Study on content-independent feature matching systems for container images

Abstract

In this paper, the study on feature matching for container images in custom areas is reported. The idea is to use computer image processing instead of manual operations in the container transportation processing system to cope with some problems in current customs operations. Our research focus on defining features for containers so that whether the containers have been opened or exchanged can be checked automatically. Features matching proposed in this study is similar to human's approach. It is to examine the colors and edge amounts of the given containers. Based on region of interest, those container images can be extracted from the whole image. The container image will be segmented into blocks by considering the proportion of an ordinary container. Then, our proposed method will try to find out the possible features for each block. First of all, the hue feature is considered to deal with the color of a container. Secondly, the pixels number of possible edges after applying edge detection is accumulated. Our approach is to combine and compare these two features to check whether there is any significant difference between two designated containers. Based on the experiments conducted, the proposed approach even very simple is very effective and thus, the security aspect during shipping and the integrity aspect after arriving of the containers can be ensured.