Title :
Mathematical Formula Detection in Heterogeneous Document Images
Author :
Wei-Ta Chu ; Fan Liu
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Chung Cheng Univ., Chiayi, Taiwan
Abstract :
This paper presents mathematical formula detection in heterogeneous document images that may contain figures, tables, text, and math formulas. We adopt the method originally proposed for sign detection in natural images to detect non-homogeneous regions and accordingly achieve text line detection and segmentation. Novel features based on centroid fluctuation information of non-homogeneous regions are proposed to more appropriately characterize both displayed formulas and embedded formulas. By comparing the proposed method with previous works, we demonstrate the effectiveness of the proposed features.
Keywords :
document image processing; image segmentation; text detection; centroid fluctuation information; displayed formulas; embedded formulas; heterogeneous document images; mathematical formula detection; natural images; nonhomogeneous region detection; sign detection; text line detection; text segmentation; Feature extraction; Fluctuations; Image segmentation; Portable document format; Support vector machines; Training; Vectors; heterogeneous document images; mathematical formula detection; text line segmentation;
Conference_Titel :
Technologies and Applications of Artificial Intelligence (TAAI), 2013 Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4799-2528-5
DOI :
10.1109/TAAI.2013.38
