Abstract: A text-recognition system and method include a trained classifier configured to identify a font of a frame of text line image. The system also includes an adaptive sliding window configured to divide the frame into a plurality of cells. A first cell is located around a prominent writing line of the text line image. Additional cells are located above the prominent writing line and below the prominent writing line, such that each of the additional cells above the prominent writing line has a same percentage of ink-pixels and each of the additional cells below the prominent writing line has a same percentage of ink-pixels. The system also includes a font-specific feature parameters database configured for extraction of text features from each of the cells. The system also includes one or more trained font-specific recognizers configured to recognize the extracted text features using an associated font-specific recognizer for the identified font.

Abstract: The automatic Arabic text image optical character recognition method includes training a text recognition system using Arabic printed text, using the produced models for classification of newly unseen Arabic scanned text, and generating the corresponding textual information. Scanned images of Arabic text and copies of minimal Arabic text are used in the training sessions. Each page is segmented into lines. Features of each line are extracted and input to Hidden Markov Model (HMM). All training data training features are used. HMM runs training algorithms to produce codebook and language models. In the classification stage new Arabic text is input in scanned form. Line segmentation where lines are extracted is passed through. In the feature stage, line features are extracted and input to the classification stage. In the classification stage the corresponding Arabic text is generated.

Abstract: The automatic Arabic text image optical character recognition method includes training a text recognition system using Arabic printed text, using the produced models for classification of newly unseen Arabic scanned text, and generating the corresponding textual information. Scanned images of Arabic text and copies of minimal Arabic text are used in the training sessions. Each page is segmented into lines. Features of each line are extracted and input to Hidden Markov Model (HMM). All training data training features are used. HMM runs training algorithms to produce codebook and language models. In the classification stage new Arabic text is input in scanned form. Line segmentation where lines are extracted is passed through. In the feature stage, line features are extracted and input to the classification stage. In the classification stage the corresponding Arabic text is generated.