CheckScan: A Reference Hashing for Identity Document Quality Detection
Résumé
One of important challenges in the document liveness detection process for identity document verification is quality verification. To tackle this challenge, this paper proposes a reference hashing approach to discriminate between the original template of the identity document image and the scan one, which is called checkScan. Actually, the discrimination process takes place between two aligned identity document images. The proposed approach is made up of two steps: feature selection based on Fast Fourier Transform (FFT) and hash construction. Feature selection based on FFT involves partitioning the identity document image into set of non-overlapping blocks, then the FFT magnitudes for each partitioned block is calculated in order to select a specific number of FFT magnitudes peaks as discriminative features. The hash construction step quantizes the selected peaks into binary codes by applying a new quantization approach that is based on the coordinates of the selected peaks. These two steps are combined together in this work to achieve good discriminate (well anti-collision) capability for distinct identity document image. Experiments were conducted in order to analyze and identify the most proper parameter to achieve higher discrimination performance. The experimental results were performed on the Mobile Identity Document Video dataset (MIDV-2020), and the results show that the proposed approach builds binary codes quite discriminative for distinct identity document images.
Domaines
Informatique [cs]Origine | Fichiers produits par l'(les) auteur(s) |
---|