Title :
A revised feature extraction method for detecting text page up/down orientation
Author :
Guo, Jun ; Liu, Xiaoping ; Chen, YouGuang ; Wang, Xingheng
Author_Institution :
Comput. Center, East China Normal Univ., Shanghai, China
Abstract :
Based on our previous work, a revised method is proposed for text page up/down orientation detection in this paper. All characters in an scanned image which is from a text page, are isolated by using edge detection algorithm. The feature of each character is extracted through three vertical component runs (VCRs). And the image will be vectorized to a 96-dimensional vector. These samples are trained by using support vector machine (SVM), and a classifier is generated. Experimental results show our proposed method is very effective and its accuracy is considerably higher than some former methods.
Keywords :
character recognition; edge detection; feature extraction; support vector machines; text detection; edge detection; feature extraction; support vector machine; text page up/down orientation detection; vertical component runs; Support vector machines; feature extraction; orientation detection; support vector machine; vertical component run;
Conference_Titel :
Applied Superconductivity and Electromagnetic Devices (ASEMD), 2011 International Conference on
Conference_Location :
Sydney, NSW
Print_ISBN :
978-1-4244-7852-1
DOI :
10.1109/ASEMD.2011.6145079
