Award Date

1-1-2004

Degree Type

Thesis

Degree Name

Master of Science (MS)

Department

Electrical and Computer Engineering

First Committee Member

Evangelos A. Yfantis

Number of Pages

37

Abstract

Handwriting Recognition is the task of transforming a language that is represented in its spatial form of graphical marks into its symbolic representation. In Offline Handwriting Recognition, there are three steps: preprocessing of the image, segmentation of words into characters and recognition of the characters. In this thesis I implemented two methods for character recognition, which is the most important step in Offline Handwriting Recognition. The heart of character recognition is the features that are extracted from the character image. The accuracy of the classification of the character image depends on the quality of the features extracted from the image. The two methods presented in this thesis use two different types of features. One uses the connectivity features among various segments in a character image, and the other method uses the gradient feature at each pixel to construct the feature vectors. Both these methods are discussed in detail in the following chapters.

Keywords

Based; Characters; Extraction; Feature; Gradient; Handwritten; Recognition

Controlled Subject

Computer science

File Format

pdf

File Size

839.68 KB

Degree Grantor

University of Nevada, Las Vegas

Language

English

Permissions

If you are the rightful copyright holder of this dissertation or thesis and wish to have the full text removed from Digital Scholarship@UNLV, please submit a request to digitalscholarship@unlv.edu and include clear identification of the work, preferably with URL.

Identifier

https://doi.org/10.25669/7i7n-6u68


Share

COinS