The ISACC project continues to develop outputs even after the natural closure of the project: the scientific team of the project relating to Unisalento and the University of Montenegro published an original scientific paper in the Journal of Maritime Sciences Vol. 24, No. 1/2023.
The authors: Andrea Chezzi, Mattia Colucci, Radmila Gagic, Danilo Martino, Claudio Pascarelli, and Adriana Pettinicchio, worked to give scientific evidence to the long work carried out during the ISACC project, addressing relevant topics such as: Customs, Antifraud, X-Ray, Computer vision, SIFT. The article submitted at the end of 2022 was accepted by the journal on March 27 and finally published online on June 12, 2023.
The theme of the article is the identification of one of the goals of customs authorities, hence, to identify, at borders, cargo that do not match their declaration, contain illegal items, or pose a hazard to society. Customs X-ray inspection procedures enable the detection of suspicious cargo and are an excellent support tool for customs officials.
The ISACC project aims at developing a web platform that integrates data, coming from heterogeneous technologies and systems, to provide a rich information base supporting customs authorities
during anti-fraud controls. In the paper is proposed a preliminary study based on the SIFT algorithm, for the automatic detection of visual changes between scanner X-Ray images.
Every year the global international trade in counterfeit, pirated and illegal goods amounts to hundreds of billion euros. Customs authorities working at borders play a vital role in contrasting this phenomenon
especially in those that have presented problems in this regard for decades, such as those between Italy, Albania and Montenegro.
Within the ISACC project an IT platform, supporting antifraud customs controls, has been designed and developed to integrate data coming from heterogeneous technologies and systems to provide a rich information base called Custom Footprint (CF). Customs authorities can use this CF and search for its variances, which would be a possible sign of fraud, at intermediate customs control points, i.e. the ports of Bari, Durres and Bar referring ISACC project. In order to compare scanner X-ray images that are part of the CF, it is proposed a possible approach, based on the SIFT algorithm (Scale-Invariant Feature Transform) and some preliminary results obtained with a synthetic dataset.
As shown in the relevant section, the final results can be considered encouraging, especially where the differences between the two images are below the 20 % threshold. This represents the case in which the proposed method is most useful: substantial differences between two images can in fact be easily detected by sight by a customs operator without the support of a computer tool.
As conclusion, the article focuses on future angle that will be directed toward further improving the developed method and testing it on a much larger number of samples (both synthetic and real). One possible solution that might be implemented and tested is to divide the images into smaller sections (tiles) so as to have not only an indicator of the difference between the two images but also to identify the region where this difference exists.