A method for the computer-aided training of an artificial neural network (ANN) for recognizing structural features on objects, by means of which method identified structural features on objects are recognizable rapidly and reliable. That is achieved by virtue of the fact that a convolutional neural network (CNN) having a multiplicity of neurons is used for the training of an ANN for feature recognition on objects. Said network comprises a multiplicity of convolutional and/or pooling layers for the extraction of information from images of individual objects. In this case, the images of the objects are respectively scaled or scaled up and/or down from layer to layer. During the scaling of the images information about the structural features of the objects is maintained, specifically independently of the scaling of the images.

An imaging apparatus according to an embodiment includes: an imaging unit having a pixel region in which a plurality of pixels is arranged; a readout controller that controls readout of pixel signals from pixels included in the pixel region; a first unit-of-readout setting unit that sets a unit of readout as a part of the pixel region, for which the readout controller performs readout of the pixel signal; an image output unit that outputs a first image based on the pixel signal read out from the unit of readout to a subsequent stage; a second unit-of-readout controller that controls the unit of readout in which the readout controller performs readout of the pixel signal; and a recognition unit that learns training data for each of the units of readout, performs a recognition process on the pixel signal for each of the units of readout, and outputs a recognition result.

An imaging apparatus according to an embodiment includes: an imaging unit having a pixel region in which a plurality of pixels is arranged; a readout controller that controls readout of pixel signals from pixels included in the pixel region; a first unit-of-readout setting unit that sets a unit of readout as a part of the pixel region, for which the readout controller performs readout of the pixel signal; an image output unit that outputs a first image based on the pixel signal read out from the unit of readout to a subsequent stage; a second unit-of-readout controller that controls the unit of readout in which the readout controller performs readout of the pixel signal; and a recognition unit that learns training data for each of the units of readout, performs a recognition process on the pixel signal for each of the units of readout, and outputs a recognition result.

In an embodiment, an image reception system is communicatively coupled to an image analysis system and is configured to receive a digital image and analyze the pixels of the digital image to determine one or more regions in the digital image. For each region in the one or more regions in the digital image, the image analysis system recognizes the content in the region. A document creation system communicatively coupled to the image analysis system is configured to create a digital document based on the recognized content for the one or more regions. In some embodiments, the image analysis system is further configured to analyze the digital image to detect one or more of the following: region markers, tables, headers.

The invention relates to a method for determining a start of relaxation (t.sub.R) when switching over an optical display device (1) controllable pixel by pixel from a burn-in image (EB′) to a relaxation image (RB), wherein. A trigger image area (TB) having at least one image pixel is set to pixel values such that a parameter determined based on the at least one pixel value across the trigger image area (TB) differs between the burn-in image (EB′) and the relaxation image (RB). The local distribution of a greyscale value is continuously recorded by means of a camera (3, 13). A trigger subfield (20) comprising at least one sensor pixel (15) is defined matching the trigger image area (TB). A trigger parameter (T) is continuously determined from the pixel values of the at least one sensor pixel (15) in the trigger subfield (20) with a trigger clock rate and the start of relaxation (t.sub.R) is determined as the point in time at which the continuously determined trigger parameter (T) crosses the trigger threshold value (T.sub.S). The invention furthermore relates to a device and a method for determining the burn-in behavior of a display device (1) as well as the use of such a method for a display (1) determined for application in a vehicle.

The invention relates to a method for determining a start of relaxation (t.sub.R) when switching over an optical display device (1) controllable pixel by pixel from a burn-in image (EB′) to a relaxation image (RB), wherein. A trigger image area (TB) having at least one image pixel is set to pixel values such that a parameter determined based on the at least one pixel value across the trigger image area (TB) differs between the burn-in image (EB′) and the relaxation image (RB). The local distribution of a greyscale value is continuously recorded by means of a camera (3, 13). A trigger subfield (20) comprising at least one sensor pixel (15) is defined matching the trigger image area (TB). A trigger parameter (T) is continuously determined from the pixel values of the at least one sensor pixel (15) in the trigger subfield (20) with a trigger clock rate and the start of relaxation (t.sub.R) is determined as the point in time at which the continuously determined trigger parameter (T) crosses the trigger threshold value (T.sub.S). The invention furthermore relates to a device and a method for determining the burn-in behavior of a display device (1) as well as the use of such a method for a display (1) determined for application in a vehicle.

Methods, systems, and apparatus for controlling smart devices are described. In one aspect a method includes capturing, by a camera on a user device, a plurality of successive images for display in an application environment of an application executing on the user device, performing an object recognition process on the images, the object recognition process including determining that a plurality of images, each depicting a particular object, are required to perform object recognition on the particular object, and in response to the determination, generating a user interface element that indicates a camera operation to be performed, the camera option capturing two or more images, determining that a user, in response to the user interface element, has caused the indicated camera operation to be performed to capture the two or more images, and in response, determining whether a particular object is positively identified from the plurality of images.

This patent document discloses physical documents including metameric ink pairs. One claim recites a document comprising: a first surface; a second surface, in which the first surface comprises a first set of print structures and a second set of print structures, in which the first set of print structures and the second set of print structures collective convey an encoded signal discernable from optical scan data representing at least a first portion of the first surface, in which the first set of print structures is provided on the first surface with a first ink and the second set of print structures is provided on the first surface with a second, different ink, and in which the first ink and the second, different ink comprise a metameric pair. Of course, other claims and combinations are described as well.

An electronic device includes a display, a memory and a processor. The memory includes instructions for causing the processor to, when generating a video, receive a video signal including an object to obtain a plurality of frame images having a first size, estimate a movement trajectory of the object included in the plurality of frame images, stitch together frame images in which overlapping portions of the video signal are arranged to overlap according to the movement trajectory of the object to generate a stitched image having a second size larger than the first size; and store the generated stitched image and the plurality of frame images as a video file.

Systems and methods for enrolling and authenticating a user in an authentication system via a user's camera of camera equipped mobile device include capturing and storing enrollment biometric information from at least one first image of the user taken via the camera of the mobile device, capturing authentication biometric information from at least one second image of the user, capturing, during imaging of the at least one second image, path parameters via at least one movement detecting sensor indicating an authentication movement of the mobile device, comparing the authentication biometric information to the stored enrollment biometric information, and comparing the authentication movement of the mobile device to an expected movement of the mobile device to determine whether the authentication movement sufficiently corresponds to the expected movement.