Methods and image processing systems are provided for determining a dominant gradient orientation for a target region within an image. A plurality of gradient samples are determined for the target region, wherein each of the gradient samples represents a variation in pixel values within the target region. The gradient samples are converted into double-angle gradient vectors, and the double-angle gradient vectors are combined so as to determine a dominant gradient orientation for the target region.

Among other things, one or more travel signals are identified by analyzing one or more images and data from sensors, classifying candidate travel signals into zero, one or more true and relevant travel signals, and estimating a signal state of the classified travel signals.

One or more binary turning function signatures for each of the layout patterns are determined. The one or more binary turning function signatures comprise binary turning function signatures for polygons in each of the layout patterns, and may further comprise binary turning function signatures for secondary polygons A binary turning function signature of a polygon is derived based on deriving a minimum binary number or a maximum binary number among variants of a binary turning function sequence number for the polygon. The variants are generated by circular bit shifting and bit sequence reversing. Similar layout patterns in the layout patterns are determined based on the one or more binary turning function signatures.

Approaches provide for analyzing image data to determine and/or recognize text in the image data. The recognized text can be used to generate a search query that can be automatically submitted to a search engine without having to type the search query to identify a product (or related products) associated with the image. For example, a camera of a computing device can be used to capture a live camera view (or single images) an item. An application executing on the computing device (or at least in communication with the computing device) can analyze the image data of the live camera view to determine a set of keywords (e.g., identified text) based on visual features extracted from the image data. The keywords can be used to query an index of product titles, common search queries, among other indexed data to return a ranked list of search suggestions based on a relevance function. The relevance function can consider the ordering of the keywords to rank search suggestions more highly that contain the keywords having the same word order. Further, the relevance function can consider the confidence of the visual recognition of each keyword, the confidence of each search suggestion, customer impact, as well as other factors to determine the ranking of the search suggestions. The search suggestions can be further refined to ensure search results that the user will be more likely to view and/or purchase.

The present invention relates to a method for encoding the borders of pixel regions of an image, wherein the borders contain a sequence of vertices subdividing the image into regions of pixels (superpixels), by generating a sequence of symbols from an alphabet including the step of: defining for each superpixel a first vertex for coding the borders of the superpixel according to a criterion common to all superpixels; defining for each superpixel the same coding order of the border vertices, either clockwise or counter-clockwise; defining the order for coding the superpixels on the base of a common rule depending on the relative positions of the first vertices; defining a set of vertices as a known border, wherein the following steps are performed for selecting a symbol of the alphabet, for encoding the borders of the superpixels: a) determining the first vertex of the next superpixel border individuated by the common criterion; b) determining the next vertex to be encoded on the basis of the coding direction; c) selecting a first symbol (0) for encoding the next vertex if the next vertex of a border pertains to the known border, d) selecting a symbol (1; 2) different from the first symbol (0) if the next vertex is not in the known border; e) repeating steps b), c), d) and e) until all vertices of the superpixel border have been encoded; f) adding each vertex of the superpixel border that was not in the known border to the set; g) determining the next superpixel whose border is to be encoded according to the common rule, if any; i) repeating steps a)-g) until the borders of all the superpixels of the image have being added to the known border.

A system for vector extraction comprising a vector extraction engine stored and operating on a network-connected computing device that loads raster images from a database stored and operating on a network-connected computing device, identifies features in the raster images, and computes a vector based on the features, and methods for feature and vector extraction.

Enhanced vectorization of raster images is described. An image vectorization module converts a raster image with bitmapped data to a vector image with vector elements based on mathematical formulas. In some embodiments, spatially-localized control of a vectorization operation is provided to a user. First, the user can adjust an intensity of a denoising operation differently at different areas of the raster image. Second, the user can adjust an automated segmentation by causing one segment to be split into two segments along a zone marked with an indicator tool, such as a brush. Third, the user can adjust an automated segmentation by causing two segments to be merged into a combined segment. The computation of the vector elements is based on the adjusted segmentation. In other embodiments, semantic information gleaned from the raster image is incorporated into the vector image to facilitate manipulation, such as joint selection of multiple vector elements.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for adapting generative neural networks to target domains utilizing an image translation neural network. In particular, in one or more embodiments, the disclosed systems utilize an image translation neural network to translate target results to a source domain for input in target neural network adaptation. For instance, in some embodiments, the disclosed systems compare a translated target result with a source result from a pretrained source generative neural network to adjust parameters of a target generative neural network to produce results corresponding in features to source results and corresponding in style to the target domain.

A system for vector extraction comprising a vector extraction engine stored and operating on a network-connected computing device that loads raster images from a database stored and operating on a network-connected computing device, identifies features in the raster images, and computes a vector based on the features, and methods for feature and vector extraction.

In some aspects, a server determines a plurality of parking lots in aerial data. The plurality of parking lots is identified by a plurality of two-dimensional polygons that correspond to the plurality of parking lots and are superimposed on aerial images in the aerial data. The server simplifies a geometry of the plurality of two-dimensional polygons to create parking lot data, determines point-of-interest data associated multiple points of interest, determines correlation data that includes a relationship between: a particular point-of-interest in the point-of-interest data and a set of one or more parking lots in the parking lot data, and sends the correlation data to a client device.