Patents by Inventor José Antonio Rodríguez-Serrano
José Antonio Rodríguez-Serrano has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20150046119Abstract: Methods, systems and processor-readable media for vehicle classification. In general, one or more vehicles can be scanned utilizing a laser scanner to compile data indicative of an optical profile of the vehicle(s). The optical profile associated with the vehicle(s) is then pre-processed. Particular features are extracted from the optical profile following pre-processing of the optical profile. The vehicle(s) can be then classified based on the particular features extracted from the optical feature. A segmented laser profile is treated as an image and profile features that integrate the signal in one of the two directions of the image and Fisher vectors which aggregate statistics of local “patches” of the image are computed and utilized as part of the extraction and classification process.Type: ApplicationFiled: August 9, 2013Publication date: February 12, 2015Applicant: Xerox CorporationInventors: Harsimrat Singh Sandhawalia, Jose Antonio Rodriguez Serrano, Herve Poirier, Gabriela Csurka
-
Patent number: 8917910Abstract: A system and a method for image segmentation use segmentation maps of one or more similar images as a basis for the segmentation. The method includes generating an image signature for an input image to be segmented and identifying at least one similar image from a set of images, based on the image signature of the input image and image signatures of images in the set of images. The similarity may be computed after first projecting the image signatures into a feature space where similarity is more likely to agree with segmentation map similarity. The input image is segmented, based on the segmentation map of one or more of the at least one identified similar images.Type: GrantFiled: January 16, 2012Date of Patent: December 23, 2014Assignee: Xerox CorporationInventor: Jose Antonio Rodriguez Serrano
-
Publication number: 20140355835Abstract: A system and method for computing confidence in an output of a text recognition system includes performing character recognition on an input text image with a text recognition system to generate a candidate string of characters. A first representation is generated, based on the candidate string of characters, and a second representation is generated based on the input text image. A confidence in the candidate string of characters is computed based on a computed similarity between the first and second representations in a common embedding space.Type: ApplicationFiled: May 28, 2013Publication date: December 4, 2014Inventors: Jose Antonio Rodriguez-Serrano, Florent C. Perronnin
-
Patent number: 8879796Abstract: A system and method are provided for segmenting an image. The method includes computing an image signature for an input image. One or more similar images are identified from a first set of images, based on the image signature of the input image and image signatures of images in the first set of images. The similar image or images are used to define a cropped region of the input image and a second image signature is computed, this time for the cropped region. One or more similar images are identified from a second set of images, based on the cropped image signature and the image signatures of images in the second set of images. The input image is segmented based on a segmentation map of at least one of the similar images identified in the second set of images.Type: GrantFiled: August 23, 2012Date of Patent: November 4, 2014Assignee: Xerox CorporationInventor: José Antonio Rodriguez Serrano
-
Publication number: 20140270350Abstract: A computer implemented method for localization of an object, such as a license plate, in an input image includes generating a task-dependent representation of the input image based on relevance scores for the object to be localized. The relevance scores are output by a classifier for a plurality of locations in the input image, such as patches. The classifier is trained on patches extracted from training images and their respective relevance labels. One or more similar images are identified from a set of images, based on a comparison of the task-dependent representation of the input image and task-dependent representations of images in the set of images. A location of the object in the input image is identified based on object location annotations for the similar images.Type: ApplicationFiled: March 14, 2013Publication date: September 18, 2014Applicant: XEROX CORPORATIONInventors: Jose Antonio Rodriguez-Serrano, Diane Larlus-Larrondo
-
Publication number: 20140270353Abstract: Methods, systems, and processor-readable media for pruning a training dictionary for use in detecting anomalous events from surveillance video. Training samples can be received, which correspond to normal events. A dictionary can then be constructed, which includes two or more classes of normal events from the training samples. Sparse codes are then generated for selected training samples with respect to the dictionary derived from the two or more classes of normal events. The size of the dictionary can then be reduced by removing redundant dictionary columns from the dictionary via analysis of the sparse codes. The dictionary is then optimized to yield a low reconstruction error and a high-interclass discriminability.Type: ApplicationFiled: March 14, 2013Publication date: September 18, 2014Applicant: Xerox CorporationInventors: Raja Bala, Zhigang Fan, Aaron Michael Burry, Jose Antonio Rodriguez-Serrano, Vishal Monga, Xuan Mo
-
Publication number: 20140219563Abstract: A system and method for comparing a text image 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 compatibility 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: ApplicationFiled: February 1, 2013Publication date: August 7, 2014Applicant: Xerox CorporationInventors: Jose Antonio Rodriguez-Serrano, Florent C. Perronnin
-
Patent number: 8666992Abstract: A system and a method of querying a remote service without revealing a private document to the remote service are provided. The method includes receiving a signature of a user's private document, and querying an intermediate database with the signature of the private document to generate an intermediate result set comprising intermediate database documents, based on a computation of similarity of the signatures of the intermediate database documents to the signature of the private document. The remote service is queried, based on the intermediate result set and a final result set is received from the remote service based on the query, which can be output to the user or further processed.Type: GrantFiled: June 15, 2012Date of Patent: March 4, 2014Assignee: Xerox CorporationInventors: Jose Antonio Rodriguez Serrano, Florent Perronnin, Vincent Devin
-
Publication number: 20140056520Abstract: A system and method are provided for segmenting an image. The method includes computing an image signature for an input image. One or more similar images are identified from a first set of images, based on the image signature of the input image and image signatures of images in the first set of images. The similar image or images are used to define a cropped region of the input image and a second image signature is computed, this time for the cropped region. One or more similar images are identified from a second set of images, based on the cropped image signature and the image signatures of images in the second set of images. The input image is segmented based on a segmentation map of at least one of the similar images identified in the second set of images.Type: ApplicationFiled: August 23, 2012Publication date: February 27, 2014Applicant: Xerox CorporationInventor: José Antonio Rodriguez Serrano
-
Publication number: 20130339386Abstract: A system and a method of querying a remote service without revealing a private document to the remote service are provided. The method includes receiving a signature of a user's private document, and querying an intermediate database with the signature of the private document to generate an intermediate result set comprising intermediate database documents, based on a computation of similarity of the signatures of the intermediate database documents to the signature of the private document. The remote service is queried, based on the intermediate result set and a final result set is received from the remote service based on the query, which can be output to the user or further processed.Type: ApplicationFiled: June 15, 2012Publication date: December 19, 2013Applicant: Xerox CorporationInventors: José Antonio Rodriguez Serrano, Florent Perronnin, Vincent Devin
-
Patent number: 8588470Abstract: Methods and systems for improved license plate signature matching by similarity learning on synthetic images comprise generating a plurality of synthetic license plate images; applying one or more transformations to the synthetic license plate images to cause the synthetic license plate images to more closely resemble authentic license plate image captures; and providing the synthetic license plate images as inputs to a machine distance learning algorithm in which weighted similarity scores are calculated between signatures of analogous and non-analogous license plate images and one or more sets of signature weights are iteratively adjusted to increase the likelihood that comparing analogous license plate images results in high weighted signature similarity scores and comparing non-analogous license plate images results in low weighted signature similarity scores.Type: GrantFiled: November 18, 2011Date of Patent: November 19, 2013Assignee: Xerox CorporationInventors: Jose Antonio Rodriguez Serrano, Raja Bala, Florent Perronnin, Craig John Saunders, Yonghui Zhao
-
Patent number: 8582819Abstract: In response to determining that a target vehicle is at large, identification information associated with the target vehicle's license plate may be retrieved and used to generate one or more synthetic license plate images. The synthetic license plate images may be subjected to one or more transformation to cause them to resemble authentic license plate image captures and/or to mimic authentic license plate image captures from existing and operational ALPR system cameras. Target signatures may then be calculated from the synthetic license plate images. Upon capturing an authentic license plate image using an ALPR system camera, a signature of the authentic license plate image may be calculated. If a match is found between the signature of the authentic license plate image and a target signature, law enforcement may be alerted that the target vehicle was detected at the location of the ALPR system camera.Type: GrantFiled: April 27, 2012Date of Patent: November 12, 2013Assignee: Xerox CorporationInventors: Jose Antonio Rodriguez Serrano, Aaron Michael Burrry, Harsimrat Sandhawalia, Craig Saunders, Vladimir Kozitsky, Abu Islam, John Deppen, Raja Bala
-
Publication number: 20130290222Abstract: 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: ApplicationFiled: April 27, 2012Publication date: October 31, 2013Applicant: Xerox CorporationInventors: Albert Gordo, José Antonio Rodriguez Serrano, Florent Perronnin
-
Publication number: 20130182909Abstract: A system and a method for image segmentation use segmentation maps of one or more similar images as a basis for the segmentation. The method includes generating an image signature for an input image to be segmented and identifying at least one similar image from a set of images, based on the image signature of the input image and image signatures of images in the set of images. The similarity may be computed after first projecting the image signatures into a feature space where similarity is more likely to agree with segmentation map similarity. The input image is segmented, based on the segmentation map of one or more of the at least one identified similar images.Type: ApplicationFiled: January 16, 2012Publication date: July 18, 2013Applicant: Xerox CorporationInventor: José Antonio Rodriguez-Serrano
-
Publication number: 20130129151Abstract: Methods and systems for improved license plate signature matching by similarity learning on synthetic images comprise generating a plurality of synthetic license plate images; applying one or more transformations to the synthetic license plate images to cause the synthetic license plate images to more closely resemble authentic license plate image captures; and providing the synthetic license plate images as inputs to a machine distance learning algorithm in which weighted similarity scores are calculated between signatures of analogous and non-analogous license plate images and one or more sets of signature weights are iteratively adjusted to increase the likelihood that comparing analogous license plate images results in high weighted signature similarity scores and comparing non-analogous license plate images results in low weighted signature similarity scores.Type: ApplicationFiled: November 18, 2011Publication date: May 23, 2013Applicant: Xerox CorporationInventors: Jose Antonio RODRIGUEZ SERRANO, Raja BALA, Florent PERRONNIN, Craig John SAUNDERS, Yonghui ZHAO
-
Publication number: 20130129152Abstract: In response to determining that a target vehicle is at large, identification information associated with the target vehicle's license plate may be retrieved and used to generate one or more synthetic license plate images. The synthetic license plate images may be subjected to one or more transformation to cause them to resemble authentic license plate image captures and/or to mimic authentic license plate image captures from existing and operational ALPR system cameras. Target signatures may then be calculated from the synthetic license plate images. Upon capturing an authentic license plate image using an ALPR system camera, a signature of the authentic license plate image may be calculated. If a match is found between the signature of the authentic license plate image and a target signature, law enforcement may be alerted that the target vehicle was detected at the location of the ALPR system camera.Type: ApplicationFiled: April 27, 2012Publication date: May 23, 2013Applicant: XEROX CORPORATIONInventors: Jose Antonio RODRIGUEZ SERRANO, Aaron Michael Burry, Harsimrat Sandhawalia, Craig Saunders, Vladimir Kozitsky, Abu Islam, John Deppen, Raja Bala
-
Publication number: 20130060786Abstract: A method and system are disclosed for conducting text-based searches of images using a visual signature associated with each image. A measure of string similarity between a query and an annotation associated with each entry in a first database is computed, and based upon the computed string similarity measures, a set of entries from the first database is selected. Each entry of the first database also includes an associated visual signature. At least one entry is then retrieved from a second database based upon a measure of visual similarity between a visual signature of each of the entries in the second database and the visual signatures of the entries in the selected set. Information corresponding to the retrieved entries from the second database is then generated.Type: ApplicationFiled: September 2, 2011Publication date: March 7, 2013Applicant: Xerox CorporationInventors: José Antonio Rodriguez Serrano, Florent Perronnin, Craig John Saunders