Graduate Thesis Or Dissertation

 

Recognition of printed Chinese characters Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/b5644w06k

Descriptions

Attribute NameValues
Creator
Abstract
  • This method of character recognition is according to the topological features of a.given character. First store the image of a Chinese character into the storage of the computer. Each image of the character appears as a 20 x 20 binary matrix. Each small square in the matrix is designated as one if the reflected light is more than 50% of that of a blank point, otherwise it is zero. The encoding method is as follows: (A) Preprocessor: This process includes three operations. These are Cleaning, Thinning and Connecting. (B) Preliminary Classification: First of all count all the " 1 " points in each column of the binary matrix from left to right. This list of digits is named as the Original Digit Code (ODC). From the ODC curve, by recording the extreme points, we get a Modified Digit Code (MDC). (C) Fundamental Classification: Choosing the longest line in each column of a binary matrix from left to right form the Longest Line Code (LLC), Plot the LLC against column number, to get the LLC curve. From the LLC curve, pick up the maximum points as the Largest Digit Code (LDC) and also record the number of digits between the two largest digits in LLC as the Distance Code (DC). In order to search easily for the English translation of a given character, the assigning of the order number to each digit in LDC is more important than the LDC itself. We call these digits as the Digit Order of LDC (DOL). According to the MDC, DC and DOL, the given character can be easily recognized by the computer.
Resource Type
Date Available
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Academic Affiliation
Non-Academic Affiliation
Subject
Rights Statement
Publisher
Peer Reviewed
Language
Digitization Specifications
  • File scanned at 300 ppi (Monochrome) using Capture Perfect 3.0.82 on a Canon DR-9080C in PDF format. CVista PdfCompressor 4.0 was used for pdf compression and textual OCR.
Replaces
Additional Information
  • description.provenance : Approved for entry into archive by Patricia Black(patricia.black@oregonstate.edu) on 2014-01-29T20:38:21Z (GMT) No. of bitstreams: 1 LokPat1971.pdf: 613203 bytes, checksum: c7bf742c3d48a1221e72bacf5875a7a8 (MD5)
  • description.provenance : Approved for entry into archive by Patricia Black(patricia.black@oregonstate.edu) on 2014-01-29T14:02:03Z (GMT) No. of bitstreams: 1 LokPat1971.pdf: 613203 bytes, checksum: c7bf742c3d48a1221e72bacf5875a7a8 (MD5)
  • description.provenance : Submitted by Georgeann Booth (gbscannerosu@gmail.com) on 2014-01-29T01:09:54Z No. of bitstreams: 1 LokPat1971.pdf: 613203 bytes, checksum: c7bf742c3d48a1221e72bacf5875a7a8 (MD5)
  • description.provenance : Made available in DSpace on 2014-01-29T20:38:21Z (GMT). No. of bitstreams: 1 LokPat1971.pdf: 613203 bytes, checksum: c7bf742c3d48a1221e72bacf5875a7a8 (MD5) Previous issue date: 1971-05-07

Relationships

Parents:

This work has no parents.

In Collection:

Items