Abstract: A method of handling mail items consists, during a first sorting pass, in taking a digital picture of each mail item for the purpose of automatically recognizing the address of the mail item, in directing the mail item towards a sorting outlet bin, and in deriving from said picture a digital fingerprint which is a logic identifier for the mail item, and, during a second sorting pass, in taking (42), once again, a digital picture of a current mail item so as to derive (43) a fingerprint from said picture, in performing, once again, automatic address recognition for obtaining address data for the current mail item, and in searching among address data recorded in the memory during the first sorting pass for a match with the address data of the current mail item (44) in order to identify a current bin to which the current mail item corresponds, so that, in order to search for a match between two digital fingerprints in the second pass, said search for matching fingerprints is conducted in an exploration space (45

Abstract: The method of sorting postal items in a plurality of sorting passes using at least one sorting machine having sorting outlets constituted by bins consists in using digital fingerprints (V_ID) identifying the items in a data processor system for automatic address recognition by OCR and/or by video coding. During the first sorting pass, the digital fingerprints of the items are recorded in association with the identification numbers (Bin_ID) of the bins. During the second sorting pass, these digital fingerprints and bin identification numbers are recovered in order to constitute a database (DB) which is updated by counting (46, 47, 48) the fingerprint matches obtained for each loaded bin and by counting consecutive accesses to the database that occur without obtaining a fingerprint match.

Abstract: The method of processing postal objects of large size in order to read automatically a postal address (AD) on each object consists in acquiring a digital image of each object at a certain level of resolution; in detecting in the image one or more zones of interest (ZI) apparently containing a postal address; in performing automatic address recognition on each zone of interest in order to extract a postal address (AD) of the object, and in the event of the automatic address recogition failing, in displaying each zone of interest (ZI) on a screen so that a video-coding operator can read the postal address (AD) of the object. Each zone of interest (ZI) is displayed on the screen on a screen context background (F) that is representative of the object but at a level of resolution that is lower than the level of resolution of the digital image and the zone of interest.

Abstract: A method of processing postal articles in which a physical magnitude is measured in order to detect (2) whether the outside surface of a postal article is made of a plastics material, and in which a digital image of said outside surface of the postal article is processed in order to detect (3) whether said surface has a noisy background. On the basis of the results of these two detection operations, it is determined (4) whether the outside surface of said postal article is a printable surface or a non-printable surface.

Abstract: The method of processing objects, in which method a digital image (1) is obtained of the surface of each postal object, which image includes address information (2), and an identifier or time stamp for the postal object is associated with the digital image of the postal object in a video-coding system, is characterized by the fact that said digital image is processed in order to extract a signature that serves as an identifier. The signature comprises a first component representative of a physical characteristic of the digital image and a second component (SC) which is a textual description of the address block. This method can be used to implement immediate video-coding in a postal sorting machine without requiring a delay line.

Abstract: The method of processing postal objects of large size in order to read automatically a postal address (AD) on each object consists in acquiring a digital image of each object at a certain level of resolution; in detecting in said image one or more zones of interest (ZI) apparently containing a postal address; in performing automatic address recognition on each zone of interest in order to extract a postal address (AD) of said object, and in the event of said step failing, in displaying each zone of interest (ZI) on a screen so that a video-coding operator can read the postal address (AD) of said object. Each zone of interest (ZI) is displayed on the screen on a screen context background (F) that is representative of the object but at a level of resolution that is lower than said certain level of resolution of the digital image. In this way, the video-coding operator has an overall view of the detected zones of interest, thus making it easier to read the postal address of the object.