Boundary-based object segmentation in X-ray imaging using spiral search

Abstract

In this paper, we propose a boundary-based method for object segmentation by using only the edge information. The proposed method is especially applied to object segmentation of dangerous firearms and knives in the X-ray images of baggage, where no colour or texture features are available to describe the target object. The Canny edge detector is used to extract edge points from the X-ray image. These edges have cluttered backgrounds and may be discontinuous. A fast spiral search is proposed to connect neighbouring points, either continuous or discontinuous, and form closed contours for individual objects. The distance and direction angle of an edge point in the search process can be obtained from a pre-constructed spiral look-up-table. No computation of the geometric features is required. Thus, the search of the coherent neighbouring points for edge connection is very fast. The experimental results have shown that the proposed method can effectively and efficiently segment a variety of firearms and knives of different shapes and sizes in the X-ray images of baggage.

Keywords:

• Object segmentation
• Firearm/knife detection
• X-ray image
• Spiral search
• Edge-linking

Additional information

Funding

This work was supported by Ministry of Science and Technology, Taiwan.