Patents by Inventor Florent Perronnin
Florent Perronnin 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: 20130028508Abstract: A system and method for computing a place profile are disclosed. The method includes providing a geographical definition of a place, retrieving a set of images based on the geographical place definition. With a classifier, image-level statistics for the retrieved images are generated. The classifier has been trained to generate image-level statistics for a finite set of classes, such as different activities. The image-level statistics are aggregated to generate a place profile for the defined place which may be displayed to a user who has provided information for generating the geographical definition or used in an application such as a recommender system or to generate a personal profile for the user.Type: ApplicationFiled: July 26, 2011Publication date: January 31, 2013Applicant: XEROX CORPORATIONInventors: Florent Perronnin, Nicolas Guérin, Craig John Saunders
-
Patent number: 8332429Abstract: A method and system to help photographers to take better quality pictures of landmarks and scenes are disclosed. A user is guided with examples of existing quality images, which are extracted from a database, of the same or similar landmarks or scenes. The method includes taking a query photograph that may include an image associated with a GPS location and other metadata, and using information extracted from the image to retrieve existing, similar images. The images retrieved may be ordered according to different criteria. When a user selects one as a model image, the user is provided with assistance for taking a target photograph of similar quality.Type: GrantFiled: June 22, 2010Date of Patent: December 11, 2012Assignee: Xerox CorporationInventors: Hervé Poirier, Florent Perronnin, Mario Agustin Ricardo Jarmasz
-
Patent number: 8326087Abstract: As set forth herein, a computer-based method is employed to align a sequences of images. Metadata associated with images from two or more sources is received and a time stamp is extracted from the metadata. The images are sorted into sequences based at least in part upon the image source. The similarity of images from disparate sequences is measured and image pairs from disparate sequences with a similarity greater than a predetermined threshold are identified. A sequence of images is aligned by minimizing the misalignment of pairs.Type: GrantFiled: November 25, 2008Date of Patent: December 4, 2012Assignee: Xerox CorporationInventors: Florent Perronnin, Claudio Cifarelli
-
Patent number: 8301579Abstract: A method of maximizing a concave log-likelihood function comprises: selecting a pair of parameters from a plurality of adjustable parameters of a concave log-likelihood function; maximizing a value of the concave log-likelihood function respective to an adjustment value to generate an optimal adjustment value, wherein the value of one member of the selected pair of parameters is increased by the adjustment value and the value of the other member of the selected pair of parameters is decreased by the adjustment value; updating values of the plurality of adjustable parameters by increasing the value of the one member of the selected pair of parameters by the optimized adjustment value and decreasing the value of the other member of the selected pair of parameters by the optimized adjustment value; and repeating the selecting, maximizing, and updating for different pairs of parameters to identify optimized values of the plurality of adjustable parameters.Type: GrantFiled: October 6, 2008Date of Patent: October 30, 2012Assignee: Xerox CorporationInventors: Florent Perronnin, Guillaume Bouchard
-
Publication number: 20120269425Abstract: A system and method for determining the aesthetic quality of an image are disclosed. The method includes extracting a set of local features from the image, such as gradient and/or color features and generating an image representation which describes the distribution of the local features. A classifier system is used for determining an aesthetic quality of the image based on the computed image representation.Type: ApplicationFiled: April 19, 2011Publication date: October 25, 2012Applicant: Xerox CorporationInventors: Luca Marchesotti, Florent Perronnin, Gabriela Csurka
-
Patent number: 8280828Abstract: 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.Type: GrantFiled: June 12, 2009Date of Patent: October 2, 2012Assignee: Xerox CorporationInventors: Florent Perronnin, Jorge Sanchez
-
Publication number: 20120163715Abstract: A system and method are provided for modeling a chromatic object, such as an image. For a set of colors of a chromatic object that are expressed as color values in a perceptual color space, the method includes optimizing a convex objective function which is a log likelihood function of a combination of weighted kernels centered on each color in the set over each of the other colors in the set. A number Nc of weighted kernels in the optimized function which each have a weight which is at least greater than 0 is identified. The chromatic object is modeled with a mixture model in which the complexity of the model is based on the identified number Nc.Type: ApplicationFiled: December 22, 2010Publication date: June 28, 2012Applicant: Xerox CorporationInventors: NAILA MURRAY, Florent Perronnin, Luca Marchesotti, Sandra Skaff
-
Publication number: 20120143853Abstract: 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: ApplicationFiled: December 3, 2010Publication date: June 7, 2012Applicant: Xerox CorporationInventors: Albert Gordo, Florent Perronnin
-
Patent number: 8165410Abstract: Category context models (64) and a universal context model (62) are generated including sums of soft co-occurrences of pairs of visual words in geometric proximity to each other in training images (50) assigned to each category and assigned to all categories, respectively. Context information (76) about an image to be classified (70) are generated including sums of soft co-occurrences of pairs of visual words in geometric proximity to each other in the image to be classified. For each category (82), a comparison is made of (i) closeness of the context information about the image to be classified with the corresponding category context model and (ii) closeness of the context information about the image to be classified with the universal context model. An image category (92) is assigned to the image to be classified being based on the comparisons.Type: GrantFiled: December 17, 2010Date of Patent: April 24, 2012Assignee: Xerox CorporationInventor: Florent Perronnin
-
Publication number: 20120075329Abstract: A system and method for color transfer are provided. The method includes retrieving a concept color palette from computer memory corresponding to a concept selected by a user. The concept color palette includes a first set of colors, which may be statistically representative of colors of a set of predefined color palettes which have been associated with the concept. The method further includes computing an image color palette for an input image. The image color palette includes a second set of colors that are representative of pixels of the input image. Colors of the image color palette are mapped to colors of the concept color palette to identify, for colors of the image color palette, a corresponding color in the concept color palette. A transformation is computed based on the mapping. For pixels of the input image, modified color values are computed, based on the computed transformation, to generate a modified image.Type: ApplicationFiled: September 24, 2010Publication date: March 29, 2012Applicant: XEROX CORPORATIONInventors: Sandra Skaff, Naila Murray, Luca Marchesotti, Florent Perronnin
-
Publication number: 20120076401Abstract: Local descriptors are extracted from an image. An image vector is generated having vector elements indicative of parameters of mixture model components of a mixture model representing the extracted local descriptors. The image vector is compressed using a vector quantization algorithm to generate a compressed image vector. Optionally, the compressing comprises splitting the image vector into a plurality of sub-vectors each including at least two vector elements, compressing each sub-vector independently using the vector quantization algorithm, and concatenating the compressed sub-vectors to generate the compressed image vector. Optionally, each sub-vector includes only vector elements indicative of parameters of a single mixture model component, and any sparse sub-vector whose vector elements are indicative of parameters of a mixture model component that does not represent any of the extracted local descriptors is not compressed.Type: ApplicationFiled: September 27, 2010Publication date: March 29, 2012Applicant: XEROX CORPORATIONInventors: Jorge Sanchez, Florent Perronnin
-
Publication number: 20120045134Abstract: An input image representation is generated based on an aggregation of local descriptors extracted from an input image, and is adjusted by performing a power normalization, an Lp normalization such as an L2 normalization, or both. In some embodiments the generating comprises modeling the extracted local descriptors using a probabilistic model to generate the input image representation comprising probabilistic model component values for a set of probabilistic model components. In some such embodiments the probabilistic model comprises a Gaussian mixture model and the probabilistic model components comprise Gaussian components of the Gaussian mixture model. The generating may include partitioning the input image into a plurality of image partitions using a spatial pyramids partitioning model, extracting local descriptors, such as Fisher vectors, from the image partitions, and concatenating the local descriptors extracted from the image partitions.Type: ApplicationFiled: August 20, 2010Publication date: February 23, 2012Applicant: XEROX CORPORATIONInventors: Florent Perronnin, Jorge Sanchez, Thomas Mensink
-
Publication number: 20120033874Abstract: 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.Type: ApplicationFiled: August 5, 2010Publication date: February 9, 2012Applicant: Xerox CorporationInventors: Florent Perronnin, Thierry Lehoux, Francois Ragnet
-
Patent number: 8111923Abstract: 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.Type: GrantFiled: August 14, 2008Date of Patent: February 7, 2012Assignee: Xerox CorporationInventors: Gabriela Csurka, Florent Perronnin
-
Publication number: 20110314049Abstract: A method and system to help photographers to take better quality pictures of landmarks and scenes are disclosed. A user is guided with examples of existing quality images, which are extracted from a database, of the same or similar landmarks or scenes. The method includes taking a query photograph that may include an image associated with a GPS location and other metadata, and using information extracted from the image to retrieve existing, similar images. The images retrieved may be ordered according to different criteria. When a user selects one as a model image, the user is provided with assistance for taking a target photograph of similar quality.Type: ApplicationFiled: June 22, 2010Publication date: December 22, 2011Applicant: Xerox CorporationInventors: Hervé Poirier, Florent Perronnin, Mario Agustin Ricardo Jarmasz
-
Publication number: 20110276872Abstract: Automated font mapping is performed for one or more document fonts of a document to map the one or more document fonts to at least one replacement font. The font mapping is limited by at least one document-specific font mapping limitation. The document is rendered using the at least one replacement font. The automated font mapping may include performing a constrained optimization of an objective function measuring similarity of the one or more document fonts and the corresponding mapped at least one replacement font, the constrained optimization being constrained by at least one constraint embodying at least one document-specific font mapping limitation. The automated font mapping may include selecting a subset of the set of fonts available for the rendering based on the at least one document-specific font mapping limitation, and performing the optimization respective to the selected subset of the set of fonts available for the rendering.Type: ApplicationFiled: May 6, 2010Publication date: November 10, 2011Applicant: XEROX CORPORATIONInventors: Saurabh Kataria, Luca Marchesotti, Florent Perronnin
-
Patent number: 8031202Abstract: 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.Type: GrantFiled: March 11, 2008Date of Patent: October 4, 2011Assignee: Xerox CorporationInventor: Florent Perronnin
-
Patent number: 8027540Abstract: 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.Type: GrantFiled: January 15, 2008Date of Patent: September 27, 2011Assignee: Xerox CorporationInventors: Jose A. Rodriguez Serrano, Florent Perronnin
-
Publication number: 20110137898Abstract: 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: ApplicationFiled: December 7, 2009Publication date: June 9, 2011Applicant: XEROX CORPORATIONInventors: Albert Gordo, Florent Perronnin, Francois Ragnet
-
Publication number: 20110091105Abstract: Category context models (64) and a universal context model (62) are generated including sums of soft co-occurrences of pairs of visual words in geometric proximity to each other in training images (50) assigned to each category and assigned to all categories, respectively. Context information (76) about an image to be classified (70) are generated including sums of soft co-occurrences of pairs of visual words in geometric proximity to each other in the image to be classified. For each category (82), a comparison is made of (i) closeness of the context information about the image to be classified with the corresponding category context model and (ii) closeness of the context information about the image to be classified with the universal context model. An image category (92) is assigned to the image to be classified being based on the comparisons.Type: ApplicationFiled: December 17, 2010Publication date: April 21, 2011Applicant: XEROX CORPORATIONInventor: Florent Perronnin