Digit Recognition Using Machine Learning Matheus Lelis University

  • Slides: 6
Download presentation
Digit Recognition Using Machine Learning Matheus Lelis University of Massachusetts: Dartmouth

Digit Recognition Using Machine Learning Matheus Lelis University of Massachusetts: Dartmouth

Abstract � The goal of this research project is to use an artificial neural

Abstract � The goal of this research project is to use an artificial neural network machine learning algorithms with back propagation to develop a program which will recognize handwritten letters and numbers.

Background Artificial Neural Network � An artificial neural network learning algorithm is a learning

Background Artificial Neural Network � An artificial neural network learning algorithm is a learning algorithm that is inspired by the structure and functional aspects of biological neural networks. � Computations are structured in terms of an interconnected group of artificial neurons, processing information using a connectionist approach to computation.

Problem Character Recognition � Reading in the images of handwritten numbers and letters and

Problem Character Recognition � Reading in the images of handwritten numbers and letters and outputting the machine-encoded version. � Adding distortion to try to solve CAPTCHAs.

Progress The machine was written using MATLAB works in two steps. 1 st step

Progress The machine was written using MATLAB works in two steps. 1 st step – runs through a set of data and learns and sets weight 2 nd step – runs through new data and tries to guess. It takes in a matrix of data with images 20 px by 20 px

Issues � Finding/Creating new data to test the machine with. � Teaching the machine

Issues � Finding/Creating new data to test the machine with. � Teaching the machine to work with letters, only works with numbers for now. � Adding the distortion and test out the CAPTCHAs.