- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
Classification of Binary Document Images Using Probabilistic Neural Network Model | ||
| Tikrit Journal of Pure Science | ||
| Article 1, Volume 17, Issue 4, 2012, Pages 209-218 | ||
| Author | ||
| Eman H. Abdurrahman | ||
| Abstract | ||
| In this work, a proposed system is used to segment and classify the gray document image to two regions texture and non-textual based on data blocks. A probabilistic neural network model has been used for this purpose . First the preprocessing is used to convert gray document image to binary document image, then the erode process used to convert the binary document into blocks. The resulting blocks are segmented to number of regions by using label procedure, the four features of each region are calculated based on the bounding box for each region, Then these features are fed to the input layer of a probabilistic neural network for classification to one of two regions are text, non-textual. Some gray documents images are used in order to test the proposed system. Finally three experiments are applied and the algorithm classified them correctly | ||
| Keywords | ||
| Binary image classification; probabilistic neural network | ||
|
Statistics Article View: 103 PDF Download: 2 |
||