摘要:
A system and method for comparing a query object and one or more of a set of database objects are provided. The method includes providing quantized representations of database objects. The database objects have each been transformed with a quantized embedding function which is the composition of a real-valued embedding function and a quantization function. The query object is transformed to a representation of the query object in a real-valued embedding space using the real-valued embedding function. Query-dependent estimated distance values are computed for the query object, based on the transformed query object and stored. A comparison (e.g., distance or similarity) measure between the query object and each of the quantized database object representations is computed based on the stored query-dependent estimated distance values. Data is output based on the comparison computation.
摘要:
A wordspotting system and method are disclosed. The method includes receiving a keyword and, for each of a set of typographical fonts, synthesizing a word image based on the keyword. A keyword model is trained based on the synthesized word images and the respective weights for each of the set of typographical fonts. Using the trained keyword model, handwritten word images of a collection of handwritten word images which match the keyword are identified. The weights allow a large set of fonts to be considered, with the weights indicating the relative relevance of each font for modeling a set of handwritten word images.
摘要:
An image adjustment includes adapting a universal palette to generate (i) an input image palette statistically representative of pixels of an input image and (ii) a reference image palette statistically representative of pixels of a reference image, and adjusting at least some pixels of the input image to generate adjusted pixels that are statistically represented by the reference image palette. In some embodiments, a user interface for controlling the image adjustment includes a display and at least one user input device, the user interface displaying a set of colors indicative of the regions of color space represented by a palette and receiving a selection of one or more regions of the color space, so that the image adjustment adjusts those pixels of the input image lying within the one or more selected regions of the color space.
摘要:
A method begins by receiving an image of a handwritten item. The method performs a word segmentation process on the image to produce a sub-image and extracts a set of feature vectors from the sub-image. Then, the method performs an asymmetric approach that computes a first log-likelihood score of the feature vectors using a word model having a first structure (such as one comprising a Hidden Markov Model (HMM)) and also computes a second log-likelihood score of the feature vectors using a background model having a second structure (such as one comprising a Gaussian Mixture Model (GMM)). The method computes a final score for the sub-image by subtracting the second log-likelihood score from the first log-likelihood score. The final score is then compared against a predetermined standard to produce a word identification result and the word identification result is output.
摘要:
A document classification method comprises: (i) classifying pages of an input document to generate page classifications; (ii) aggregating the page classifications to generate an input document representation, the aggregating not being based on ordering of the pages; and (iii) classifying the input document based on the input document representation. A page classifier for use in the page classifying operation (i) is trained based on pages of a set of labeled training documents having document classification labels. In some such embodiments, the pages of the set of labeled training documents are not labeled, and the page classifier training comprises: clustering pages of the set of labeled training documents to generate page clusters; and generating the page classifier based on the page clusters.
摘要:
To compute a signature for an object comprising or represented by a set of vectors in a vector space of dimensionality D, statistics are computed that are indicative of distribution of the vectors of the set of vectors amongst a set of regions Ri, i=1, . . . , N of the vector space, at least some statistics associated with each region are binarized to generate sets of binary values ai, i=1, . . . , N indicative of statistics of the vectors of the set of vectors belonging to the respective regions Ri, i=1, . . . , N; and a vector set signature is defined for the set of vectors including the sets of binary values ai, i=1, . . . , N. The computing, binarizing, and defining operations may be repeated for two sets of vectors, and a quantitative comparison of the two sets of vectors determined based on the corresponding vector set signatures.
摘要:
A classifier method comprises: projecting a set of training vectors in a vector space to a comparison space defined by a set of reference vectors using a comparison function to generate a corresponding set of projected training vectors in the comparison space; training a linear classifier on the set of projected training vectors to generate a trained linear classifier operative in the comparison space; and transforming the trained linear classifier operative in the comparison space into a trained nonlinear classifier that is operative in the vector space to classify an input vector.
摘要:
An educational recommender system and a method are provided. The method includes receiving a request to recommend a course of action related to a plurality of current students; accessing a computer database storing student data that corresponds to the plurality of current students; clustering in a computer process the plurality of current students into at least two clusters based at least on granular assessment data associated with student data corresponding to respective current students; and outputting the results of the clustering to a user. The granular assessment data includes a result of an assessment administered to respective students of the plurality of current students, and each assessment includes a plurality of questions for assessing one of the current students. The associated result includes an independent evaluation of each respective question of the plurality of questions.
摘要:
An automated image processing system and method are provided for class-based segmentation of a digital image. The method includes extracting a plurality of patches of an input image. For each patch, at least one feature is extracted. The feature may be a high level feature which is derived from the application of a generative model to a representation of low level feature(s) of the patch. For each patch, and for at least one object class from a set of object classes, a relevance score for the patch, based on the at least one feature, is computed. For at least some or all of the pixels of the image, a relevance score for the at least one object class based on the patch scores is computed. An object class is assigned to each of the pixels based on the computed relevance score for the at least one object class, allowing the image to be segmented and the segments labeled, based on object class.
摘要:
In an image classification system (70), a plurality of generative models (30) correspond to a plurality of image classes. Each generative model embodies a merger of a general visual vocabulary and an image class-specific visual vocabulary. A gradient-based class similarity modeler (40) includes (i) a model fitting data extractor (46) that generates model fitting data of an image (72) respective to each generative model and (ii) a dimensionality enhancer (50) that computes a gradient-based vector representation of the model fitting data with respect to each generative model in a vector space defined by the generative model. An image classifier (76) classifies the image respective to the plurality of image classes based on the gradient-based vector representations of class similarity.