A method for presenting an image on a display device (100) includes modifying the image by applying a geometric transformation to the image so that an area of the image on the display device is presented to a viewer with higher density of pixels than that in the rest of the image (S18).

An embodiment method for converting an initial digital image into a converted digital image, electronic chip, system and computer program product are disclosed, the initial digital image comprising a set of pixels, the pixels being associated respectively with colors, the initial digital image being acquired by an acquisition device, and the converted digital image able to be used by a neural network. The embodiment method comprises redimensioning of the initial digital image in order to obtain an intermediate digital image, the redimensioning being carried out by a reduction in the number of pixels of the initial image, modification of a format of one of the pixels of the intermediate digital image in order to obtain a converted digital image, the modification being carried out, after the redimensioning, by increasing the number of bits used to represent the color of the pixel.

Disclosed are systems and associated methods for generating a regularized image from non-uniformly distributed image data based on a curve derived from the image data. The curve is used to reduce the non-uniformity in the image data without losing detail or changing the overall image. Regularizing the image includes obtaining a tree-based representation of the non-uniformly distributed image data, generating a regularization curve that models a particular distribution of the image data, and applying the regularization curve to the tree-based representation in order to select the nodes of the tree-based representation for the decimated image data to render in place of the original image data and the original image data to preserve and render as part of the regularized image. Specifically, the system render the original image data associated with leaf nodes and the decimated image data associated with parent nodes that intersect or are within the regularization curve.

Embodiments described herein provide an integrated holographic reconstruction platform that enables a user to perform three-dimensional visualization of a phenomenon by reconstructing holograms using a combination of normalization and propagation algorithms, which yields better results with significantly less demanding processing time and computing resources. Specifically, the integrated holographic reconstruction platform may be implemented as an all-in-one computer software that includes software components of digital holographic reconstruction, de-twining and optical distortion removal via a user-friendly graphical interface.

The invention relates to a method for online quality control of decorative prints on substrate materials, including similarity comparisons of actual and target images and adjusting decorative prints if deviations of color values are detected. The method may include the steps of: a) producing a hyperspectral digital image of a print decoration; b) calibrating the print decoration via a hyperspectral digital image; c) producing and storing a digital target image of the print decoration; d) creating a first print decoration on a first substrate material; e) producing and storing a digital actual image of the printed decoration on the first substrate material; f) determining color deviations between the digital target image and the digital actual image via a computer program; and g) printing on at least one side of substrate materials so as to form a decorative layer. The invention also relates to a device for carrying out the method.

In some examples, the disclosure describes a device, comprising: a processor resource, and a non-transitory memory resource storing machine-readable instructions stored thereon that, when executed, cause the processor resource to: determine an emotion based on a facial expression of a user captured within an image, apply a plurality of alterations to the image to exaggerate the facial expression of the user when the emotion has continued for a threshold quantity of time, and remove the plurality of alterations to the image when the emotion of the user has changed.

An LED controller system includes an LED controller including an image frame buffer able to receive image data. A sensor processing module is used to receive and process sensor data and a decision module is used to determine actions taken in response to processed sensor data. An image creation module is used to create images to be sent to the image frame buffer of the LED controller.

The present subject matter provides technical solutions facing technical problems associated with preserving spatial dimension of images used in CNNs. Transposed convolutional layers may be used to provide improved spatial dimension preservation or reconstruction. In contrast with image interpolation, transposed convolutional layers may use a set of weights to reconstruct input images. When using CNNs for ADAS and AV applications, the transposed convolutional layers may be trained jointly with convolutional layers during the CNN training process. This may provide the ability to use a lower-dimensional representation of input images, while preserving the spatial dimension of images for use in ADAS and AV systems.

Various embodiments herein each include at least one of systems, methods, software, and data structures for context-aided machine vision item differentiation. For example, one method embodiment includes identifying a customer in a shopping area, receiving an image of the customer holding an item, and performing item identification processing on the image to identify the item the customer is holding. The item identification processing, in some embodiments, includes generating a multidimensional feature vector with a data representation of each feature extracted from the image forming each dimension of the multidimensional feature vector. The item identification processing further includes matching the multidimensional feature vector to a stored multidimensional feature vector of a plurality of stored multidimensional feature vectors that are each associated with a respective product and passing a representation of the identified item for use by another process.

Techniques for video manipulation based on an immersive video experience including rotation are disclosed. Parameters pertaining to a video are determined. Second parameters pertaining to a video display are determined. A minimum scale value is calculated to inscribe a rectangle within an oval based on a height and a width of the video. A height and a width of the video display define the rectangle. A gravity sensor input is preprocessed using a low-pass filter before using it to determine the minimum scale value. The video is preprocessed using a video inset and a viewport inset. The video can be trimmed, and the rectangle can be scaled. A rectangular portion of the video is rendered on the video display wherein the rectangular portion is on or inside the boundaries of the oval.