الفهرس 
Applications of Pattern RecognitionOnly 14 pages are availabe for public view
 |  | from | 16 |  |  |
| | | from | 16 | | |
Abstract
Optical character Recognition (OCR) has attracted many researches because it contributes to the advancement of the automation process and it improves the interaction between man and machine in many applications. A lot of work has been done on English OCR, but Arabic OCR is still under development because Arabic text has some special characteristics that makes Arabic OCR continues to be a difficult task.
Commercial systems for Arabic Optical character Recognition (AOCR) are becoming more available. characterizing the performance of OCR systems is important for predicting OCR performance and providing explanations for system behavior and identifying open problems.
The first contribution of thesis is to use metrics that are useful for characterize the performance accuracy of AOCR systems. These metrics consists of word-based and character-based metrics.
The second contribution is to design and to implement evaluation tool with GUI to help users to evaluate the systems and to compare between the performances of most available Arabic OCR systems.
Another contribution is studying noise affected on Arabic OCR evaluation on image by using different percentage of salt and pepper noise.
The thesis contains six chapters in addition to references. Contents of the thesis are organized as follows:
Chapter (1) presents a brief introduction of the research study which includes the objectives, the problem description and the methodology of study that has been used to solve this problem.