PA3Description

PA3Description - CS228 Programming Assignment#3 1 Stanford...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: CS228 Programming Assignment #3 1 Stanford CS 228, Winter 2011-2012 Programming Assignment #3: Markov Networks for OCR This assignment is due at 12 noon on January 30 . 1 Overview 1.1 Introduction In the last assignment, you used Bayesian networks to model real-world genetic inheritance networks. Your rival claims that this application to genetic inheritance underscores the lim- ited applicability of graphical models, because one doesn't often nd problems with network structures that clear. To prove him wrong, you decide to apply the graphical model framework to the task of optical character recognition (OCR), a problem that is considerably messier than that of genetic inheritance. Your goal is to accept as input an image of text and output the text content itself. The real-world applications of OCR are endless. Some examples include: 1. The Google Books project has scanned millions of printed books from libraries around the country. Using OCR, these book scans can be converted to text les, making them available for searching and downloading as eBooks. 2. There has long been research on OCR applied to handwritten documents. This research has been so successful that the US Postal Service can use OCR to pre-sort mail (based on the handwritten address on each envelope), and many ATMs now automatically read the checks you deposit so the funds are available sooner without the need for human intervention. 3. Research on OCR for real-world photos has made it possible for visually impaired indi- viduals to read the text of street and building signs with the assistance of only a small camera. The camera captures an image of the sign, runs OCR on that image, and then uses text-to-speech synthesis to read the contents of the sign. In this assignment, we will give you sets of images corresponding to handwritten characters in a word. Your task is to build a graphical model to recognize the character in each image as accurately as possible. This assignment is based on an assignment developed by Professor Andrew McCallum, Sameer Singh, and Michael Wick, from the University of Massachussetts, Amherst. The full OCR system will be split across two assignments. In this one, you will construct a Markov network with a variety of di erent factors to gain familiarity with undirected graphical models and conditional random elds (CRFs) in particular. We provide code that will perform inference in the network you construct, so you can nd the best character assignment for every image and evaluate the performance of the network. In Programming Assignment 7, you will extend the network to incorporate more features, use an inference engine that you built yourself, and learn the optimal factor weights from data. CS228 Programming Assignment #3 2 1.2 Markov Networks for OCR Suppose you are given n total character images (corresponding to a single word of length n )....
View Full Document

{[ snackBarMessage ]}

Page1 / 8

PA3Description - CS228 Programming Assignment#3 1 Stanford...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online