Abstract: A computer system selects 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, copies 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: A computer implemented method for recognizing facial expressions by applying feature learning and feature engineering to face images. The method includes conducting feature learning on a face image comprising feeding the face image into a first convolution neural network to obtain a first decision, conducting feature engineering on a face image, comprising the steps of automatically detecting facial landmarks in the face image, transforming the facial features into a two-dimensional matrix, and feeding the two-dimensional matrix into a second convolution neural network to obtain a second decision, computing a hybrid decision based on the first decision and the second decision, and recognizing a facial expression in the face image in accordance to the hybrid decision.

Abstract: A system for performing background and floor replacement in full-length subject images is described. A set of three or more images of a subject can be captured under different illumination conditions. For example, at least one of the images is captured while a foot portion of the subject and surrounding floor, including a floor mat on which the subject is positioned, are illuminated by a floor lighting device. The floor mat has a Lambertian surface to reflect light in a particular manner such that a maximum contrast between the floor and the subject is captured in the image. Varying contrast between the background, floor, and subject among the images of the set can be leveraged by an image processing system to generate a background mask and a floor mask that are combined and seamlessly transitioned to yield a compiled mask for use in background and floor replacement.

Abstract: A computer-implemented method for creating a photo product design with minimal user inputs includes generating a first portion of a photo product design by a product design module in response to user input, determining one or more layout parameters from the user input to the first portion of the photo product design by a user design learning module, automatically creating a second portion of the photo product design by an intelligent product creation engine at least in part in response to the one or more layout parameters, and automatically making a physical photo product based on at least the first portion and the second portion of the photo product design.

Abstract: A computer-implemented method for automatically detecting events and creating photo-product designs based on the events in a photo-product design system includes automatically identifying an event by an event detection module based on daily numbers of captured photos over a plurality of days, automatically selecting a photo-product type by an intelligent product design creation engine in the photo-product design system, calculating a daily weight for a photo product design in the photo-product type based on the daily numbers of captured photos, automatically determining a number of product photos allocated to each day based on associated daily weight, automatically selecting product photos from the captured photos each day at the event according to the number of product photos allocated to each day, and automatically creating a photo-product design for the event using the selected product photos.

Abstract: A repositionable display panel includes a rigid image plate that includes a front surface configured to receive a colorant to form an image thereon and a back surface opposite to the first surface. The rigid image plate is defined by an image plate thickness and image plate widths. A spacer block is defined by a spacer block thickness and spacer block widths smaller than the image plate widths. A pressure-sensitive adhesive layer between the back surface of the rigid image plate and the spacer block bonds the rigid image plate and the spacer block together.

Abstract: An automated communication design analysis and construction system 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.

Abstract: A method for proactively creating a photo product includes storing a library of points of interest in a computer storage, detecting one or more images from a user, automatically extracting image capture locations from the images, automatically comparing the image capture locations with the points of interest in the library to obtain one or more identified points of interest, automatically identifying an occasion based on the identified points of interest in the library, automatically selecting, by the computer processor, a photo product type in part based on the occasion, automatically creating a design of a photo product of the photo product type using one or more images from the user, and manufacturing a physical photo product based on the photo product design.

Abstract: A method of identifying a background type in a photograph includes extracting a background image from a photograph, feeding the background image into a first convolution neural network to obtain a first decision, extracting color features in the background image, transforming the color features into a two-dimensional color feature matrix, feeding the two-dimensional color feature matrix into a second convolution neural network to obtain a second decision by the one or more computer processors, extracting texture features in the background image, transforming the texture features into a two-dimensional texture feature matrix image by the one or more computer processors, feeding the two-dimensional texture feature matrix into a third convolution neural network to obtain a third decision, computing a hybrid decision based on the first decision, the second decision, and the third decision, and identifying a background type in the background image based on the hybrid decision.

Abstract: A computer-implemented method for creating a photo product design with minimal user inputs includes generating a first portion of a photo product design by a product design module in response to user input, determining one or more layout parameters from the user input to the first portion of the photo product design by a user design learning module, automatically creating a second portion of the photo product design by an intelligent product creation engine at least in part in response to the one or more layout parameters, and automatically making a physical photo product based on at least the first portion and the second portion of the photo product design.

Abstract: A system for assembling a group composite image from individual subject images is described. Often subjects of a group vary in height. Additionally, as each subject is photographed individually, different zoom factors can be applied by a camera that affects a pixel density of the image captured. The system includes a fiducial marking device that emits collimated light to form one or more fiducial markers on a subject while an image is captured by the camera. Based on a location of the fiducial markers in the image, a pixel density of the image and a reference height of the subject can be determined. The individual subject image can be scaled based on the pixel density and reference height to account for the varying subject heights and zoom factors to generate a group composite image that accurately represents the subjects of the group relative to one another.

Abstract: A method and device for generating a composite group image from subgroup images is provided. Subgroup images, each having a common background, are accessed. The boundaries of a subgroup area within each of the subgroup images is determined. At least one horizontal and at least one vertical shift factor is determined using the determined boundaries. An arrangement for the subgroup images based on the at least one horizontal and the at least one vertical shift factor is generated. The composite group image is generated by blending the subgroup images arranged in the arrangement.

Abstract: A photo product design customization system for customizing a photo product design with minimal and intuitive user inputs includes a product design module that displays a photo product design in a main design panel, a user input detection unit that can detect a first directional movement from a first dynamic object in a product type selection panel to the main design panel, or a second directional movement from a second dynamic object in a product style selection panel to the main design panel, or a third directional movement from a third dynamic object in a product style selection panel to the main design panel, and an intelligent product design creation engine that can automatically change the photo product design in the main design panel in response to detection of the first, the second, or the third directional movement.

Abstract: A repositionable display panel includes a rigid image plate that includes a front surface configured to receive a colorant to form an image thereon and a back surface opposite to the first surface. The rigid image plate is defined by an image plate thickness and image plate widths. A spacer block is defined by a spacer block thickness and spacer block widths smaller than the image plate widths. A pressure-sensitive adhesive layer between the back surface of the rigid image plate and the spacer block bonds the rigid image plate and the spacer block together.

Abstract: A method of tracking digital images includes inputting data identifying a subject of an image into a camera, acquiring an image with the camera, and storing the image and the inputted data, as metadata, in an image file when the image is acquired. The method can be implemented using a scanner, a digital camera, and a data processor. The scanner obtains the identifying data and transmits the data to the camera. The camera obtains digital images and embeds the data into digital image files encoding the digital images. The identifying data has a format different from any of the formats processable by the digital camera. The data processor converts the format of the identifying data to one of the plurality of formats processable by the digital camera loads the converted information into the digital camera as metadata.

Abstract: Devices and methods for conducting a remote photography session are described. In some instances, a computing device at a photography station receives messages from a photography station controller which is remote from the photography station. In some examples, the computing device receives one or more messages instructing the computing device to capture an image from an image capture device. The computing device can also receive one or more messages instructing the computing device to adjust the image capture device. Additionally, the messages may instruct the computing device to present instructions to a subject of the photography session. These instructions can prompt the subject to make adjustments to meet a criteria for a photograph in the photography session.

Abstract: A method of identifying a background type in a photograph includes extracting a background image from a photograph, feeding the background image into a first convolution neural network to obtain a first decision, extracting color features in the background image, transforming the color features into a two-dimensional color feature matrix, feeding the two-dimensional color feature matrix into a second convolution neural network to obtain a second decision by the one or more computer processors, extracting texture features in the background image, transforming the texture features into a two-dimensional texture feature matrix image by the one or more computer processors, feeding the two-dimensional texture feature matrix into a third convolution neural network to obtain a third decision, computing a hybrid decision based on the first decision, the second decision, and the third decision, and identifying a background type in the background image based on the hybrid decision.

Abstract: A system for assembling a group composite image from individual subject images is described. Often subjects of a group vary in height. Additionally, as each subject is photographed individually, different zoom factors can be applied by a camera that affects a pixel density of the image captured. The system includes a fiducial marking device that emits collimated light to form one or more fiducial markers on a subject while an image is captured by the camera. Based on a location of the fiducial markers in the image, a pixel density of the image and a reference height of the subject can be determined. The individual subject image can be scaled based on the pixel density and reference height to account for the varying subject heights and zoom factors to generate a group composite image that accurately represents the subjects of the group relative to one another.

Abstract: A photography system includes a lighting system configured to provide a lighting scene that is diffused and is artistically desirable. The system includes an array of light panels configured to simulate a wall of windows that receive natural, diffused, and consistent sunlight, such as a large window facing the north. The light panels can operate in various modes of operation, such as a continuous light mode a strobe light mode.

Abstract: A computer implemented method for gender classification by applying feature learning and feature engineering to face images. The method includes conducting feature learning on a face image comprising feeding the face image into a first convolution neural network to obtain a first decision, conducting feature engineering on a face image, comprising the steps of automatically detecting facial landmarks in the face image, transforming the facial features into a two-dimensional matrix, and feeding the two-dimensional matrix into a second convolution neural network to obtain a second decision, computing a hybrid decision based on the first decision and the second decision, and classifying gender of the face image in accordance with the hybrid decision.