Cohen's class distributions for skew angle estimation in noisy ancient Arabic documents

This paper presents an adaptive method for the skew angle estimation of noisy handwritten Arabic documents using the energy distributions of Cohen’s class. The presence of noise in raw document images can create local maxima which disturb the projection histogram analysis. To avoid this drawback, we propose to use Cohen’s class distributions on the projection histogram profiles obtained using different projection angles. These distributions reduce the importance of these local maxima and are fitted to the nonstationary nature of these histogram profiles. The orientation of the document is given by the highest maximum. The proposed skew angle detection technique has been evaluated on 864 skewed documents. The results of each distribution are presented at the end of this paper.

• Type: Journal
• Year: 2009
• Where: AND
• Authors: Nazih Ouwayed, Abdel Belaïd, François Auger
• Keywords: AND 2009, Local Maxima, Machine Learning, Projection Histogram, Skew Angle