Xerox Corporation

Luca Marchesotti

Florent C Perronnin

Gabriela Csurka

Naila Murray

Sandra Skaff

Marco Bressan

Tommaso Colombino

Craig John Saunders

Ana Fucs

Claudio Cifarelli

Robert John Rolleston

Jutta Willamowski

Julianna Elizabeth Lin

Yanal Wazaefi

Kun Duan

Rodrigue Nkoutche

This disclosure provides method and systems of classifying a digital image of an object. Specifically, according to one exemplary embodiment, an object classifier is trained using a constrained MI-SVM (multiple instance-support vector machine) approach whereby training images of objects are sampled to generate a collection of image regions associated with an object type and viewpoint, and the classifier is trained to determine an appropriate mid-level representation of the training image which is discriminative.

Object classification with constrained multiple instance support vector machine

A system and method for searching a finite collection of images using at least one semantic network. Upon receipt of a query from a user that includes a theme and one or more initial keywords, a set of keywords based on the theme and including the initial keywords is generated from one or more semantic networks corresponding to the theme and/or initial keywords. When the finite collection of images includes suitable metadata, a result set is generated of images corresponding to the expanded set of keywords. When the finite collection includes images lacking in metadata, a remote third-party image collection is searched with the set of keywords to obtain a result set that is used to train visual classifiers as to visual concepts associated with the keywords. The classifiers are used to classify the images in the finite collection lacking metadata and the search of the finite collection is performed with the set of keywords to generate a result set.

Image search system and method for personalized photo applications using semantic networks

A method, a system, and a computer program product for extracting one or more images from a storage medium. A search model is selected based on the availability of a semantically related aesthetic model. A search model includes a generic aesthetic model if the semantically related aesthetic model for query is not available. A semantic score and an aesthetic score are computed based on the selected search model. The images are further ranked based on the semantic and aesthetic score.

Methods and systems for ranking images using semantic and aesthetic models

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

An image selection method includes receiving a collection of images and optionally, filtering the collection of images. The filtering may include removing images that are near-duplicates of other images in the collection. A plurality of features is extracted from each of the images in the optionally-filtered collection. The optionally-filtered collection of images is considered as a time-ordered sequence of images and is segmented to form a sequence of segments. Each segment includes at least one of the images. The segmenting of the sequence of images is based on the extracted features and positions of the images in the sequence of images. Images from the segments are selected to form a sub-collection of the images.

System and method for image selection using multivariate time series analysis

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

A method for learning visual attribute labels for images includes, from textual comments associated with a corpus of images, identifying a set of candidate textual labels that are predictive of aesthetic scores associated with images in the corpus. The candidate labels in the set are clustered into a plurality of visual attribute clusters based on similarity and each of the clusters assigned a visual attribute label. For each of the visual attribute labels, a classifier is trained using visual representations of images in the corpus and respective visual attribute labels. The visual attribute labels are evaluated, based on performance of the trained classifier. A subset of the visual attribute labels is retained, based on the evaluation. The visual attribute labels can be used in processes such as image retrieval, image labeling, and the like.

Learning beautiful and ugly visual attributes

A system and method are disclosed for image selection based on photographic style in which photographic style annotations are learned using a data-driven approach. The method includes assigning a style value for each of a set of photographic style categories to each of a set of database images with a trained classifier of a computing device. A user's selection of a subset of the photographic style categories, such as three style categories, is received. A user interface is generated for assigning values to each of the selected photographic style categories. A set of database images is identified, based on the assigned values for each of the selected photographic style categories and the style values for each of the selected photographic style categories of the database images.

Image selection based on photographic style

A system and method for assisting a user in navigation of an image dataset are disclosed. The method includes receiving a user's text query, retrieving images responsive to the query from an image dataset, providing for receiving the user's selection of a first feature selected from a set of available first features via a graphical user interface, providing for receiving the user's selection of a second feature selected from a set of available second features different from the first features via the graphical user interface, and displaying at least some of the retrieved images on the graphical user interface. The displayed images are arranged, e.g., grouped, according to levels and/or combinations of levels of the user-selected first and second features.

System for creative image navigation and exploration

Systems and methods of replacing digital assets within a multimedia document are provided. The systems and methods include a user workstation that can receive a selection from a user for an original asset in the document to be replaced. Alternative assets can be retrieved that have a level of appropriateness with the selected original asset. Constraints on use of the alternative assets can be determined and a fitness value of each of the alternative assets can be calculated based on the appropriateness and the constraints on use. The alternative assets with the highest fitness values can be presented to the user for the user to select to replace the original asset.

Method for visual asset replacement accounting for cost, copyright, and confidentiality requirements

An apparatus, method and an image quality guide document are disclosed. The method includes, for at least one image in a set of images undergoing image enhancement, identifying image quality-related features for the image based on enhancements being applied to the image, identifying image content-related features based on content of the image, determining a content-based degradation of the image based on the identified image quality-related features and image content-related features, and generating a thumbnail of the image. The method further includes generating an image quality guide document for the set of images in which at least one of the thumbnails is associated with a respective text description that is based on the determined content-based degradation.

Automatic generation of a photo guide

A computer-implemented system and method for predicting an image quality of an image are disclosed. For an input image, the method includes generating a first descriptor based on semantic content information for the image and generating a second descriptor based on aesthetic features extracted from the image. With a categorizer which has been trained to assign a quality value to an image based on first and second descriptors, a quality value is assigned to the image based on the first and second descriptors and output.

Image quality assessment

A system and method for categorizing color palettes are provided. A taxonomy for a particular type of achromatic entity, such as emotions, is generated and populated with a list of terms. Natural language terms extracted from annotated color palettes are associated with the corresponding achromatic entity categories in the taxonomy. Features are extracted from the color palettes. The features, together with the category information, are used to train a classifier which is then able to assign achromatic entities to palettes outside the training set, based on extracted features.

System and method for classification and selection of color palettes

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.

Predicting the aesthetic value of an image

A method for color transfer 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.

Growing community of inventors

Grenoble, France

Luca Marchesotti