摘要:
Systems and methods for perceptual image preview are described. In one aspect, a naive preview image is generated by downsampling a larger image. Perceptual features of the larger image are then detected. Information associated with the detected perceptual features is then incorporated into the naive preview image to create a perceptual preview image. Since the perceptual preview image incorporates information associated with the detected perceptual features, a viewer of the perceptual preview image will be more likely to detect the presence or absence of such perceptual features in the larger image.
摘要:
Systems and methods for perceptual image preview are described. In one aspect, a naïve preview image is generated by downsampling a larger image. Perceptual features of the larger image are then detected. Information associated with the detected perceptual features is then incorporated into the naïve preview image to create a perceptual preview image. Since the perceptual preview image incorporates information associated with the detected perceptual features, a viewer of the perceptual preview image will be more likely to detect the presence or absence of such perceptual features in the larger image.
摘要:
Methods and systems for converting text into natural personal handwriting are provided. One aspect relates to the training of a computer to recognize a user's handwriting style. In one embodiment, the computer receives handwriting samples of at least one character written by the user, such as the character being provided as the beginning, middle, or ending character among a plurality of other characters. Further embodiments allow for increased personalization of the handwriting. Another aspect relates to system and methods for displaying a representation of a computer user's handwriting. In one embodiment, the handwriting comprises variant shapes of letters, personalized connection style between letters, and connection parts that look pressure-sensitive. In another embodiment, characters are adjusted, such as cutting portions of the character to create a more realistic recreation and synthesis of the handwriting.
摘要:
Methods and systems for converting text into natural personal handwriting are provided. One aspect relates to the training of a computer to recognize a user's handwriting style. In one embodiment, the computer receives handwriting samples of at least one character written by the user, such as the character being provided as the beginning, middle, or ending character among a plurality of other characters. Further embodiments allow for increased personalization of the handwriting. Another aspect relates to system and methods for displaying a representation of a computer user's handwriting. In one embodiment, the handwriting comprises variant shapes of letters, personalized connection style between letters, and connection parts that look pressure-sensitive. In another embodiment, characters are adjusted, such as cutting portions of the character to create a more realistic recreation and synthesis of the handwriting.
摘要:
Methods and systems for training a computer to recognize and verify an individual's signature are provided. One illustrative method extracts a plurality of both global and local features from a relatively small sample of handwriting samples. In one such embodiment, only 5 samples are needed from an individual without requiring forgeries. In yet another embodiment, only three global parameters are utilized, thus reducing the complexity, and processing power, of the system. Utilizing such few global parameters also facilitates fine tuning of the systems. Further aspects of the invention relate to a multi-stage statistical system for on-line signature verification. In one embodiment, the system may comprise a simplified GMM model built on global signature properties and a left-to-right HMM model based on segmental features. In one embodiment, specific strategies are utilized to create model simplification and initialization in contrast to general GMM and HMM models.
摘要:
Methods and systems for training a computer to recognize and verify an individual's signature are provided. One illustrative method extracts a plurality of both global and local features from a relatively small sample of handwriting samples. In one such embodiment, only 5 samples are needed from an individual without requiring forgeries. In yet another embodiment, only three global parameters are utilized, thus reducing the complexity, and processing power, of the system. Utilizing such few global parameters also facilitates fine tuning of the systems. Further aspects of the invention relate to a multi-stage statistical system for on-line signature verification. In one embodiment, the system may comprise a simplified GMM model built on global signature properties and a left-to-right HMM model based on segmental features. In one embodiment, specific strategies are utilized to create model simplification and initialization in contrast to general GMM and HMM models.
摘要:
Described is a technology, such as implemented in a computational software program, by which a minimal polynomial is efficiently determined for a radical expression over the ring Z of integer numbers or the ring Q of rational numbers. The levels of the radical are grouped into a level permutation group that is used to find a level permutation set. An annihilation polynomial is found based upon the level permutation set. The annihilation polynomial is factored, and a selection mechanism selects the minimal polynomial based upon the annihilation polynomial's factors.
摘要:
Described is using semi-Riemannian geometry in supervised learning to learn a discriminant subspace for classification, e.g., labeled samples are used to learn the geometry of a semi-Riemannian submanifold. For a given sample, the K nearest classes of that sample are determined, along with the nearest samples that are in other classes, and the nearest samples in that sample's same class. The distances between these samples are computed, and used in computing a metric matrix. The metric matrix is used to compute a projection matrix that corresponds to the discriminant subspace. In online classification, as a new sample is received, it is projected into a feature space by use of the projection matrix and classified accordingly.
摘要:
An exemplary method for extracting discriminant feature of samples includes providing data for samples in a multidimensional space; based on the data, computing local similarities for the samples; mapping the local similarities to weights; based on the mapping, formulating an inter-class scatter matrix and an intra-class scatter matrix; and based on the matrices, maximizing the ratio of inter-class scatter to intra-class scatter for the samples to provide discriminate features of the samples. Such a method may be used for classifying samples, recognizing patterns, or other tasks. Various other methods, devices, system, etc., are also disclosed.
摘要:
Ink-parser-parameter optimization may be performed via parallel processing to accelerate searching for a set of optimal ink-parser parameters. Evaluators may parse pages of ink notes with different groups of parameters and may compute corresponding values for evaluation functions. Separate evaluation functions may be defined for the following types of ink-parker parsing engines: writing parser, writing/drawing classification, table detection, and list detection. A searcher may perform a grid-searching algorithm or a genetic algorithm to generate groups of parameters and may then pass the parameters to available evaluators for evaluation until evaluation-function values for a group of parameters satisfy a convergence condition.