The problem of optical pattern recognition is a broad one. It ranges from identifying shapes in aerial photographs to recognizing letters in hand or machine printed words. This thesis examines many of the issues relating to pattern recognition and, specifically, those pertaining to the optical recognition of characters. It discusses several approaches to various parts of the problem as an illustration of the variety of methods of attack. Some of the particular strengths and weaknesses of those approaches are discussed as well. Finally, a new method of approaching OCR is introduced, developed, and studied. At the conclusion, the study is summarized, the results are examined, and suggestions are made for continued research. / Department of Computer Science

Thesis (M.S.)--University of Nevada, Reno, 2006. / "May, 2006." Includes bibliographical references (leaves 94-99). Online version available on the World Wide Web.

Thesis (M.S.)--Rochester Institute of Technology, 1989. / "References": leaves 50-51.

Thesis (M.S.)--Rochester Institute of Technology, 1992. / Typescript. Includes bibliographical references.

Thesis (M.S.)--Ohio University, June, 1992. / Title from PDF t.p.

Thesis (Ph.D.)--Rochester Institute of Technology, 2008. / Typescript. Includes bibliographical references (p. 175-179) and index.

Thesis (Ph. D.)--University of Hong Kong, 2005.

Thesis (M.Comp. Sc.)--Dept. of Computer Science, Concordia University, 1995. / Includes bibliographical references (leaves 119-128) and index. Available also on the Internet.

Thesis (Ph. D.)--University of Missouri-Columbia, 2000. / Typescript. Vita. Includes bibliographical references (leaves 96-109). Also available on the Internet.

This study investigated if it was feasible to use machine learning tools on OCR extracted text data to classify receipts and extract specific data points. Two OCR tools were evaluated, the first was Azure Computer Vision API and the second was Google Drive REST Api, where Google Drive REST Api was the main OCR tool used in the project because of its impressive performance. The classification task mainly tried to predict which of five given categories the receipts belongs to, and also a more challenging task of predicting specific subcategories inside those five larger categories. The data points we where trying to extract was the date of purchase on the receipt and the total price of the transaction. The classification was mainly done with the help of scikit-learn, while the extraction of data points was achieved by a simple custom made N-gram model. The results were promising with about 94 % cross validation score for classifying receipts based on category with the help of a LinearSVC classifier. Our custom model was successful in 72 % of cases for the price data point while the results for extracting the date was less successful with an accuracy of 50 %, which we still consider very promising given the simplistic nature of the custom model.