Fourth International Conference Document Analysis and Recognition (ICDAR'97)
Segmentation of Stick Text Based on Sub Connected Area Analysis
Ulm, GERMANY
August 18-August 20
ISBN: 0-8186-7898-4
A new stick text segmentation method based on the sub connected area analysis is introduced in this paper. The foundation of this method is the sub connected area representation of text image that can represent all connected areas in an image efficiently. This method consists mainly four steps: sub connected area classification, finding initial boundary following point, finding optimal segmentation point by boundary tracing, text segmentation. This method is similar to boundary analysis method but is efficient than boundary analysis.
Index Terms:
stick text, text segmentation, sub connected area
Citation:
Gao Jingbo, Li Xinyou, Tang Zesheng, "Segmentation of Stick Text Based on Sub Connected Area Analysis," icdar, pp.417, Fourth International Conference Document Analysis and Recognition (ICDAR'97), 1997