Farsi Font Detection using the Adaptive RKEM-SURF Algorithm

Farsi font detection is considered as the first stage in the Farsi optical character recognition (FOCR) of scanned printedtexts. To this aim, this paper proposes an improved version of the speeded-up robust features (SURF) algorithm, as thefeature detector in the font recognition process. The SURF algorithm suffers from creation of several redundant featuresduring the detection phase. Thus, the presented version employs the redundant keypoint elimination method (RKEM) toenhance the matching performance of the SURF by reducing unnecessary keypoints. Although the performance of theRKEM is acceptable in this task, it exploits a fixed experimental threshold value which has a detrimental impact on theresults. In this paper, an Adaptive RKEM is proposed for the SURF algorithm which considers image type and distortion,when adjusting the threshold value. Then, this improved version is applied to recognize Farsi fonts in texts. To do this, theproposed Adaptive RKEM-SURF detects the keypoints and then SURF is used as the descriptor for the features. Finally,the matching process is done using the nearest neighbor distance ratio. The proposed approach is compared with recentlypublished algorithms for FOCR to confirm its superiority. This method has the capability to be generalized to otherlanguages such as Arabic and English.

Keywords:

Adaptivity , Feature Extraction , Font Detection , Redundant Keypoint Elimination Method (RKEM) , Speeded-Up Robust Features (SURF)