Pairing of images of postal articles with descriptors of singularities of the gradient field

    公开(公告)号:US10223587B2

    公开(公告)日:2019-03-05

    申请号:US15502169

    申请日:2016-06-15

    申请人: Solystic

    发明人: Olivier Desprez

    摘要: A method of processing articles, in particular postal articles, which method consists in forming a first digital image of an article and in deriving from said first image a first image signature that is a unique identifier for said article, in forming a current digital image again for said article, and in deriving from the current image a current signature that is compared with first article image signatures that are recorded in a memory, for the purpose of pairing-off the image signatures on the basis of similarity. The method is characterized in that each signature is derived using the following steps: extracting a digital map of the luminance gradient field of said image by local planar regression; identifying in said digital map points of interest corresponding to topological singularities of the gradient field having high local circular convergence or high local circular divergence.

    Structurally matching images by hashing gradient singularity descriptors

    公开(公告)号:US11640702B2

    公开(公告)日:2023-05-02

    申请号:US16652799

    申请日:2019-12-19

    申请人: SOLYSTIC

    发明人: Olivier Desprez

    摘要: The method of matching digital images of the same article in a data processor unit comprises the steps of: transforming each digital image of an article into a local divergence topographic map of the luminance gradient vector field; detecting singularities or extrema of local divergence in the luminance gradient vector field, such singularities corresponding to points of interest in said digital image; and, for each detected point of interest, encoding the values for the singularity of the gradient field that are located on a plurality of concentric rings centered on the point of interest so as to derive a digital data vector (210); and transforming said vector into a digital hash key (220) by means of a family of hash functions of the cosine Locality-Sensitive Hashing (LSH) type.