.png){kind=icon}
.png){kind=icon}
Return
An efficient gray-level thresholding algorithm for historic document images
.png){kind=icon}
PRE
AI
DOI：10.1016/j.culher.2007.09.004.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
For further processing of document images, the ink pixels must be separated from the background pixels. This paper presents a new method for thresholding images of historical documents. The main objective is to create monochromatic images with high quality at low processing time. This allows easier access to the contents of the image files. One important problem arises when the document is written on both sides of the paper. The thresholding process can lose the contents of the document completely if the separation between the ink and the background is not correctly defined. We present a new efficient algorithm for binarization of historical documents and we analyze its performance by comparing it to other nineteen classic thresholding algorithms using measures like precision, recall, accuracy, specificity and a fidelity index. Our method achieved better results than other well-known algorithms. (C) 2008 Elsevier Masson SAS. All rights reserved.
Keywords:
historical documents
Joaquim Nabuco file
image thresholding
automatic document processing
ROC curves
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.3
Papers:
3.0K
Citations:
7.0K