Abstract: A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, copying the feature matrix T to produce a feature matrix T_best, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the SVM model on the feature matrix T_best. The first SVM model can be used classify the faces or the objects in the images. An image-product design can be created based on the faces or the objects in the images classified by the first SVM model using the feature matrix T_best.
Abstract: An edge light device of the present disclosure creates edge light effects, such as spectral highlight or artistic effect, on a subject. The edge light device emits light to provide an illumination zone which can be generally out of the field of view of the camera. The edge light device includes a housing having features for controlling light to create edge light effects on a subject. In certain examples, the housing provides a light blocker for concentrating light toward the subject and blocking the light from illuminating the other areas, such as the camera, in the photography station. The housing further includes at least one aperture that cooperates with the light blocker and defines a light passage through which the light is directed toward the subject.
Abstract: A method for creating a design for an image product includes registering a group of image sources by a network based image service system, wherein the group of image sources comprise a first device and a second device, receiving a notification, by the network based image service system, from the image sources about availabilities of the image sources, representing the second device and a local storage of the first device at a user interface on the first device, indicating an availability status of the second device on the first device, and if the availability status of the second device indicates that the second device is available, allowing a user to browse, on the first device, images stored on the second device.
Abstract: A computer-implemented method is disclosed for image recognition and other applications. The method employs an SVM model and can reduce false negatives and increase recognition accuracies by raising the sample-to-support-vector ratio.
Abstract: An assembled group image is generated from subject images. Each of the subject images is associated with height data for the subject in the image. The height data is used to position the subject images in the assembled group image to provide a natural appearance. Shadows can also be added to the assembled group image.
Type:
Grant
Filed:
June 1, 2018
Date of Patent:
February 25, 2020
Assignee:
Shutterfly, LLC
Inventors:
Michael T. Breckenridge, Eric J. Runquist, Michael J. Surma, Earl John Adolphi
Abstract: A computer-implemented method includes selecting a kernel and kernel parameters for a first Support Vector Machine (SVM) model, testing the first SVM model on a feature matrix T of n feature vectors of length m to produce false positive (FP) data set and false negative (FN) data set by a computer processor, wherein n and m are integer numbers, automatically removing feature vectors corresponding to the FP data set from the feature matrix T by the computer processor to produce a feature matrix T_best of size (n-size(FN))*m, retraining the first SVM model on the feature matrix T_best to produce a second SVM model, and checking if a ratio (T_best sample number)/(SVM support vector number) is above a threshold for the second SVM model on T_best. If the ratio is above the threshold, SVM predictions are performed using the second SVM model on the feature matrix T_best.
Abstract: A method for proactively creating a photobook includes identifying a group of images by a computer system and automatically creating a design for a photobook by the computer system without receiving a user's request for designing a photobook if the number of images in the group is determined to be within a predetermined range. Pages of the photobook incorporate a plurality of images in the group. The method further includes presenting the design of the photobook to a user for preview and receiving an order from the user for a physical manifestation of the photobook based on the design.
Type:
Grant
Filed:
November 5, 2018
Date of Patent:
February 11, 2020
Assignee:
Shutterfly, LLC
Inventors:
Eugene Chen, Preeti Nathan, Trynne Anne Miller, Wiley H. Wang, Zhaohui Feng, Erik Weitzman
Abstract: A computer-implemented method for automatically displaying variable image content in an image product includes automatically obtaining markers in photos or videos in a user account which includes detecting features in image content of the photos or the video frames and obtaining a marker for one of the photos or the video frames, automatically identifying a sequence of similar photos or videos if the markers detected in the photos or the associated video frames include more than a predetermined number or percentage of common features, detecting a marker in a photo product by a user device when the photo product is viewed by the user device, identifying a marked photo incorporated in the photo product based on the marker detected in the photo product, and enabling photos or videos in a sequence photos or videos associated with the marked photo to be displayed on the user device.
Type:
Grant
Filed:
July 23, 2019
Date of Patent:
December 31, 2019
Assignee:
Shutterfly, LLC
Inventors:
Nimrod Aroyo, Shy Lev-Ari, Yaron Stein, Jonatan Mor
Abstract: An automated communication design analysis and construction system includes that includes one or more intelligent communication design servers, comprising: a normalization module that converts communication content files for different recipients to normalized intermediate format files; an objects identification and quantification module that identifies text objects and image objects in the normalized intermediate format files; a cross recipient group analysis module configured to identify static global objects that are invariant between recipients, data variables, and variable global objects that vary between recipients in the normalized intermediate format files; and an intelligent communication content learning and constructing engine that can construct standard communication design files based on the static global objects, the data variables, and the variable global objects. A data storage stores the communication content files and the standard communication design files.
Type:
Grant
Filed:
March 5, 2018
Date of Patent:
December 10, 2019
Assignee:
Shutterfly, LLC
Inventors:
Aaron P. Reihl, Sairam Vangapally, Aaron Gregory Rasset
Abstract: A computer system for creating a design for a photo product includes servers that can identify a blog page that includes an image, text, or designs, automatically incorporate at least one of the image, text, or the design object in the blog page into the design of a photo product, and allow a user to review the design of the photo product. The servers communicate with a printing finishing facility that makes a physical photo product according to the design of the photo product.
Type:
Grant
Filed:
May 30, 2013
Date of Patent:
December 10, 2019
Assignee:
Shutterfly, LLC
Inventors:
Joseph Andrew Rozek, Jonathan Scott Delamater, Wiley H Wang, Craig Jorasch