Title :
Improved document skew detection based on text line connected-component clustering
Author :
Liolios, N. ; Fakotakis, N. ; Kokkinakis, G.
Author_Institution :
Electr. & Comput. Eng. Dept., Patras Univ., Greece
fDate :
6/23/1905 12:00:00 AM
Abstract :
The classical method of document skew detection, based on nearest-neighbor clustering, is revisited. A heuristic is proposed which attempts to group all the connected components that belong to the same line of text, into one cluster. The larger clusters are known to result in better skew angle estimation. The skew detection accuracy of this improved connected-components method is several orders of magnitude better, when compared to the classical approach, with no change in the order of complexity
Keywords :
computational complexity; document image processing; optical character recognition; parameter estimation; pattern clustering; connected-component clustering; document skew detection; nearest-neighbor clustering; optical character recognition; skew angle estimation; text line; Character recognition; Clustering algorithms; Clustering methods; Computational efficiency; Data mining; Histograms; Laboratories; Nearest neighbor searches; Optical character recognition software; Wire;
Conference_Titel :
Image Processing, 2001. Proceedings. 2001 International Conference on
Conference_Location :
Thessaloniki
Print_ISBN :
0-7803-6725-1
DOI :
10.1109/ICIP.2001.959241
