2024-03-29T14:47:04Z
https://meral.edu.mm/oai
oai:meral.edu.mm:recid/3530
2021-12-13T08:07:45Z
1582963302567:1597824273898
user-ucsy
Image Enhancement Processes for Myanmar Printed Text Recognition
Win, Htwe Pa Pa
Tun, Khin Nwe Ni
Image enhancement processing step is the basiccrucial part of the OCR system as the recognitionaccuracy of OCR systems greatly depends on thequality of the input text image. Most of the OCRsystems, especially Myanmar OCR systems are littleeffort for preprocessing or image enhancementprocess. And Myanmar glyphs are complex in shape;combine with many circular, dots and line and pixeldistribution to form this scripts are not uniform.Therefore, making the input image to be better isimportant for our native OCR system. In this paperwe propose image enhancement processes suit that,through reducing noise, separating text andbackground, skew detection and rotation, improvesthe accuracy of the OCR System for Myanmarprinted text. These steps can produce a refined imagethat is ready for the segmentation or characterextraction process of the OCR system.
2010-12-16
http://hdl.handle.net/20.500.12678/0000003530
https://meral.edu.mm/records/3530