Handwritten Arabic word/character recognition : common approaches
Offline handwriting word recognition is the automatic transcription by computer, where only the image of the handwriting is available. The recognition operation includes many steps, the segmentation step and the recognition step of offline handwritten Arabic words are suggested to be implemented usi...
| Main Authors: | , , |
|---|---|
| Format: | Book Chapter |
| Language: | English |
| Published: |
IIUM Press
2011
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/21662/ http://irep.iium.edu.my/21662/ http://irep.iium.edu.my/21662/1/Chapter_29.pdf |
| Summary: | Offline handwriting word recognition is the automatic transcription by computer, where only the image of the handwriting is available. The recognition operation includes many steps, the segmentation step and the recognition step of offline handwritten Arabic words are suggested to be implemented using different techniques, since off-line Arabic character recognition operations involves many inter-related steps that can't be separated from each other, as a simple genes of operations, the two steps has to be discussed together. What makes Arabic
handwriting words recognition so challenging is that unlike Latin, Arabic is written right to left and is always cursive. Letters are joined together along the writing line to form words or sub-words. The Arabic Alphabet has 28 letters, each with two to four shapes. The shape of a
letter is determined by its position within the word: Initial, medial, or final, if we included character recognition as well as the word recognition, there would be another shape for each character, which is the isolated character. The researchers in this field have proposed many
techniques to solve the problems; such as cursiveness of the Arabic handwritten words, in this paper a review of the used techniques, followed by a comparison to show the pros and cons of each technique are conducted |
|---|