Abstract: Disclosed are various embodiments for generating recommendations utilizing visual image analysis. A digital image provided by a client device is analyzed to identify an empty region in a setting embodied in the digital image. A recommended item, available for consumption via an electronic commerce system, may be identified based on characteristics of the setting embodied in the digital image and historical data associated with a user. A modified form of the digital image is generated comprising the recommended item in the empty region.

Abstract: Techniques for grouping images are disclosed. In some situations, the techniques include identifying at least one event-based image group among a plurality of images based on an event that is associated with each identified image, receiving a selection of one or more objects in a first image of the identified event-based image group, identifying other images in the identified event-based image group that each include at least one of the selected one or more objects, and associating the identified images with the first image. In one instance, the selected objects include individuals captured in the image.

Abstract: A visual refinement interface enables users to adjust and/or refine search results by selecting results that match a user's interest, and displaying subsequent results that are closer to the selected items. Multiple result sets can be displayed concurrently such that the user can maintain context for the results. Further, the user can quickly go back to modify an earlier selection without having to navigate to a previous page, for example, and a single modification can cause several subsequent result sets to automatically change such that the user can quickly view dozens of new results, for example, simply by selecting at least one different result from a displayed result set. Prior result sets can be modified, such as by reducing the size or adjusting the placement of the sets, such that the user can easily determine the current set and the relatedness to previous results sets.

Abstract: Techniques for facilitating a shape-based search of content items are disclosed. In some situations, the techniques include receiving a request for search of content that includes an image of an item and a glyph input by the user on the image that indicates a shape of the first item, extracting features associated with the item from an area of the image on which the glyph is input; identifying a shape category of the first item based at least in part on the indicated shape of the glyph; and conducting a search for items having features that match the extracted features of the first item, the search being conducted among a plurality of items associated with the identified shape category. The retrieved search results may be returned to a user.

Abstract: Displaying item attributes may include receiving, from a client device, a search query, providing, for display to a user, a network page containing search result items relevant to the received query and selectable facets, where each selectable facet corresponds to an attribute associated with at least one of the search result items, and, in response to a selection of one of the selectable facets, identifying each of the search result items that is associated with the attribute corresponding to the selected facet, and causing the attributes corresponding the selected facet to be exposed for each of the identified search result items. The identified search results are retained with exposed attributes.

Abstract: Systems and methods for providing personalized content in substantially real time are presented. In one embodiment, a method for providing personalized content in substantially real time includes providing first content including a plurality of user-selectable content elements, detecting an interaction of a user with respect to the provided content including a selection by the user of one of the plurality of the user-selectable content elements displayed on a page of the first content, and providing second content in response to a request. The second content includes at least a portion of the first content modified according to the detected interaction by moving the user-selectable content element up on a page of the second content relative to a position of the content element on the page of the first content.

Abstract: Asynchronous updating of content pages with suggested search terms and search results is performed by receiving at least one character from a search term user interface element is received and suggested search terms are generated. At least one search result associated with the at least one suggested search term is retrieved from an electronic repository, and the content page is asynchronously updated with additional data about the search result retrieved from the electronic repository.

Abstract: Various embodiments enable a computing device to perform tasks such as highlighting words in an augmented reality view that are important to a user. For example, word lists can be generated and the user, by pointing a camera of a computing device at a volume of text, can cause words from the word list within the volume of text to be highlighted in a live field of view of the camera displayed thereon. Accordingly, users can quickly identify textual information that is meaningful to them in an Augmented Reality view to aid the user in sifting through real-world text.

Abstract: Various embodiments may increase scalability of image representations stored in a database for use in image matching and retrieval. For example, a system providing image matching can obtain images of a number of inventory items, extract features from each image using a feature extraction algorithm, and transform the same into their feature descriptor representations. These feature descriptor representations can be subsequently stored and used to compare against query images submitted by users. Though the size of each feature descriptor representation isn't particularly large, the total number of these descriptors requires a substantial amount of storage space. Accordingly, feature descriptor representations are compressed to minimize storage and, in one example, machine learning can be used to compensate for information lost as a result of the compression.

Abstract: Various embodiments enable a device to perform an adaptive sampling method for locating text regions in images of natural scenes. Since only a fraction of pixels in an input image correspond to text regions, it is desirable to eliminate non-text regions early in the text detection process. Therefore, in at least one embodiment, an image is sampled horizontally to identify connected pixel regions indicative of text. In this example, each sampled row of the image is tested for containing Maximally Stable Extremal Regions (MSERs) in order to identify regions containing text. If a respective row contains a connected pixel region indicative of text, the neighboring rows are recursively sampled at finer levels in order to fully contain the text and sampling is terminated for regions which are unlikely to contain text. This sampling process can also be performed for the vertical dimension for regions which are determined to contain text.

Abstract: Visual incongruity in search result sets may be reduced at least in part by searching an optimized visually significant subset of a category tree that categorizes a collection of content. The category tree may be optimized at build time at least in part by pruning with respect to visual coherence and by the size of the content collection subset referenced by particular categories. Content collection subset sizes both too large and too small can detract from the visual significance of a particular category. The visually significant subset of the category tree may be further optimized at query time by intersecting the visually significant subset with the query-associated sub-tree(s) and further pruning categories in the visually significant subset that have child categories in the visually significant subset. Searching with respect to the optimized visually significant subset can also improve search efficiency.

Abstract: Systems and methods for displaying an image of a virtual object in an environment are described. A computing device is used to capture an image of a real environment including a marker. One or more virtual objects which do not exist in the real environment are displayed in the image based at least on the marker. The distance and orientation of the marker may be taken into account to properly size and place the virtual object in the image. Further, virtual lighting may be added to an image to indicate to a user how the virtual object would appear with the virtual lighting.

Abstract: Techniques for augmenting an image of an object captured and displayed in real time with associated content are disclosed. In one embodiment, the method for augmenting the image includes receiving information defining a sampled frame of a video being captured by an electronic device in substantially real time, determining information representative of an object captured in the sampled frame based on the received information, causing the determined information to match stored information defining a plurality of items to locate an item matched to the captured object, retrieving content associated with the matched item, and providing the retrieved content for display with the captured image on the electronic device. The retrieved content may be rendered in an overlay element that overlays the captured image displayed on the electronic device. The rendered content is configured to enable a user to interact with the content.

Abstract: A method, system and computer program product for virtually placing an object on an image of a human appendage is provided. First, image boundaries are detected in the image of the appendage and converted into a set of line segments. A pair of line segments is evaluated according to a function that combines subscores of the pair of line segments to produce a score. The subscores of the line segments are computed based on various properties such as orientation difference, extent, proximity to the center of the image, bilateral symmetry, and the number of skin-colored pixels. A pair of line segments with the highest score is chosen as the appendage boundaries and is used to determine the position, orientation, and extent of the object. The image of the object is then transformed according to the determined parameters and combined with the image of the appendage to produce the desired result.

Abstract: Embodiments of the present invention provide a method and system for generating an online listing, such as a yellow pages listing, that includes information about an object, such as a business, and also includes at least one image of the structure containing the object. For example, the image may be a digital image of the store front of a business taken at a street view. Additionally, a user may select an image from a plurality of images that the user perceives as being an appropriate representative image for the business. Based on votes received a default representative image may be identified that is provided in response to a request for information about the business.

Abstract: Various embodiments of the present invention relate to a method, system and computer program product for detecting and recognizing text in the images captured by cameras and scanners. First, a series of image-processing techniques is applied to detect text regions in the image. Subsequently, the detected text regions pass through different processing stages that reduce blurring and the negative effects of variable lighting. This results in the creation of multiple images that are versions of the same text region. Some of these multiple versions are sent to a character-recognition system. The resulting texts from each of the versions of the image sent to the character-recognition system are then combined to a single result, wherein the single result is detected text.

Abstract: A method, system and computer program product for encoding an image is provided. The image that needs to be represented is represented in the form of a Gaussian pyramid which is a scale-space representation of the image and includes several pyramid images. The feature points in the pyramid images are identified and a specified number of feature points are selected. The orientations of the selected feature points are obtained by using a set of orientation calculating algorithms. A patch is extracted around the feature point in the pyramid images based on the orientations of the feature point and the sampling factor of the pyramid image. The boundary patches in the pyramid images are extracted by padding the pyramid images with extra pixels. The feature vectors of the extracted patches are defined. These feature vectors are normalized so that the components in the feature vectors are less than a threshold.

Abstract: Systems and methods are provided that allow a user to send a search query and a hint associated with the search query to a search system. Suggested queries are associated with hints prior to the suggested queries being provided to a user interface that allows a user to enter search information into a search field. After receiving input into the search field, the input is sent to a search system and suggested queries with their associated hints are returned. In response to selecting a suggested query, the suggested query and the associated hint are returned to the search service. The search service then provides search results based on the suggested query and the associated hint.

Abstract: The subject technology provides embodiments for performing fast corner detection in a given image for augmented reality applications. Embodiments disclose a high-speed test that examines intensities of pairs of pixels around a candidate center pixel. In one example, the examined pairs are comprised of pixels that are diametrically opposite ends of a circle formed with the candidate center pixel. Further, a pyramid of images including four rings of surrounding pixels is generated. An orientation of the pixels from the four rings are determined and a vector of discrete values of the pixels are provided. Next, a forest of trees are generated for the vector of discrete values corresponding to a descriptor for a first image. For a second image including a set of descriptors, approximate nearest neighbors are determined from the forest of tree representing closest matching descriptors from the first image.

Abstract: A system can monitor data usage, including an amount of searchable data used and/or a rate at which the searchable data is manipulated, on a storage allocation in a networked environment. The storage allocation can have a quantity/number of partitions, including at least one partition, configured to store the searchable data. The system can detect that the data usage is beyond a specified threshold and then based at least in part on factors such as network traffic, CPU usage, and/or data usage, the system can modify the storage allocation to increase or decrease a size of the partition and/or the quantity of partitions. Network traffic for the storage allocation can be directed away from the portion of the storage allocation being modified. When modifying the storage allocation is complete, the network traffic can be directed to the modified portion of the storage allocation.