The line segment table: a fast region description algorithm

Abstract

In this paper a new fast region description method named line segment table is proposed. Each element in the table represents a horizontal line, which includes the coordinates of a line segment, the relationship between upper and lower lines, and the characteristics of a line. Thus a segment table can be used to describe the shape of a region precisely. This paper shows that these regional operations can be decomposed into a set of union operations of the corresponding components of all horizontal lines. Thus the resource intensive regional operations can be turned into combinations or truncations of the line segments. This paper also presents a set of line processing operations, which can be applied in binary image processing such as erosion, dilation, convolution and correlations. Line segment encoding is particularly applicable to line-based processing. Furthermore it is also useful for applications such as seed filling. This paper proposes a fast bucket sorting algorithm which is faster than traditional contour tracing algorithms and seed filling algorithms. This algorithm simplifies regional processing and improves processing efficiency, and is particularly advantageous in the application of industrial real-time detection and hardware design.