Abstract: An example system includes a feature extraction engine. The feature extraction engine is to determine a plurality of scale-dependent features for a portion of a target. The system also includes a signature-generation engine to select a subset of the plurality of scale-dependent features based on a strength of each feature. The signature-generation engine also is to store a numeric representation of the portion of the target and the subset of the plurality of scale-dependent features.

Abstract: An example system includes a feature extraction engine. The feature extraction engine is to determine a plurality of scale-dependent features for a portion of a target. The system also includes a signature-generation engine to select a subset of the plurality of scale-dependent features based on a strength of each feature. The signature-generation engine also is to store a numeric representation of the portion of the target and the subset of the plurality of scale-dependent features.

Abstract: An example system includes a feature extraction engine. The feature extraction engine is to determine a plurality of scale-dependent features for a portion of a target. The system also includes a signature-generation engine to select a subset of the plurality of scale-dependent features based on a strength of each feature. The signature-generation engine also is to store a numeric representation of the portion of the target and the subset of the plurality of scale-dependent features.

Abstract: Examples herein disclose receiving a service request including a latency associated with a publication of a result of the service request. The examples disclose computing a workload for the service request and identifying multiple resources which are to perform the service request by applying the latency to the multiple resources.

Abstract: A learning graph is generated for documents according to a sequencing approach. The learning graph includes nodes corresponding to the documents and edges. Each edge connects two of the nodes and indicates a sequencing relationship between two of the documents to which the two of the nodes correspond that specifies an order in which the two of the documents are to be reviewed in satisfaction of the learning goal. The learning graph is a directed graph specifying a learning path through the documents to achieve a learning goal in relation to a subject.

Abstract: A system for distinguishing a package includes a plurality of identifiers, where at least one of the identifiers is intentionally non-functional. The system also includes an identifier indicator that indicates the identity of the at least one of the identifiers that is intentionally non-functional. In addition, the identifier indicator is stored on at least one of the package and a database and is accessible by a user to authenticate the package.

Abstract: A method for making an authenticating system for an object includes selecting an image and adding a watermark in a predetermined area of the image. The predetermined area may be a portion of the image. The method also includes establishing the image having the watermark therein on the object, and associating the watermark with the object to render object-specific authenticating data.

Abstract: A method for making an authenticating system for a package includes establishing a plurality of variable instruments on the package and depositing a product in the package after the instruments have been established thereon. The method also includes acquiring information from at least two of the plurality of instruments, and associating the acquired information with the product to render product-specific authentication data.

Abstract: A method is provided of personalizing color reproduction of an output device by determining a user-specific color mapping. A user is enabled to individually select different color reproductions of a plurality of different test images according to the user's preferences, wherein the different color reproductions are associated with different color mappings. The test images are reproduced by the output device or a display device simulating the output device. The user-specific color mapping is determined by combining the color mappings of the selected color reproductions.

Abstract: A system for distinguishing a package includes a plurality of identifiers, where at least one of the identifiers is intentionally non-functional. The system also includes an identifier indicator that indicates the identity of the at least one of the identifiers that is intentionally non-functional. In addition, the identifier indicator is stored on at least one of the package and a database and is accessible by a user to authenticate the package.

Abstract: A system and method for deploying a document classification system include deploying a document classification system with a first classification engine configuration, and thereafter, automatically redeploying the document classification system with a second classification engine configuration in response to a cost function.

Abstract: A method for classifying regions defined within a digital image includes defining a tessellated set of regions from a plurality of regions identified by a plurality of segmented versions of the digital image and then classifying each tessellated region according to a likelihood that the tessellated region contains text.

Abstract: Disclosed are methods of refining the region boundaries for individual negatives or slides when scanning a plurality of negative or slides, including the defining of rows and columns based on the median spacings between regions, and the median spans of the regions, in the vertical and horizontal directions; and aligning the identified negative or slide regions to the defined rows and columns. The negative or slide regions may then be ordered to conform to the ordering represented on the scanning adapter.

Abstract: A method for embedding covert information on a printed substrate is provided. The method can include the steps of printing overt indicia on a substrate and generating a pattern of microtext representative of at least a portion of the overt indicia. Such microtext is capable of being printed in at least two distinct fonts, including a first font and a second font. The method can further include steps of varying the pattern of microtext such that at least one character of the pattern of microtext is configured to be printed in the first font and at least one character is configured to be printed in the second font, thereby providing a font variation which corresponds to a covert code, and printing the pattern of microtext which includes the font variation on the substrate.

Abstract: There is disclosed a method of identifying a product involving generating a code unique to the product, said code being provided by a multitude of individual identifiers, applying the multitude of the identifiers of the code to the packaging of the product as a pattern to identify the product. The method also involves applying a sub-set of two or more of the multitude of the identifiers of said code to the product, said sub-set of the multitude of the identifiers of the code being applied so they will be presented in the same pattern order as they appear in the pattern order of the multitude of the identifiers of the code applied to the packaging. The product can be identified with a reasonable likelihood of being a genuine product by determining that a presented pattern order of the sub-set of the multitude of the identifiers applied to the product corresponds to a presented pattern order within the multitude of the identifiers applied to the packaging.

Abstract: A method of providing customized medical monitoring to a patient is disclosed. The method can include steps of selecting a medical monitoring device for a patient, where the medical monitoring device is associated with a biological transducer, determining at least one desired monitoring parameter, and customizing locally the medical monitoring device to monitor the desired monitoring parameter collected by the biological transducer. The method may further include steps of providing the medical monitoring device to the patient, and monitoring at least one health parameter of the patient from a remote location. The medical monitoring device can also be customized remotely.

Abstract: A method for dynamic control of medications provided to a patient at a remote location is disclosed. The method can include steps of selecting a customized set of medications for a patient, where the customized set of medications at least partially reflect a medical diagnosis of the patient, and providing the customized set of medications to the patient, where the customized set of medications are inaccessible to the patient without authorization from a medical care provider. Further steps of the method can include authorizing the patient to receive a first medication regimen from the customized set of medications, monitoring remotely at least one health parameter of the patient, and authorizing the first medication regimen to be modified to a second medication regimen based at least partially on the at least one health parameter.

Abstract: A method of creating a virtual lead associated with a physiological recording is provided. The method can include obtaining a first physiological signal from a first lead having a first angle and a second physiological signal from a second lead having a second angle, the first lead and the second lead being associated with a subject. The method can also include transforming the first and second physiological signals into a vector representation of the first and second physiological signals and transforming the vector representation to a virtual physiological signal representing a virtual lead having a virtual lead angle.

Abstract: A method of obtaining a filtered electrocardiogram is provided. The method includes the steps of obtaining a vectorcardiogram, filtering the vectorcardiogram to form a filtered vectorcardiogram, and transforming the filtered vectorcardiogram into a filtered electrocardiogram. The method may also include the preliminary step of obtaining an electrocardiogram, and then transforming the electrocardiogram into the vectorcardiogram.

Abstract: A method for generating a modifiable summary of medical data derived from a patient can comprise steps of selecting a subset of medical data from a medical database, wherein the subset at least partially is uniquely associated with an individual patient, and generating a living graphical representation from at least a portion of the subset. The living graphical representation can be dynamically reconfigurable upon modification of the portion. In another embodiment, a method for customizing patient medical information for presentation to a patient as a customized file can comprise steps of determining a medical condition of a patient, identifying static data related to the medical condition, and identifying dynamic data uniquely related to the patient. Additional steps can include forming a customized file of the patient from the static and dynamic data, wherein the customized file summarizes at least an episode of medical care.