Curvedness of a line picture

作者:

Highlights:

摘要

The shape analysis of a binary picture is of great importance for pictorial pattern recognition. In this paper, we propose a useful geometric feature parameter called curvedness. Curvedness represents which lines are dominant in a binary picture, straight or curved. Our algorithm for measuring curvedness is based on the relationship between the distance to a boundary point on each black point along each quantized direction and the mean width of a binary picture. We investigate the fundamental property of curvedness. The experimental results for Japanese Hiragana and Kanji characters show the validity of curvedness.

论文关键词:Binary picture processing,Line picture,Shape analysis,Geometric feature,Feature extraction,Character recognition

论文评审过程:Received 17 October 1985, Revised 29 September 1986, Available online 19 May 2003.

论文官网地址:https://doi.org/10.1016/0031-3203(87)90002-1