Abstract:
A system comprises a combination of digital fingerprint authentication techniques, processes, programs, and hardware to facilitate highly reliable authentication of a wide variety of composite physical objects. “Composite” in this case means that there are distinct regions of the object that must be authenticating individually and in tandem to authenticate the entire object. Preferably, a template is stored that defines for a class of objects what regions must be found, their locations, optionally semantic content of the regions, and other criteria. digital fingerprinting is utilized to locate and attempt to match candidate regions by querying a database of reference object records.
Abstract:
A security element is applied to a document or an object in the form of a directly printed marking or in the form of a tag made of paper or another material, with or without an identifier. A user can take a picture of the marking or tag with a smartphone and then send the picture to a device including software provided with a recognition algorithm including neural networks. The device visualizes the fingerprint of the tag or marking, thus making it possible to ascertain the authenticity of the document or object. In order to establish the authenticity of the product protected by the device, the image, stored in a cloud or blockchain database, of the tag obtained after printing same or of the marking is compared with a new description.
Abstract:
A computer-implemented method, a computer system, and a computer program product for managing physical objects. A computer system associates a physical object of a set of physical objects with an object identifier. The computer system obtains a digital fingerprint, from a unique physical property of the physical object, wherein the digital fingerprint is impacted by the unique physical property. The computer system obtains a dataset from the object identifier and the digital fingerprint. The computer system cryptographically signs the dataset to obtain a signature. The computer system instructs to store the object identifier and the signature on a data storage device.
Abstract:
The present disclosure relates to system(s) and method(s) for processing a scanned cheque. The system is configured for receiving a scanned cheque from a banking system, wherein the scanned cheque comprises a set of fields. Further, the system is configured for processing the scanned cheque using deep neural network for digitize the set of values. Further, the system is configured for applying a data processing algorithm on the digitized set of values to generate a set of processed values. Further, the system is configured for extracting a sub set of processed values, from the set of processed values, based on natural language processing of the set of processed values. Further, the system is configured for applying one or more validations, from a set of validations, on the sub set of processed values and transmit the sub set of processed values to the banking system thereby processing the scanned cheque.
Abstract:
New authentication features are proposed that are visible, can be authenticated with a mobile equipment and yet are challenging to counterfeit. In a possible embodiment, the surface of the authentication feature may have three-dimensional characteristics, which can be recognized by a handheld camera, such as a smartphone camera, while it cannot be easily reproduced by a simple scan and print procedure. In a further possible embodiment, at least two different viewpoints of the authentication feature may be acquired using a smartphone camera and the resulting images may be analyzed using the smartphone processor to identify the three-dimensional characteristics of the authentication feature. The manufacturing of the feature may be performed at a low cost by embossing the three dimensional structure on a surface. The authentication feature may be carried by a self-adhesive label or directly embedded on the product packaging.
Abstract:
There is described a new coding approach for printed document authentication, one objective of which is to increase the difficulty of copying. In addition, this new coding approach provides better performance compared to other 2D coding technologies under certain constraints. The new coding technique requires less print space in comparison to other coding techniques. This is achieved by optimizing some of the features which are used in standard 2D-codes for stabilization and which are necessary for e.g. mobile applications. Furthermore, the code can be decomposed in elementary units, or “byte-units” which can be widely spread over a text document. Such “byte-units” can in particular be used for integration in text symbols. If a document protected with such a coding is copied, at least some of these symbols will be extensively degraded by the copying process. Therefore, copy detection is intrinsically achieved thanks to the new coding technique.
Abstract:
Authentication method that provides: to make an authentication device, randomly attaching a plurality of reflecting particles, such as glitter, on a support; a first step of acquiring, with an optical acquisition device, at least two first images of the authentication device, the two first images each being acquired according to different lighting conditions; a first step of encoding each of the two first images in order to determine at least a first identifying indicator to be attributed to the authentication device.
Abstract:
Disclosed is a marking for an article, item or substrate. The marking comprises a printable code, at least a part of which is covered by a chiral liquid crystal polymer (CLCP) layer, and further preferably including an intermediate layer including a distribution of flakes, to provide readable information of at least two different types on the article.
Abstract:
Methods for certifying a security document comprising the steps of: a) selecting a set of unique characteristics, obtained as the result of the variations in the manufacturing process and supplies, b) getting a digital image of a security document and obtaining data of the relative position between features selected from different manufacturing processes (register), c) constructing a message by measuring the register of selected features from the document and the document ID data, d) constructing a hashed message, the hashed message being the message obtained after being encoded by means of a unidirectional cryptographic hash function, e) encrypting the hashed message using a public key cryptographic system to obtain a digital certificate by means of a private key, and f) storing the digital certificate in an external database.
Abstract:
Embodiment for detecting duplicate images include systems for determining that two or more of the images have similar key attributes such as attributes related to certain data in the images or image quality. Further, the embodiments include superimposing at least a portion of a first image of the two or more images over at least a portion of the second image of the two or more images, comparing the first image and second image; and determining whether the first image and the second image are identical.