Xerox Corporation

Conduent Business Services, LLC

Craig John Saunders

Florent C Perronnin

Nicolas Guérin

Raja Bala

Gabriela Csurka

Luca Marchesotti

Jose Antonio Rodriguez Serrano

Beilei Xu

Peter Paul

Vladimir Kozitsky

Yonghui Zhao

Abu Saeed Islam

Diane Larlus-Larrondo

Sandra Skaff

John Deppen

Harsimrat Singh Sandhawalia

Ruhul Islam

Diane Larlus

Sebastien Dabet

Christine Cayol

Jose Antonio Rodriquez Serrano

Aaron Michael Burrry

Neda Salamati

Rui Hu

Sébastien Dabet

Thomas Dalban

Jose A Rodriguez Serrano

Jose-Antonio Rodriguez

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.

System and method for computing the visual profile of a place

The disclosed embodiments related to a method and system for creating a digital image album implementable on a computing device. The method includes grouping a plurality of digital images to generate a plurality of groups. Each of the plurality of groups is then transmitted to one or more crowdworkers for ranking each digital image of the plurality of groups. A final rank corresponding to each of the plurality of digital images is then determined based on the one or more ranks assigned by the one or more crowdworkers to each digital image of the plurality of groups. Thereafter, at least one digital image is selected from each of the plurality of groups based on the final rank of at least one digital image to create the digital image album.

Method and system for creating digital image album

The disclosed embodiments are related to a method and system for creating a digital image album implementable on a computing device. The method includes receiving a plurality of digital images. The method further includes creating a first signature corresponding to each of the plurality of digital images. The method further includes comparing the first signature corresponding to each of the plurality of digital images with one or more second signatures. Each of the second signatures corresponds to each of one or more prototype digital albums. The method further includes selecting one or more digital images from the plurality of digital images based on the comparison to create the digital image album.

Method and system for creating a digital image album

An advertising system and method are disclosed for generating advertising content based on a user's images. These can be photographs owned by a user of a web page. An advertising template for an advertising sponsor is provided. For a user viewing the web page, a set of the user's images is categorized, based on image content of the images in the set. The categorization is performed with at least one classifier which has been trained on a finite set of image categories. An advertising image is selected for advertising content based on the categorization of the user's images. The template is combined with the selected advertising image to form the advertising content. The advertising content can then be displayed to the user on the web page. A user profile is also disclosed which can be used as the categorized user images.

System and method for advertising using image search and classification

An image segmentation method includes generating a hierarchy of regions by unsupervised segmentation of an input image. Each region is described with a respective region feature vector representative of the region. Hierarchical structures are identified, each including a parent region and its respective child regions in the hierarchy. Each hierarchical structure is described with a respective hierarchical feature vector that is based on the region feature vectors of the respective parent and child regions. The hierarchical structures are classified according to a set of predefined classes with a hierarchical classifier component that is trained with hierarchical feature vectors of hierarchical structures of training images. The training images have semantic regions labeled according to the set of predefined classes. The input image is segmented into a plurality of semantic regions based on the classification of the hierarchical structures and optionally also on classification of the individual regions.

Image segmentation using hierarchical unsupervised segmentation and hierarchical classifiers

A method for segmenting an image includes extracting unary potentials for pixels of the input image. These can be based for each of a set of possible labels, on information for a first channel in the image, such as in the visible range of the spectrum. Pairwise potentials are extracted for neighboring pairs of pixels of the image. These can be based on information for a second channel in the image, such as in the infrared range of the spectrum. An objective function is optimized over pixels of the input image to identify labels for the pixels. The objective function is based on a combination of ones of the extracted unary and pairwise potentials. The image is then segmented, based on the identified pixel labels. The method and system can provide an improvement in segmentation over methods which use only the visible information.

Graph-based segmentation integrating visible and NIR information

A system for detecting a vehicle occupancy violation includes an image capture module that acquires an image including a vehicle cabin from a camera positioned to view oncoming traffic. The system includes a violation determination device, which includes a feature extraction module that processes the image pixels for determining an image descriptor. The process is selected from a group consisting of a Successive Mean Quantization Transform; a Scale-Invariant Feature Transform; a Histogram of Gradients; a Bag-of-Visual-Words Representation; a Fisher Vector Representation; and, a combination of the above. The system further includes a classifier that determines a distance that the vehicle image descriptor/representation is positioned in the projected feature space relative to a hyper-plane. The classifier determines whether the distance meets a threshold and classifies the image when the threshold is met. A processor implements the modules. A graphic user interface outputs the classification.

Occupancy detection for managed lane enforcement based on localization and classification of windshield images

A system and a method for playing a photograph-based game are provided. The method includes establishing a communication link between a game playing system and one or more game playing devices, each of which is operated by a respective player. Game rules are presented to the player(s) on the respective game playing device(s). The game rules include at least one task for the submission of at least one photographic image. Provision is made for receiving a photographic image in the game playing system which has been submitted via the established link from the game playing device in response to the presented task. An image signature is computed for the submitted photographic image based on visual features extracted from the image and a relevance to the task is computed, based on the computed image signature. A score for the game is output for each player, based on the computed relevance of the submitted images for each of the tasks.

Photograph-based game

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.

Methods and systems for improved license plate signature matching by similarity learning on synthetic images

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.

Methods and systems for improving yield in wanted vehicle searches

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.

Growing community of inventors

Grenoble, France

Craig John Saunders