:

Digit recognition is one of the active research topics in digital image processing. It is a classic machine learning problem. The goal of this project is to take an image of handwritten digits and determine what those digits are. The principal task in digit recognition is to extract HOG features from the database of handwritten digits and to build a classifier on it. Then we predict the digits of the database using this classifier. To build the classifier we write python scripts.

EXISTING SYSTEM:

The current systems use resource intensive image processing methods and algorithms with varying accuracies and rejections.

PROPOSED SYSTEM:

The proposed system uses efficient pattern classification and machine learning approach to improve overall performance of predicting the digits.

FUTURE EXPANSION:

This digit recognition can be further scaled to achieve big data processing levels.

Hardware and software requirements:

Hardware Requirements:

  • RAM : 1 GB and above
  • OS : Linux, Windows

Software Requirements:

  • Python 2.7