Abstract: A machine may be configured to perform image evaluation of images depicting items for online publishing. For example, the machine performing a user behavior analysis based on data pertaining to interactions by a plurality of users with a plurality of images pertaining to a particular type of item. The machine determines, based on the user behavior analysis, that a presentation type associated with one or more images of the plurality of images corresponds to a user behavior in relation to the one or more images. The machine determines that an item included in a received image is of the particular type of item. The machine generates an output for display in a client device. The output includes a reference to the received image and a recommendation of the presentation type for the item included in the received image, for publication by a web server of a publication system.

Abstract: A machine is configured to determine fashion preferences of users and to provide item recommendations based on the fashion preferences. For example, the machine accesses an indication of a fashion style of a user. The fashion style is determined based on automatically captured data pertaining to the user. The machine identifies, based on the fashion style, one or more fashion items from an inventory of fashion items. The machine generates one or more selectable user interface elements for inclusion in a user interface. The one or more user interface elements correspond to the one or more fashion items. The machine causes generation and display of the user interface that includes the one or more selectable user interface elements. A selection of a selectable user interface element results in display of a combination of an image of a particular fashion item and an image of an item worn by the user.

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: Disclosed are methods and systems for displaying items of clothing on a model having a similar body shape to that of an ecommerce user. In one aspects, a system includes one or more hardware processors configured to perform operations comprising receiving, by one or more hardware processors, an image, the image representing a user height, user weight, and user gender, causing display, by the one or more hardware processors, of a second image via a computer interface, the second image representing a model, the model selected based on a comparison of a model height, weight, and gender with the user height, weight, and gender respectively, receiving, by the one or more hardware processors, a selection of an item of clothing, and causing display, by the one or more hardware processors, of a representation of the selected model wearing the selected item of clothing.

Abstract: Apparatus and method for performing accurate text recognition of non-simplistic images (e.g., images with clutter backgrounds, lighting variations, font variations, non-standard perspectives, and the like) may employ a machine-learning approach to identify a discriminative feature set selected from among features computed for a plurality of irregularly positioned, sized, and/or shaped (e.g., randomly selected) image sub-regions.

Abstract: Images uploaded to photo sharing websites often include some tags or sentence descriptions. In an example embodiment, these tags or descriptions, which might be relevant to the image contents, become the weak labels of these images. The weak labels can be used to identify concepts for the images using an iterative hard instance learning algorithm to discover visual concepts from the label and visual feature representations in the weakly labeled images. The visual concept detectors can be directly applied to concept recognition and detection.

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: An image is passed through an image identifier to identify a coarse category for the image and a bounding box for a categorized object. A mask is used to identify the portion of the image that represents the object. Given the foreground mask, the convex hull of the mask is located and an aligned rectangle of minimum area that encloses the hull is fitted. The aligned bounding box is rotated and scaled, so that the foreground object is roughly moved to a standard orientation and size (referred to as calibrated). The calibrated image is used as an input to a fine-grained categorization module, which determines the fine category within the coarse category for the input image.

Abstract: Apparatus and method for performing accurate text recognition of non-simplistic images (e.g., images with clutter backgrounds, lighting variations, font variations, non-standard perspectives, and the like) may employ a machine-learning approach to identify a discriminative feature set selected from among features computed for a plurality of irregularly positioned, sized, and/or shaped (e.g., randomly selected) image sub-regions.

Abstract: A configured machine performs image matching and retrieval of natural images that may depict logos. The machine generates and uses color-localized spatial masks, which may be computationally less expensive than spatial verification techniques. Key points are detected within images that form a reference database of images. Local masks are defined by the machine around each key point based on the scale and orientation of the key point. To utilize color information presented in logo images, ordered color histograms may be extracted by the machine from locally masked regions of each image. A cascaded index may then be constructed for both visual descriptors and color histograms. For faster matching, the cascaded index maps the visual descriptors and color histograms to a list of relevant or similar images. This list may then be ranked to generate relevant matches for an input query image.

Abstract: In various example embodiments, a system and method for image query are presented. A feature detector generates first feature description data of a first type. An image processor accesses feature codes and angle bins. The image processor generates second feature description data of a second type by comparing a plurality of groups with respective codes of the feature codes. Each of the plurality of groups comprises at least of portion of the first feature description data determined based at least on the feature codes and the angle bins. A search engine selects a first one of a plurality of stored feature description data linked to respective stored images. An interface provides an indication of the stored image linked to the first stored feature description data for display of the stored image linked to the first stored feature description data on a remote device.

Abstract: An image is passed through an image identifier to identify a coarse category for the image and a bounding box for a categorized object. A mask is used to identify the portion of the image that represents the object. Given the foreground mask, the convex hull of the mask is located and an aligned rectangle of minimum area that encloses the hull is fitted. The aligned bounding box is rotated and scaled, so that the foreground object is roughly moved to a standard orientation and size (referred to as calibrated). The calibrated image is used as an input to a fine-grained categorization module, which determines the fine category within the coarse category for the input image.

Abstract: An apparatus and method to facilitate providing recommendations are disclosed herein. A query image is received via a user interface. An image attribute from the query image is extracted. A determination that a usage condition for an image index is satisfied by the query image based on a comparison of an image attribute of the image index to the image attribute of the query image is performed. In response to the determination that the usage condition for the image index is satisfied by the query image, the image index is selected. Based on the selected image index and the usage condition, a set of item images from a plurality of item images stored in a database that correspond to the selected image index is identified. The identified set of item images are presented at the user interface.

Abstract: An apparatus and method to facilitate finding complementary recommendations are disclosed herein. One or more fashion trend or pleasing color combination rules are determined based on data obtained from one or more sources. One or more template images and rule triggers corresponding to the fashion trend or pleasing color combination rules are generated, each of the rule triggers associated with at least one of the template images. A processor compares a first image attribute of a particular one of the template images to a second image attribute of each of a plurality of inventory images corresponding to the plurality of inventory items to identify the inventory items complementary to the query image. The particular one of the template images is selected based on the rule trigger corresponding to the particular one of the template images being applicable for a query image.

Abstract: During a training phase, a machine accesses reference images with corresponding depth information. The machine calculates visual descriptors and corresponding depth descriptors from this information. The machine then generates a mapping that correlates these visual descriptors with their corresponding depth descriptors. After the training phase, the machine may perform depth estimation based on a single query image devoid of depth information. The machine may calculate one or more visual descriptors from the single query image and obtain a corresponding depth descriptor for each visual descriptor from the generated mapping. Based on obtained depth descriptors, the machine creates depth information that corresponds to the submitted single query image.

Abstract: A configured machine performs image matching and retrieval of natural images that may depict logos. The machine generates and uses color-localized spatial masks, which may be computationally less expensive than spatial verification techniques. Key points are detected within images that form a reference database of images. Local masks are defined by the machine around each key point based on the scale and orientation of the key point. To utilize color information presented in logo images, ordered color histograms may be extracted by the machine from locally masked regions of each image. A cascaded index may then be constructed for both visual descriptors and color histograms. For faster matching, the cascaded index maps the visual descriptors and color histograms to a list of relevant or similar images. This list may then be ranked to generate relevant matches for an input query image.

Abstract: During a training phase, a machine accesses reference images with corresponding depth information. The machine calculates visual descriptors and corresponding depth descriptors from this information. The machine then generates a mapping that correlates these visual descriptors with their corresponding depth descriptors. After the training phase, the machine may perform depth estimation based on a single query image devoid of depth information. The machine may calculate one or more visual descriptors from the single query image and obtain a corresponding depth descriptor for each visual descriptor from the generated mapping. Based on obtained depth descriptors, the machine creates depth information that corresponds to the submitted single query image.

Abstract: A machine may be configured to perform image evaluation of images depicting items for online publishing. For example, the machine performing a user behavior analysis based on data pertaining to interactions by a plurality of users with a plurality of images pertaining to a particular type of item. The machine determines, based on the user behavior analysis, that a presentation type associated with one or more images of the plurality of images corresponds to a user behavior in relation to the one or more images. The machine determines that an item included in a received image is of the particular type of item. The machine generates an output for display in a client device. The output includes a reference to the received image and a recommendation of the presentation type for the item included in the received image, for publication by a web server of a publication system.

Abstract: Products (e.g., books) often include a significant amount of informative textual information that can be used in identifying the item. An input query image is a photo (e.g., a picture taken using a mobile phone) of a product. The photo is taken from an arbitrary angle and orientation, and includes an arbitrary background (e.g., a background with significant clutter). From the query image, the identification server retrieves the corresponding clean catalog image from a database. For example, the database may be a product database having a name of the product, image of the product, price of the product, sales history for the product, or any suitable combination thereof. The retrieval is performed by both matching the image with the images in the database and matching text retrieved from the image with the text in the database.

Abstract: An image is passed through an image identifier to identify a coarse category for the image and a bounding box for a categorized object. A mask is used to identify the portion of the image that represents the object. Given the foreground mask, the convex hull of the mask is located and an aligned rectangle of minimum area that encloses the hull is fitted. The aligned bounding box is rotated and scaled, so that the foreground object is roughly moved to a standard orientation and size (referred to as calibrated). The calibrated image is used as an input to a fine-grained categorization module, which determines the fine category within the coarse category for the input image.