Defeating fake food labels using watermarking and biosequence analysis

Publisher:
IEEE
Publication Type:
Conference Proceeding
Citation:
Proceedings - 2019 18th IEEE International Conference on Trust, Security and Privacy in Computing and Communications/13th IEEE International Conference on Big Data Science and Engineering, TrustCom/BigDataSE 2019, 2019, pp. 435-441
Issue Date:
2019-08-01
Filename Description Size
08887374 (1).pdfPublished version205.98 kB
Adobe PDF
Full metadata record
© 2019 IEEE. Fake food label is one of the leading ways to distribute a low quality food item as a high quality branded product. For example, under fake labels, significantly higher amount of fake Manuka honey is sold than what is actually being produced. In this paper, we propose a scheme to combat the spread of such low quality food items by identifying fake food labels. In our scheme, a watermarking is inserted to a genuine food label and biosequence analysis is used to detect this watermark. The proposed biosequence analysis is such that it can detect duplicate labels, for example a photocopy of the genuine label. The proposed method works by converting a label image into biological amino acid form (e.g., to A, C, D, G, H, etc. form) and then extracting a signature from the label (which is represented in amino acid form) using biological tools. These signatures are then matched against a query label image to find out its originality. Experiment with honey food labels (honey watermarked dataset created by us) shows that the proposed method has true positive rate of 91:67%.
Please use this identifier to cite or link to this item: