Techniques describe computing computer vision (CV) features based on sensor readings from a sensor and detecting macro-features based on the CV features. The sensor may include a sensor element array that includes a plurality of sensor elements. The sensor may also include in-pixel circuitry coupled to the sensor elements, peripheral circuitry and/or a dedicated microprocessor coupled to the sensor element array. The in-pixel circuitry, the peripheral circuitry or the dedicated microprocessor may include computation structures configured to perform analog or digital operations representative of a multi-pixel computation for a sensor element (or block of sensor elements), based on sensor readings generated by neighboring sensor elements in proximity to the sensor element, and to generate CV features. The dedicated microprocessor may process the CV features and detect macro-features. Furthermore, in certain embodiments, the dedicated microprocessor may be coupled to a second microprocessor through a wired or wireless interface.

In one embodiment, an uploaded multimedia object comprising a photo image or video is subjected to computer vision algorithms to detect and isolate objects within the multimedia object, and the isolated object is searched against a photographic location database containing images of a plurality of locations. Upon detecting a matching object, the location information associated with the photograph in the database containing the matching object may be leveraged to automatically check the user in to the associated location.

The present invention relates to a saliency-based apparatus and methods for visual prostheses. A saliency-based component processes video data output by a digital signal processor before the video data are input to the retinal stimulator. In a saliency-based method, an intensity stream is extracted from an input image, feature maps based on the intensity stream are developed, plural most salient regions of the input image are detected and one of the regions is selected as a highest saliency region.

According to an embodiment, a moving image recognition apparatus includes a moving object detection unit, a data code reading unit, a label recognition unit, an association unit, and an output unit. The moving object detection unit detects moving objects from a moving image stored in a buffer unit and identifies each of the moving objects. The data code reading unit detects a data code from each frame of the moving image and decodes the detected data code. The label recognition unit detects and recognizes a label from each frame of the moving image. When the recognized label and the decoded data code exist on the same object, the association unit associates them. The output unit outputs together the decoding result of the data code and the recognition result of the label associated with the decoding result.

In order to acquire recognition environment information impacting the recognition accuracy of a recognition engine, an information processing device 100 comprises a detection unit 101 and an environment acquisition unit 102. The detection unit 101 detects a marker, which has been disposed within a recognition target zone for the purpose of acquiring information, from an image captured by means of an imaging device which captures images of objects located within the recognition target zone. The environment acquisition unit 102 acquires the recognition environment information based on image information of the detected marker. The recognition environment information is information representing the way in which a recognition target object is reproduced in an image captured by the imaging device when said imaging device captures an image of the recognition target object located within the recognition target zone.

A method includes receiving media data corresponding to a media content item. The method further includes analyzing the media data to determine characteristics of the media content item based on first visual information contained in the media content item. The method further includes analyzing the characteristics of the media content item based on a media popularity model to generate a prediction of whether the media content item is likely to exceed a popularity threshold within a particular period of time. The method further includes determining, at the computing device, a network location at which to store the media content item based on the prediction.

Methods for prioritizing a set of images identified as responsive to an image search query from a user based on features of the images identified as relevant to a geographic region of the user are provided. In one aspect, the method includes submitting a plurality of images to a computer-operated convolutional neural network that is configured to analyze image pixel data for each of the plurality of images to identify features, in each of the plurality of images, influencing a download probability of the corresponding image in a plurality of geographic regions. The method also includes receiving, from the neural network and for each of the plurality of images, a download probability of each image for each of the plurality of geographic regions. Systems and machine-readable media are also provided.

A system for and method of storing two two-dimensional objects on an information storage medium, the method comprising: acquiring a first two-dimensional object and a second, a first perimeter of the first two-dimensional object comprising a first perimeter portion and a second perimeter portion, and the second two-dimensional object comprising the second perimeter portion and a third perimeter portion; storing, on the information storage medium, the first perimeter as storing the first and the second perimeter portions; storing, on the information storage medium, the second perimeter as storing the third perimeter portion and storing a reference to the second perimeter portion.

Means which enables image conversion in which a plurality of conversion results can be output without once saving all of video-image data, which has been input from image-pickup means, in a storage medium is provided. A single line memory having a plurality of lines is used while switching the role thereof for a reading use by a video-image converting means and a use for inputting image data from the image-pickup means. The image converting means obtains an input image, which is in the line memory, and carries out conversion of the input image based on a conversion specifying means interpreted by an instruction decoder.

A system for organizing digital files is provided, wherein tagging data is applied to a sequence of files. A tagging image having tagging data therein is preferably provided before or after the sequence, or both. A text recognizing technology may be used to extract the tagging data from a tagging image. For example, if a tagging image is taken on a camera prior to a sequence of images, the system may extract tagging data from the tagging image and apply such tagging data to the sequence of image files. Preferably, the system provides for renaming of the image files utilizing the tagging data.