Abstract: Various approaches discussed herein enable browsing groups of visually similar items to an item of interest, wherein the item of interest may be identified in a query image, for example. One ore more visual attributes associated with the item of interest are identified, and the visually similar items matching at least one of the visual attributes are grouped together, wherein the group is ranked according to the visually similar items' overall visual similarity to the item of interest, for example by using a visual similarity score and/or metric.

Abstract: Disclosed are various embodiments for comparing images of network pages using computer vision to identify changes that have occurred between two versions of a network page. A first plurality of segments in a first image representing a first version of a network page are identified and a second plurality of segments in a second image representing a second version of the network page are identified. It is then determined whether each segment in the first plurality of segments matches a respective segment in the second plurality of segments or vice versa.

Abstract: Recommendations can be generated even in situations where sufficient user information is unavailable for providing personalized recommendations. Instead of generating recommendations for an item based on item type or category, a relation graph can be consulted that enables other items to be recommended that are related to the item in some way, which may be independent of the type or category of item. For example, images of models, celebrities, or everyday people wearing items of clothing, jewelry, handbags, shoes, and other such items can be received and analyzed to recognize those items and cause them to be linked in the relation graph. When generating recommendations or selecting advertisements, the relation graph can be consulted to recommend products that other people have obtained with the item from any of a number of sources, such that the recommendations may be more valuable to the user.

Abstract: Approaches introduce a pre-processing and post-processing framework to a neural network-based approach to identify items represented in an image. For example, a classifier that is trained on several categories can be provided. An image that includes a representation of an item of interest is obtained. Rotated versions of the image are generated and each of a subset of the rotated images is analyzed to determine a probability that a respective image includes an instance of a particular category. The probabilities can be used to determine a probability distribution of output category data, and the data can be analyzed to select an image of the rotated versions of the image. Thereafter, a categorization tree can then be utilized, whereby for the item of interest represented the image, the category of the item can be determined. The determined category can be provided to an item retrieval algorithm to determine primary content for the item of interest.

Abstract: Real-time evaluation of high quality preview images of a document prior to capturing a final image of the document on a mobile device is disclosed. In one aspect, an image capture device is activated on the mobile device. A plurality of preview images of the document is then captured, each of which has a lower image quality than a final image to be captured by the image capture device. Next, for each of the plurality of preview images, the system measures a parameter associated with the image capturing. Next, the system selects a preview image among a subset of the captured preview images when the value of the at least one parameter meets a threshold value.

Abstract: A computing device can be configured to analyze information, such as frames captured in a video by a camera in the computing device, to determine locations of objects in captured frames using a scene-based tracking approach without individually having to track the identified objects across the captured frames. The computing device can track scenes, a global planar surface, across newly captured frames and the changes to (or transformation) the scene can be used to determine updated locations for objects that were identified in previously captured frames. Changes to the scene between frames can be measured using various techniques for estimating homographies. An updated location for the particular object in the currently captured frame can be determined by adjusting the location of the object, as determined in the previously captured frame, with respect to the transformation of the scene between the previously captured frame and the currently captured frame.

Abstract: Real-time evaluation of high quality preview images of a document prior to capturing a final image of the document on a mobile device is disclosed. In one aspect, an image capture device is activated on the mobile device. A plurality of preview images of the document is then captured, each of which has a lower image quality than a final image to be captured by the image capture device. Next, for each of the plurality of preview images, the system measures a parameter associated with the image capturing, and related to the ability to accurately extract text and other content from a captured preview image of the document. Next, the system selects a preview image among a subset of the captured preview images that passes the image quality measurement. When a predetermined condition is met, the system chooses the selected preview image as a final captured image of the document.

Abstract: A plurality of instances of image data can be analyzed, and favored aspects of each instance identified and utilized in generating an enhanced output image. For example, a plurality of instances of image data can be analyzed to identify metric values associated with each pixel location, such as contrast, saturation, and exposedness. A weight map corresponding to each metric is generated for each instance of image data, each weight map indicating a value for the metric at each pixel location of the instance of image data. The weight maps associated with each instance of image data are merged, and a Gaussian pyramid of the merged weight map for each instance of image data is determined along with a Laplacian pyramid for each instance of image data. The Gaussian pyramids and Laplacian pyramids are merged into a Laplacian pyramid, which is then collapsed to form an enhanced output image.

Abstract: Various embodiments describe systems and methods for utilizing a reduced amount of processing capacity for incoming data over time, and, in response to detecting a scene-change-event, notify one or more data processors that a scene-change-event has occurred, and cause incoming data to be processed as new data. In some embodiments, an incoming frame can be compared with a reference frame to determine a difference between the reference frame and the incoming frame. The reference frame may be correlated to a latest scene-change-event. In response to a determination that the difference does not meet one or more difference criteria, a user interface or at least one processor of the computing device can be notified to reduce processing of incoming data over time. In response to a determination that the difference meets the one or more difference criteria, the user interface or the at least one processor can be notified that a scene-change-event has occurred.

Abstract: Various embodiments utilize two-dimensional (“2D”) and three-dimensional (“3D”) object features for purposes such as object recognition and/or image matching. For example, a user can capture an image (e.g., still images or video) of an object and can receive information about items that are determined to match the object. For example, the image can be analyzed to detect visual features (e.g., corners, edges, etc.) of the object and the detected visual features can be combined to generate a combined visual feature vector which can be used for object recognition, image matching, or other such purposes. Other approaches utilize the image to generate a 3D model of the object represented in the image, which can be used to determine at least one object or types of objects that match the object represented in the image.

Abstract: A system that identifies and recognizes text that offers reduced the computational complexity for processing complex images. Widths of scan line segments within candidate text regions are determined, with the shortest segments selected as being representative of stroke width. Statistical features of the stroke widths are used as part of the process to classify each region as containing or not containing a text character or glyph.

Abstract: An object recognition system may recognize an object in a query image by matching the image to one or more images in a database. The database may include images corresponding to multiple viewpoints of a particular device. Key points of the query image are compared to key points in the database images. Database images with many overlapping key points to the query image are selected as potential matches. The geometry of objects in the potential matches is verified to the geometry of the object in the query image to determine if the overlapping key points have a similar geographic relationship to each other across images. Objects in geometrically verified database images may be selected as potentially matching objects to the object in the query image. When a potential matching image is found, the system may confirm the match by performing matching with a second image of the object.

Abstract: Approaches enable the projection of one or more visual elements, such as one or more dynamically changing graphical elements, that can substantially bound, or otherwise at least partially surround or identify, an object recognized by a computing device. The computing device can project the graphical elements to collectively appear as a bounding element for the recognized/actionable object or object portion. As such, the graphical elements can appear as a bounding element that adorns, decorates, highlights, and/or emphasizes, etc., the recognized/actionable object or object portion. The graphical elements to be dynamic. For example, the graphical elements can be projected to move around individually over time, while still appearing to at least partially surround the recognized/actionable object or object portion. Further, the graphical elements can be used to improve various object recognition approaches.

Abstract: Embodiments of the subject technology provide methods and systems of image pre-processing for improving the accuracy of optical character recognition (OCR) and reducing the power consumption on a given computing device (e.g., mobile computing device). The subject technology, in some examples, classifies an image received from a camera of a mobile computing device into one or more classes: 1) normal background, 2) textured background, 3) image with text, 4) image with barcode, 5) image with QR code, and/or 6) image with clutter or “garbage.” Based on the classes associated with the image, the subject technology may forgo certain image processing operations, when the image is not associated with a particular class, in order to save resources (e.g., CPU cycles, battery power, memory usage, etc.) on the mobile computing device.

Abstract: Systems and methods are provided for capturing and processing images of remittance coupons using a mobile device and obtaining data from the captured image which is used to set up or carry out payment of a bill that corresponds to the remittance coupon. Optimization and enhancement of image capture and image processing are provided on the mobile device to improve the initial quality of the captured image and provide a user with real time feedback. The image is then sent from the mobile device to a remote server, where additional image processing is performed to improve the quality of the image and then extract data from the image that is relevant to paying the bill. The extracted data may be verified through comparisons with databases which store information on billers, bill formats and other relevant content that will appear on the bill.

Abstract: Systems and methods are provided for capturing and processing images of remittance coupons using a mobile device and obtaining data from the captured image which is used to set up or carry out payment of a bill that corresponds to the remittance coupon. Optimization and enhancement of image capture and image processing are provided on the mobile device to improve the initial quality of the captured image and provide a user with real time feedback. The image is then sent from the mobile device to a remote server, where additional image processing is performed to improve the quality of the image and then extract data from the image that is relevant to paying the bill. The extracted data may be verified through comparisons with databases which store information on billers, bill formats and other relevant content that will appear on the bill.