Techniques are disclosed for extracting micro-features at a pixel-level based on characteristics of one or more images. Importantly, the extraction is unsupervised, i.e., performed independent of any training data that defines particular objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specific object definitions. A micro-feature extractor that does not require training data is adaptive and self-trains while performing the extraction. The extracted micro-features are represented as a micro-feature vector that may be input to a micro-classifier which groups objects into object type clusters based on the micro-feature vectors.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for collaboratively training an interaction prediction machine learning model using a plurality of user devices in a manner that respects user privacy. In one aspect, the machine learning model is configured to process an input comprising: (i) a search query, and (ii) a data element, to generate an output which characterizes a likelihood that a given user would interact with the data element if the data element were presented to the given user on a webpage identified by a search result responsive to the search query.

A labeling device includes: an image-signal acquisition unit that acquires an image signal indicating an image captured by a camera; an image recognition unit that has learned by machine learning and performs image recognition on the captured image; and a learning-data-set generation unit that generates, by performing labeling on each object included in the captured image on the basis of a result of image recognition, a learning data set including image data corresponding to each object and label data corresponding to each object.

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.

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.

Systems and methods for performing object identification via template matching. An example method includes obtaining one or more images of a target object and determining spatial vectors for pixels of the one or more images. The spatial vectors include a metric indicative of spatial differences in image properties of the pixels. The method then performs a transformation on the spatial vectors and determines a mapped pixel value for each pixel of the images. The method determines a distance transform from the mapped pixel values and performs a convolution between the distance transform and a model to generate a score map. The method further identifies peaks indicative of a potential target object match from the score map, and then determines target object matches from the one or more peaks of the score map. Finally, the method includes providing an indication of the target object matches to a user or system.