Tn. Tan, ROTATION-INVARIANT TEXTURE FEATURES AND THEIR USE IN AUTOMATIC SCRIPTIDENTIFICATION, IEEE transactions on pattern analysis and machine intelligence, 20(7), 1998, pp. 751-756
This paper concerns the extraction of rotation invariant texture featu
res and the use of such features in script identification from documen
t images. Rotation invariant texture features are computed based on an
extension of the popular multi-channel Gabor filtering technique, and
their effectiveness is tested with 300 randomly rotated samples of 15
Brodatz textures. These features are then used in an attempt to solve
a practical but hitherto mostly overlooked problem in document image
processing-the identification of the script of a machine printed docum
ent. Automatic script and language recognition is an essential front-e
nd process for the efficient and correct use of OCR and language trans
lation products in a multilingual environment. Six languages (Chinese,
English, Greek, Russian, Persian, and Malayalam) are chosen to demons
trate the potential of such a texture-based approach in script identif
ication.