Abstract: Machine learning-based approaches are used to identify complementary sets of items, such as articles of clothing and accessories that “match,” and suggest items that would complement a given item of interest. A simulated representation of how the item of interest and the identified complementary items would look together is then generated. For example, given a particular piece of clothing or other apparel item of interest, additional items that complement the item of interest can be identified and suggested to a potential purchaser of the item. Additionally, a three-dimensional (3D) or pseudo-3D representation of a human body can be generated to model the apparel item of interest and the identified complementary apparel items to give the user an idea of how the suggested outfit would look on a user. The representation can be modified to more closely resemble a particular user.

Abstract: A method and apparatus for locating and/or determining the condition of a wear part in an image of an operating implement associated with heavy equipment is disclosed. The method involves capturing at least one image of the operating implement during operation of the heavy equipment, the image including a plurality of pixels each having an intensity value. The method also involves selecting successive pixel subsets within the plurality of pixels, and processing each pixel subset to determine whether pixel intensity values in the pixel subset meet a matching criterion indicating a likelihood that the pixel subset corresponds to the wear part. The matching criterion is based on processing a labeled set of training images during a training exercise prior to capturing the at least one image of the operating implement.

Abstract: Soft absorbent sheets, structuring fabrics for producing soft absorbent sheets, and methods of making soft absorbent sheets. The soft absorbent sheets have a plurality of domed regions or projected regions extending from a surface of the sheets, and connecting regions form a network between domed regions. The domed and projected regions include indented bars that extend across the domed and projected regions in a substantially cross machine direction of the absorbent sheets. The absorbent sheets can be formed by structuring fabrics that have long warp yarn knuckles.

Abstract: Methods and systems for arranging shapes within a document prior to printing cut-out patterns are described. A printing device may identify and group contents in a page of a print job as shapes to be cut out from the paper after they are printed. The printing device may then detect the grouped page contents as cut-out patterns. For each cut-out pattern, the printing device may detect the white spaces of content of the cut-out pattern and mark them as available for printing other cut-out patterns. Thus, the printing device may print multiple cut-out patterns on a same page based on using the white space within larger cut-out patterns.

Abstract: An apparatus that facilitates the manual sorting of objects is disclosed. The apparatus includes a display surface having a surface that can be selectively illuminated and that is adapted for receiving the objects. An identification reader reads identification information stored on the objects. A controller causes an area on the display surface corresponding to one of the objects to be illuminated based on the identification information and indicates a location to which the illuminated object is to be moved. In one aspect of the invention, the display surface includes an area adapted for positioning a receiver for the objects. The display surface provides an indication of a position in the receiver at which the one of the objects is to be placed.

Abstract: Systems and methods are provided for image classification using histograms of oriented gradients (HoG) in conjunction with a trainer. The efficiency of the process is greatly increased by first establishing a bitmap which identifies a subset of the pixels in the HoG window as including relevant foreground information, and limiting the HoG calculation and comparison process to only the pixels included in the bitmap.

Abstract: Certain embodiments involve recognizing combinations of body shape, pose, and clothing in three-dimensional input images. For example, synthetic training images are generated based on user inputs. These synthetic training images depict different training figures with respective combinations of a body pose, a body shape, and a clothing item. A machine learning algorithm is trained to recognize the pose-shape-clothing combinations in the synthetic training images and to generate feature descriptors describing the pose-shape-clothing combinations. The trained machine learning algorithm is outputted for use by an image manipulation application. In one example, an image manipulation application uses a feature descriptor, which is generated by the machine learning algorithm, to match an input figure in an input image to an example image based on a correspondence between a pose-shape-clothing combination of the input figure and a pose-shape-clothing combination of an example figure in the example image.

Abstract: In the field of protective equipment, a method can be provided for design and manufacture of protective equipment that allows for a degree of customization to provide enhanced performance characteristics without incurring high cost. In some examples, the method includes a method of determining a mold for a body part including the steps of inputting body part information, searching a database of existing anatomical components and selecting components that most closely match the information, searching a database of body part models and selecting at least one body part model that closely corresponds to the selected components, creating a body part model from the selected components, comparing the two models and determining which model is most appropriate and using a mold associated with that model.

Abstract: A cutting apparatus includes a cut mechanism configured to cut a workpiece; and a control device configured to: judge whether or not each of plural patterns to be cut by the cut mechanism is a test pattern used for evaluating a cut quality of the workpiece cut by the cut mechanism; determine a cut sequence, the cut sequence indicating a sequence in which the plural patterns are cut from the workpiece by the cut mechanism, the cut sequence being determined so that a pattern judged as the test pattern is cut before a normal pattern judged to not be the test pattern; and control the cut mechanism to cut the plural patterns from the workpiece according to the cut sequence.

Abstract: A machine may be configured to determine fashion preferences of users and to provide item recommendations to the users based on the users' fashion preferences. For example, the machine receives an image of a user and a set of spatial data indicating a position of the body of the user in a three-dimensional space. The machine may perform an analysis of the image and the set of spatial data. The performing of the analysis may include extracting, from the image, an image swatch that depicts a portion of an item worn by the user. The machine may identify a fashion preference of the user based on the analysis of the image and of the set of spatial data. The machine may identify an item that corresponds to the fashion preference of the user within an inventory of fashion items and may generate a recommendation of the identified fashion item.

Abstract: Various embodiments provide methods and systems for detecting one or more segments of an image that are related to a particular object in the image (e.g., a logo or trademark) and extracting at least one feature point, each of which is represented by one feature point descriptor, based at least upon a contour curvature of the one or more segments. The at least one feature point descriptor can be converted into one or more codewords to generate a codeword database. A discriminative codebook can then be generated based upon the codeword database and utilized to detect objects and/or features in a query image.

Abstract: A large synthetic 3D human body model dataset using real-world body size distributions is created. The model dataset may follow real-world body parameter distributions. Depth sensors can be integrated into mobile devices such as tablets, cellphones, and wearable devices. Body measurements for a user are extracted from a single frontal-view depth map using joint location information. Estimates of body measurements are combined with local geometry features around joint locations to form a robust multi-dimensional feature vector. A fast nearest-neighbor search is performed using the feature vector for the user and the feature vectors for the synthetic models to identify the closest match. The retrieved model can be used in various applications such as clothes shopping, virtual reality, online gaming, and others.

Abstract: Systems and methods for generating segmented content based on related ranking information are disclosed. Some embodiments include indexing audio information of primary content based on a first plurality of time segments, where the indexed audio information includes a plurality of audio identifiers; indexing video information of the primary content based on a second plurality of time segments, where the indexed video information includes a plurality of video identifiers, obtaining secondary data related to the primary content from an external source, generating identifying information corresponding to the secondary data and comparing the generated identifying information with the indexed audio information and video information, increasing a rank value associated with a segment of the primary content, and generating a media file corresponding to a segment associated with a highest rank value and storing the generated media file in a memory.

Abstract: An augmented reality design system is disclosed. The augmented reality design system allows a user to create a design for an article in real time using a proxy. The system can be configured using a head mounted display for displaying at least one virtual design element over a proxy located in a real-world environment. The system can also be configured using a projector that projects at least one virtual design element onto a proxy located in the real world.

Abstract: Systems and methods are disclosed for fitting a subject by generating one or more 3D deformable models for an anatomical portion; capturing images of a user anatomical portion and a reference object using a mobile camera; generating an updated model of the user anatomical portion by selecting a closest 3D deformable model to the user anatomical portion and matching points on the closest 3D deformable model to one or more predetermined points on the user anatomical portion; and selecting a best-fit product from a plurality of product variations based on the 3D model.

Abstract: A computer implemented method. The method includes generating, using a processor, a set of calibration data relating to a plurality of pigments that are present in a collection of coatings. Generating includes calculating an absorption/reflectance relationship of a plurality of samples coated with a plurality of the pigments, wherein calculating includes using a color matching calculation, and calculating a plurality of concentrations of a non-standard pigment. Generating also includes plotting a relationship between the concentrations and the absorption/reflectance relationships, and determining a correlation of the concentrations for a plurality of Fresnel coefficients relating to the samples. The method further includes determining, using the processor, a coating formulation of a target coating based on the correlation.

Abstract: The invention relates to a method and arrangement for detecting free fiber ends in a paper surface. The method comprises illuminating a target sample (6) surface, which comprises free fiber ends, from at least two directions one at the time, with at least one light source (1). Original reflectance images are obtained for the target sample (6) surface with an imaging device (4), and a surface normal is estimated for each image pixel of the original reflectance image. Thus it is possible to reconstruct a reconstructed reflectance image from the estimated surface normals, and to compare the reconstructed reflectance image and the corresponding original reflectance image and to construct a difference image, where the differences represent shadow objects of the free fiber ends in a paper surface.

Abstract: A system and method for clothing matching is provided. The clothing matching system automatically processes the captured image of the user once the image is captured and identifies a face region, a torso region, and a bottom region of the user from the captured image. The clothing matching system further identifies (i) colour coordination and contrast of the captured image, (ii) a dress colour and a pattern of clothes of the user in the captured image, (iii) a body type of the user, and (iv) a skin tone of the user in the captured image. The clothing matching system communicates information related to the captured image to the server. The server receives and compares the information related to the captured image of the user with the training images/patterns stored in the ML model to compute a score for the captured image of the user for the dress combination.

Abstract: The invention provides an all-in-one imaging apparatus for photographing products, particularly suitable for photographing fashion related products such as apparel products, fashion accessories or other life style products. The imaging apparatus comprising a table part, a portable controller for user interaction with the table part, and a storage for storing images. The table part comprises a substantially horizontal table surface for supporting the product, lights, a fixture for fixing a camera, a backlighting system below the table surface, and an embedded system comprising an embedded computer and a wireless communication controller. The embedded computer controls the camera, switches the backlighting system, wirelessly transmits a live stream from the camera to the portable controller, and wirelessly receives instructions from the portable controller.

Abstract: A method for deriving accurate body size measures of a user from a sequence of 2D images includes: a) automatically guiding the user through a sequence of body poses and motions; b) scanning the body of said user by obtaining a sequence of raw 2D images of said user as captured by at least one camera during said guided sequence of poses and motions; c) analyzing the behavior of said user to ensure that the user follows the provided instructions; d) extracting and encoding 2D shape data descriptors from said sequence of images by using a 2D shape analyzer (2DSA); and e) integrating said 2D shape descriptors and data representing the user's position, pose and rotation into a 3D shape model.

Abstract: Methods for verifying calibration points against mark lines on workpiece surfaces are disclosed. Other embodiments including related systems are also disclosed. A material removal component may precisely remove extraneous material from a workpiece when calibration points of the material removal component along a predetermined trajectory are aligned with a mark line upon a marked surface of a workpiece. The marked surface of the workpiece may be disposed opposite of the material removal component. By employing an optical device aligned with the material removal component, calibration points may determined along the marked surface of the workpiece and verified against the mark line. In this manner, the extraneous material may be efficiently removed while minimizing rework and/or destruction of the workpiece.

Abstract: A footwear digitization system and method configured to determine physical attributes for any given footwear or other cut-and-stitched item, including dimensional and spatial properties, optical attributes, and assembly information, and utilizing those properties and attributes to generate a digital three-dimensional model thereof. The invention relates generally to the field of garment digitization, and the subsequent production of computer-generated images depicting the (digitized) garment at a level of quality comparable to studio photographs of the real garment article.

Abstract: The present technology relates to a computer-implemented method for tracking an object in a sequence of multi-view input video images comprising the steps of acquiring a model of the object, tracking the object in the multi-view input video image sequence, and using the model.

Abstract: A method of constructing 3D clothing model based on single image, estimating a 3D model of human body of an inputted image and constructing 3D clothing plane according to the clothing silhouette of the inputted image. The method includes utilizing the 3D clothing plane and the 3D model of human body to generate a smooth 3D clothing model through a deformation algorithm. A decomposition algorithm of intrinsic image is utilized along with a shape-from-shading algorithm to acquire a set of detail information of clothing from the inputted image. A weighted Laplace editing algorithm is utilized to shift the acquired detail information of clothing to the smooth 3D clothing model to yield a final 3D clothing model. A 3D clothing model is used to generate the surface geometry details including folds, wrinkles.

Abstract: A method, computer program, and system for optimizing kit nesting. The method, computer program, and system include defining a priority for each kit in a plurality of kits. Each of the plurality of kits is associated with at least one machine in a machine family, such that each machine family is associated with a set of kits. A first optimized nest is determined for each machine in each machine family by providing all machine-compatible parts in the highest priority kit to a nesting engine, allowing the nesting engine access to one or more subsequent priority kits to be arranged into the first nest. A second optimized nest is determined for at least one machine by providing all remaining machine-compatible parts in the highest priority kit to a nesting engine, allowing the nesting engine access to one or more subsequent priority kits to be arranged into the second nest.

Abstract: A method and system for generating user-accessible effects. The method includes receiving a library of operators, each operator including a set of operations performable on an image. The method includes receiving an effect definition from a designer via a graphical user interface, wherein the effect definition includes a set of operators from the library to be executed on a user-provided image and parameters associated with each operator. The method includes saving the effect definition to an accessible memory. The method includes uploading the effect definition to a servers wherein the effect definition is accessible to a user over a network.

Abstract: A method for measuring the lengths of industrial fibers is provided. The method employs the depth perception properties of a confocal laser microscope to monitor three-dimensional properties of the sample to determine fiber connectivity in areas where individual fibers in the sample overlap one another. This results in a more accurate matching of fiber termini in such situations, and obviates the need for algorithms which match fiber termini based on curvature, angle, or other two-dimensional properties.

Abstract: An automated apparatus for use in selectively cutting side walls of a honeycomb core is provided. The apparatus includes an end effector, a cutting tool coupled to the end effector, wherein the end effector is configured to position the cutting tool in an initial cutting position based on a schematic geometry of the honeycomb core. The automated apparatus also includes an adaptive vision system configured to direct the end effector to modify the initial cutting position based on an actual geometry of the honeycomb core acquired by the adaptive vision system.

Abstract: A system and method for fusing the outputs from multiple LiDAR sensors. The method includes providing object files for objects detected by the sensors at a previous sample time, where the object files identify the position, orientation and velocity of the detected objects. The method also includes receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time and constructing a point cloud from the scan returns. The method then segments the scan points in the point cloud into predicted clusters, where each cluster initially identifies an object detected by the sensors. The method matches the predicted clusters with predicted object models generated from objects being tracked during the previous sample time. The method creates new object models, deletes dying object models and updates the object files based on the object models for the current sample time.

Abstract: A computer-implemented technique can include receiving, at a server including one or more processors, a source word in a source language. The technique can include determining, at the server, one or more potential translations for the source word in a target language different than the source language. The technique can include determining, at the server, one or more synonyms for each of the one or more potential translations to obtain a plurality of potential translations. The technique can include determining, at the server, one or more translation clusters using the plurality of potential translations and a clustering algorithm. Each translation cluster can contain all of the plurality of potential translations that have a similar denotation and each of the plurality of translations that have a similar denotation can be included in a specific translation cluster. The technique can also include outputting, at the server, the one or more translation clusters.

Abstract: In a computer-implemented method and system for capturing the condition of a structure, the structure is scanned with a three-dimensional (3D) scanner. The 3D scanner generates 3D data. A point cloud or 3D model is constructed from the 3D data. The point cloud or 3D model is then analyzed to determine the condition of the structure.

Abstract: Described herein are quartz crystal microbalance (QCM) and quartz crystal microbalance with dissipation (QCMD) techniques that can be used for measuring characteristics of a creping adhesive film similar to the creping adhesive film that is formed on a Yankee dryer during the tissue and towel manufacturing process. In addition, exemplary embodiments described herein may use these techniques to predict performance of creping aids utilized to form a creping adhesive film.

Abstract: Processing method for transforming a first surface into a second surface, according to which: a/ in a (k+1)th iteration step, for each couple comprising a first elementary surface and a second elementary surface transformed from the first elementary surface in iteration k, the projection of the second elementary surface on the plane of the first elementary surface is determined and a matrix (A) is defined for said couple, where (A)=Pkt,(Pt)?1 and Pt=[pn+1?pi]i=1 to n, Pkt,=[p?n+1,k?p?i,k]i=1 to n; b/ the second elementary surfaces obtained for the (k+1)th iteration are determined as those minimizing a function including at least the term Eshape—k+1=(B).

Abstract: A method for determining the effective cleaning of bath tissue.

Abstract: A set of silhouette attributes are determined for a class of objects, where each of the silhouette attribute corresponds to a discriminative feature that is not associated with any other silhouette attribute in the set. An image content item depicting an object of the class is analyzed. A discriminative feature is identified for the object. The silhouette attribute associated with the determined discriminative feature is associated with the object as provided in the image content item.

Abstract: An image processing apparatus such as a surveillance apparatus and method thereof are provided. The image processing apparatus includes: an object detecting unit which detects a plurality of moving objects from at least one of two or more images obtained by photographing a surveillance area from two or more view points, respectively; a depth determination unit which determines depths of the moving objects based on the two or more images, wherein the depth determination unit determines the moving objects as different objects if the moving objects have different depths.

Abstract: A method for determining the effective cleaning of bath tissue.

Abstract: A first size adjusting unit adjusts a size of a first clothing image which is an image of a first piece of clothing worn on an upper half of a body based on a width of a shoulder part of the first piece of clothing in the first clothing image. A second size adjusting unit adjusts a size of a second clothing image which is an image of a second piece of clothing worn on a lower half of a body based on a width of a waist part of the second piece of clothing in the second clothing image. A display control unit causes a display to display a screen on which the first piece of clothing and the second piece of clothing are vertically displayed, based on the first clothing image and the second clothing image.

Abstract: Methods and systems for generating a size measurement of a body part of person for fitting a garment include providing photographic data that includes images of the body part and using feature extraction techniques to create a computer model of the body part.

Abstract: A product modeling system and method are provided. On one embodiment, the product modeling system is used to model a piece of apparel, such as a shirt, with a design wherein the model with the design is used to display the piece of apparel with the design to a consumer.

Abstract: Systems and methods for populating a design model for engineering, design, and construction projects are described. The design model contains a 3D representation of an assembled structure. Each structural component within the assembled structure has a set of physical attributes that are electronically stored as design model objects. Additional information about each structural component is electronically supplied by a detailer as detailing model objects. The detailing model objects are imported into the design model using a utility tool. The utility tool comprises a processor and executable code that is configured to: (i) correlate the design and detailing model objects; and (ii) recommend to a user which detailing objects should be imported into the design model. The utility tool correlates physical attributes (e.g., location, section size, section type) rather than unique identification numbers, thus allowing the design model to be populated without relying on identification numbers.

Abstract: An apparatus includes a processor and a memory configured to store computer-readable instructions that, when executed, cause the apparatus to perform steps comprising calculating a first angle characteristic and an intensity of the first angle characteristic with respect to each of pixels, arranging a first line segment in a position corresponding to a first pixel based on the first angle characteristic, calculating a second angle characteristic of a second pixel based on the first angle characteristic of at least one pixel adjacent to the second pixel, acquiring information indicating a third angle characteristic, calculating a fourth angle characteristic based on the second angle characteristic and on the third angle characteristic, arranging a second line segment in a position corresponding to the second pixel based on the calculated fourth angle characteristic, and creating data indicating at least stitches that respectively correspond to the first line segment and the second line segment.

Abstract: Examples disclose a method executed on a computing device to locate a clothing region within an image to segment into a region of related clothing. Further, the examples provide detecting a feature of the related clothing. Additionally, the examples also disclose determining a style of the related clothing in the region based on the detection of the feature.

Abstract: Image labeling with global parameters is described. In an embodiment a pose estimation system executes automatic body part labeling. For example, the system may compute joint recognition or body part segmentation for a gaming application. In another example, the system may compute organ labels for a medical imaging application. In an example, at least one global parameter, for example body height is computed for each of the images to be labeled. In an example, the global parameter is used to modify an image labeling process. For example the global parameter may be used to modify the input image to a canonical scale. In another example, the global parameter may be used to adaptively modify previously stored parameters of the image labeling process. In an example, the previously stored parameters may be computed from a reduced set of training data.

Abstract: Apparatuses, processes, and systems for determining features of a paper-making fabric. The apparatus, processes, and systems utilize a representation of a portion of a surface of the fabric, with the representation showing locations and sizes of knuckles and pockets in the surface of the fabric. An image of the portion of the fabric is generated based on the representation. Using the displayed image, an outline is drawn around at least one of the knuckles, and guidelines are drawn such that the guidelines pass through the center of the outlined knuckle, pass through the other knuckles, and form a shape that surrounds areas of the image that correspond to where the pockets are formed between the knuckles. With the outlined knuckle and guidelines, properties that affect the paper-making functionality of the fabric may be calculated.

Abstract: The invention relates to localizing the position of a person speaking by using pictures of a pattern (21) on an object (20) worn by the person. The object (20) carries a complex pattern (21) that is optimized for determining the orientation of the object (20), the distance from the object to a microphone device (14) and/or to a camera (11). Moreover, the pattern (21) may be arranged for identifying the person carrying the object (20). The determination of the position of the person carrying the object (20) may be used to enhance speech recognition (SR) and/or to provide hands-free voice control of devices (DC), e.g. in hospitals or in industrial settings.

Abstract: An image processing device includes a clothing extractor extracting a face or head portion from an input image, the face or head portion being a region estimated to be a face or head image, and extracting a clothing region from a region immediately below the face or head portion, the clothing region being a region estimated to be a clothing image, and a clothing converter changing clothing in the input image by performing predetermined image processing on an image in the clothing region in the input image.

Abstract: Methods and systems for processing coverings such as leather hides and fabrics are provided. A system can include a worktable having a surface on which a covering is placeable. An imaging device can be positionable relative to the worktable. The imaging device can be configured to obtain an image of the covering on the surface of the worktable. A projector can be positionable relative to worktable. The projector can be configured to project an image onto the surface of the worktable and the covering on the surface of the worktable. A controller can be in communication with the imaging device and projector. The controller can be configured to correct images taken by the imaging device. The controller can also be configured to correct the images projected onto the surface of the worktable and the covering thereon. The controller can be configured to permit the showing of virtual markings on the covering placed on the surface of the worktable through an image projected thereon by the projector.

Abstract: A digital image of a first garment having one or more first garment portions is received. A user has identified the first garment portions as matching one or more corresponding second garment portions of a second garment. The probability of accidental match of the first garment within the digital image in relation to the second garment is determined, by using a statistical model based on one or more parameters and based on analyses of the first garment portions. The probability of accidental match is output.

Abstract: This disclosure relates to methods and systems for generating deformers that allow nondynamic objects, such as representations of skin, to appear to slide on a target surface. Computer simulations can be inflexible when it comes to creative input and also introduces extra time into the production process. One or more controls (e.g., a slider or a dial) can be generated based on a weight map and a direction field of an irregular surface that allow the user to slide nondynamic objects, such as representations of skin, on the surface facilitating computer-generated animation.