Title
Algorithms To Generate Partiall Damaged Characters And Readability Study For Ocr Readers In Semiconductor Manufacturing
Keywords
Character recognition; Damaged; Neural network; Readability
Abstract
Ever since the character strings on silicon wafers were read using OCR (Optical Character Recognition) cameras, there has been a problem with damaged characters. This problem is due to reflection from the light source or physical damage of the characters themselves. There are obvious types of damage that occur frequently on many of the bitmaps that the OCR camera reads. With these types, one can test them to find the most damaging types for each particular character. However, currently there is no known research that systematically determines the worst damages or limits of damage to characters for specific OCR methods such as template matching or neural network algorithms. This article presents algorithms for testing common forms of damages on template-matching optical readers reading strings on silicon wafers. It also displays results from combining a simple neural network and the algorithms. The results on readability are critical for the development of robust OCR systems.
Publication Date
10-6-2004
Publication Title
International Journal of Computers and Applications
Volume
26
Issue
4
Number of Pages
223-228
Document Type
Article
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
4644346358 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/4644346358
STARS Citation
Desrochers, Dave; Jin, Yufang; Qu, Zhihua; and Saengdeejing, Apiwat, "Algorithms To Generate Partiall Damaged Characters And Readability Study For Ocr Readers In Semiconductor Manufacturing" (2004). Scopus Export 2000s. 4688.
https://stars.library.ucf.edu/scopus2000/4688