Search Patents
  • EXTRACTING GRADIENT FEATURES FROM NEURAL NETWORKS
    Publication number: 20170011280
    Abstract: A method for extracting a representation from an image includes inputting an image to a pre-trained neural network. The gradient of a loss function is computed with respect to parameters of the neural network, for the image. A gradient representation is extracted for the image based on the computed gradients, which can be used, for example, for classification or retrieval.
    Type: Application
    Filed: July 7, 2015
    Publication date: January 12, 2017
    Applicant: Xerox Corporation
    Inventors: Albert Gordo Soldevila, Adrien Gaidon, Florent C. Perronnin
  • Supervised mid-level features for word image representation
    Patent number: 9245205
    Abstract: Disclosed is a method and system to learning mid-level features for text images that leverages character bounding box annotations. According to an exemplary embodiment, the disclosed method and system includes extracting semantic local descriptors by aggregating local statistics of small patches and correlating them with character bounding box annotations.
    Type: Grant
    Filed: October 1, 2014
    Date of Patent: January 26, 2016
    Assignee: Xerox Corporation
    Inventor: Albert Gordo Soldevila
  • Extracting gradient features from neural networks
    Patent number: 9792492
    Abstract: A method for extracting a representation from an image includes inputting an image to a pre-trained neural network. The gradient of a loss function is computed with respect to parameters of the neural network, for the image. A gradient representation is extracted for the image based on the computed gradients, which can be used, for example, for classification or retrieval.
    Type: Grant
    Filed: July 7, 2015
    Date of Patent: October 17, 2017
    Assignee: XEROX CORPORATION
    Inventors: Albert Gordo Soldevila, Adrien Gaidon, Florent C. Perronnin
  • SYSTEM AND METHOD FOR PRODUCT IDENTIFICATION
    Publication number: 20160155011
    Abstract: A system and method for object instance localization in an image are disclosed. In the method, keypoints are detected in a target image and candidate regions are detected by matching the detected keypoints to keypoints detected in a set of reference images. Similarity measures between global descriptors computed for the located candidate regions and global descriptors for the reference images are computed and labels are assigned to at least some of the candidate regions based on the computed similarity measures. Performing the region detection based on keypoint matching while performing the labeling based on global descriptors improves object instance detection.
    Type: Application
    Filed: December 2, 2014
    Publication date: June 2, 2016
    Inventors: Milan Sulc, Albert Gordo Soldevila, Diane Larlus Larrondo, Florent C. Perronnin
  • System and method for product identification
    Patent number: 9443164
    Abstract: A system and method for object instance localization in an image are disclosed. In the method, keypoints are detected in a target image and candidate regions are detected by matching the detected keypoints to keypoints detected in a set of reference images. Similarity measures between global descriptors computed for the located candidate regions and global descriptors for the reference images are computed and labels are assigned to at least some of the candidate regions based on the computed similarity measures. Performing the region detection based on keypoint matching while performing the labeling based on global descriptors improves object instance detection.
    Type: Grant
    Filed: December 2, 2014
    Date of Patent: September 13, 2016
    Inventors: Milan Sulc, Albert Gordo Soldevila, Diane Larlus Larrondo, Florent C. Perronnin
  • RETRIEVAL SYSTEM AND METHOD LEVERAGING CATEGORY-LEVEL LABELS
    Publication number: 20130290222
    Abstract: An instance-level retrieval method and system are provided. A representation of a query image is embedded in a multi-dimensional space using a learned projection. The projection is learned using category-labeled training data to optimize a classification rate on the training data. The joint learning of the projection and the classifiers improves the computation of similarity/distance between images by embedding them in a subspace where the similarity computation outputs more accurate results. An input query image can thus be used to retrieve similar instances in a database by computing the comparison measure in the embedding space.
    Type: Application
    Filed: April 27, 2012
    Publication date: October 31, 2013
    Applicant: Xerox Corporation
    Inventors: Albert Gordo, José Antonio Rodriguez Serrano, Florent Perronnin
  • QUERY EXPANSION LEARNING WITH RECURRENT NETWORKS
    Publication number: 20180260414
    Abstract: A method for query expansion uses a representation of an input query object, such as an image, to retrieve representations of similar objects retrieved using the query object representation as a query. Given the set of image representations, a weight is predicted for each using a prediction model which assigns different weights to the image representations. An expanded query is generated as a weighted aggregation (e.g., sum) of the query object representation and at least a subset of the set of similar object representations in which each object representation is weighted with its predicted weight. A higher weight can thus be given to one of the similar object representations, in the expanded query, than to another.
    Type: Application
    Filed: March 10, 2017
    Publication date: September 13, 2018
    Applicant: Xerox Corporation
    Inventor: Albert Gordo Soldevila
  • Retrieval system and method leveraging category-level labels
    Patent number: 9075824
    Abstract: An instance-level retrieval method and system are provided. A representation of a query image is embedded in a multi-dimensional space using a learned projection. The projection is learned using category-labeled training data to optimize a classification rate on the training data. The joint learning of the projection and the classifiers improves the computation of similarity/distance between images by embedding them in a subspace where the similarity computation outputs more accurate results. An input query image can thus be used to retrieve similar instances in a database by computing the comparison measure in the embedding space.
    Type: Grant
    Filed: April 27, 2012
    Date of Patent: July 7, 2015
    Assignee: XEROX CORPORATION
    Inventors: Albert Gordo, Jose Antonio Rodriguez Serrano, Florent Perronnin
  • COARSE-TO-FINE CASCADE ADAPTATIONS FOR LICENSE PLATE RECOGNITION WITH CONVOLUTIONAL NEURAL NETWORKS
    Publication number: 20170177965
    Abstract: Methods and systems for license plate recognition utilizing a trained neural network. In an example embodiment, a neural network can be subject to operations involving iteratively training and adapting the neural network for a particular task such as, for example, text recognition in the context of a license plate recognition application. The neural network can be trained to perform generic text recognition utilizing a plurality of training samples. The neural network can be applied to a cropped image of a license plate in order to recognize text and produce a license plate transcription with respect to the license plate. An example of such a neural network is a CNN (Convolutional Neural Network).
    Type: Application
    Filed: December 17, 2015
    Publication date: June 22, 2017
    Inventors: Albert Gordo Soldevila, Jon Almazan
  • LATENT EMBEDDINGS FOR WORD IMAGES AND THEIR SEMANTICS
    Publication number: 20170011279
    Abstract: A system and method enable semantic comparisons to be made between word images and concepts. Training word images and their concept labels are used to learn parameters of a neural network for embedding word images and concepts in a semantic subspace in which comparisons can be made between word images and concepts without the need for transcribing the text content of the word image. The training of the neural network aims to minimize a ranking loss over the training set where non relevant concepts for an image which are ranked more highly than relevant ones penalize the ranking loss.
    Type: Application
    Filed: July 7, 2015
    Publication date: January 12, 2017
    Applicant: Xerox Corporation
    Inventors: Albert Gordo Soldevila, Jon Almazán Almazán, Naila Murray, Florent C. Perronnin
  • Latent embeddings for word images and their semantics
    Patent number: 10635949
    Abstract: A system and method enable semantic comparisons to be made between word images and concepts. Training word images and their concept labels are used to learn parameters of a neural network for embedding word images and concepts in a semantic subspace in which comparisons can be made between word images and concepts without the need for transcribing the text content of the word image. The training of the neural network aims to minimize a ranking loss over the training set where non relevant concepts for an image which are ranked more highly than relevant ones penalize the ranking loss.
    Type: Grant
    Filed: July 7, 2015
    Date of Patent: April 28, 2020
    Assignee: XEROX CORPORATION
    Inventors: Albert Gordo Soldevila, Jon Almazán Almazán, Naila Murray, Florent C. Perronnin
  • UNSTRUCTURED DOCUMENT CLASSIFICATION
    Publication number: 20110137898
    Abstract: 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.
    Type: Application
    Filed: December 7, 2009
    Publication date: June 9, 2011
    Applicant: XEROX CORPORATION
    Inventors: Albert Gordo, Florent Perronnin, Francois Ragnet
  • Coarse-to-fine cascade adaptations for license plate recognition with convolutional neural networks
    Patent number: 9785855
    Abstract: Methods and systems for license plate recognition utilizing a trained neural network. In an example embodiment, a neural network can be subject to operations involving iteratively training and adapting the neural network for a particular task such as, for example, text recognition in the context of a license plate recognition application. The neural network can be trained to perform generic text recognition utilizing a plurality of training samples. The neural network can be applied to a cropped image of a license plate in order to recognize text and produce a license plate transcription with respect to the license plate. An example of such a neural network is a CNN (Convolutional Neural. Network).
    Type: Grant
    Filed: December 17, 2015
    Date of Patent: October 10, 2017
    Assignee: Conduent Business Services, LLC
    Inventors: Albert Gordo Soldevila, Jon Almazan
  • SIMILARITY-BASED DETECTION OF PROMINENT OBJECTS USING DEEP CNN POOLING LAYERS AS FEATURES
    Publication number: 20170083792
    Abstract: A system and method provide object localization in a query image based on a global representation of the image generated with a model derived from a convolutional neural network. Representations of annotated images and a query image are each generated based on activations output by a layer of the model which precedes the fully-connected layers of the neural network. A similarity is computed between the query image representation and each of the annotated image representations to identify a subset of the annotated images having the highest computed similarity. Object location information from at least one of the subset of annotated images is transferred to the query image and information is output, based on the transferred object location information.
    Type: Application
    Filed: September 22, 2015
    Publication date: March 23, 2017
    Applicant: Xerox Corporation
    Inventors: José A. Rodríguez-Serrano, Albert Gordo Soldevila
  • LEVERAGING CAPTIONS TO LEARN A GLOBAL VISUAL REPRESENTATION FOR SEMANTIC RETRIEVAL
    Publication number: 20180373955
    Abstract: Similar images are identified by semantically matching human-supplied text captions accompanying training images. An image representation function is trained to produce similar vectors for similar images according to this similarity. The trained function is applied to non-training second images in a different database to produce second vectors. This trained function does not require the second images to contain captions. A query image is matched to the second images by applying the trained function to the query image to produce a query vector, and the second images are ranked based on how closely the second vectors match the query vector, and the top ranking ones of the second images are output as a response to the query image.
    Type: Application
    Filed: June 27, 2017
    Publication date: December 27, 2018
    Applicant: Xerox Corporation
    Inventors: Albert Gordo Soldevila, Diane Larlus-Larrondo
  • Similarity-based detection of prominent objects using deep CNN pooling layers as features
    Patent number: 9767381
    Abstract: A system and method provide object localization in a query image based on a global representation of the image generated with a model derived from a convolutional neural network. Representations of annotated images and a query image are each generated based on activations output by a layer of the model which precedes the fully-connected layers of the neural network. A similarity is computed between the query image representation and each of the annotated image representations to identify a subset of the annotated images having the highest computed similarity. Object location information from at least one of the subset of annotated images is transferred to the query image and information is output, based on the transferred object location information.
    Type: Grant
    Filed: September 22, 2015
    Date of Patent: September 19, 2017
    Assignee: XEROX CORPORATION
    Inventors: José A. Rodríguez-Serrano, Albert Gordo Soldevila
  • METHOD AND SYSTEM TO PERFORM TEXT-TO-IMAGE QUERIES WITH WILDCARDS
    Publication number: 20160210532
    Abstract: A system and method for comparing a text image with or without a wildcard character and a character string are provided. The method includes embedding a character string into a vectorial space by extracting a set of features from the character string and generating a character string representation based on the extracted features, such as a spatial pyramid bag of characters (SPBOC) representation. A text image is embedded into a vectorial space by extracting a set of features from the text image and generating a text image representation based on the text image extracted features. A similarity between the text image representation and the character string representation is computed, which includes computing a function of the text image representation and character string representation.
    Type: Application
    Filed: January 21, 2015
    Publication date: July 21, 2016
    Inventors: Albert Gordo Soldevila, José Antonio Rodríguez-Serrano, Florent Perronnin
  • ONE-TO-MANY MATCHING WITH APPLICATION TO EFFICIENT PRIVACY-PRESERVING RE-IDENTIFICATION
    Publication number: 20160277190
    Abstract: Authentication methods are disclosed for determining whether a person or object to be authenticated is a member of a set of authorized persons or objects. A query signature is acquired comprising a vector whose elements store values of an ordered set of features for the person or object to be authenticated. The query signature is compared with an aggregate signature comprising a vector whose elements store values of the ordered set of features for the set of authorized persons or objects. The individual signatures for the authorized persons or objects are not stored; only the aggregate signature. It is determined whether the person or object to be authenticated is a member of the set of authorized persons or objects based on the comparison. The comparing may comprise computing an inner product of the query signature and the aggregate signature, with the determining being based on the inner product.
    Type: Application
    Filed: March 19, 2015
    Publication date: September 22, 2016
    Inventors: Albert Gordo Soldevila, Naila Murray, Florent C. Perronnin
  • LARGE-SCALE ASYMMETRIC COMPARISON COMPUTATION FOR BINARY EMBEDDINGS
    Publication number: 20120143853
    Abstract: 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.
    Type: Application
    Filed: December 3, 2010
    Publication date: June 7, 2012
    Applicant: Xerox Corporation
    Inventors: Albert Gordo, Florent Perronnin
  • Large-scale asymmetric comparison computation for binary embeddings
    Patent number: 8370338
    Abstract: 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.
    Type: Grant
    Filed: December 3, 2010
    Date of Patent: February 5, 2013
    Assignee: Xerox Corporation
    Inventors: Albert Gordo, Florent Perronnin
Narrow Results

Filter by US Classification