A system for a tracker for cursor navigation is described herein. The system includes a display, camera, memory, and processor. The memory that is to store instructions and is communicatively coupled to the camera and the display. The processor is communicatively coupled to the camera, the display, and the memory. When the processor is to execute the instructions, the processor is to extract an object mask of an object and execute an optical flow on good feature points from the object mask. The processor is also to estimate a movement of the object and render a cursor on the display based on the movement of the object.

An image processing method is provided. The method is configured to process the color-block image output by the image sensor. The face region of the color-block image is determined. A part of the color-block image beyond the face region is converted into a first simulation image using a first interpolation algorithm. A part of the color-block image within the face region is converted into a second simulation image using a second interpolation algorithm. The complexity of the second interpolation algorithm is less than that of the first interpolation algorithm. The first simulation image and the second simulation image are merged into a simulation image corresponding to the color-block image. An image processing apparatus and an electronic device are provided. With the image processing method, the image processing apparatus and the electronic device, distinguishability and resolution of the image are improved, and time required for processing the image is reduced.

A photo design smart assistant system for reducing similar photos for display and product design includes a similarity distance computation module that can calculate hash values of images and to calculate similarity distances between the images using at least the hash values, a burst grouping module that can automatically group the images into a burst based at least in part on the similarity distances of the images, wherein at least one image is automatically selected from the burst of images, an intelligent design creation engine that can automatically create a photo product design using the selected image from the burst, and a printing and finishing facility that can automatically make a physical photo product based on the photo product design.

A method is provided for generating a three dimensional frame. The method comprises the steps of: retrieving information that relates to a plurality of images of a target captured by two image capturing devices; determining data that will be applied for analyzing objects of interests included in the captured images; calculating disparity between groups of corresponding frames, wherein each of said groups comprises frames taken essentially simultaneously by the two image capturing devices; determining an initial estimation of a disparity range for the frames included in the groups of the corresponding frames; evaluating a disparity range value for each proceeding group based on information retrieved on a dynamic basis from frames included therein, and changing the value of said disparity range when required; and applying a current value of the disparity range in a stereo matching algorithm, and generating a three-dimensional frame for each proceeding group of corresponding frames.

An image processing method is provided. The method is configured to process the color-block image output by the image sensor. The face region of the color-block image is determined. A part of the color-block image beyond the face region is converted into a first simulation image using a first interpolation algorithm. A part of the color-block image within the face region is converted into a second simulation image using a second interpolation algorithm. The complexity of the second interpolation algorithm is less than that of the first interpolation algorithm. The first simulation image and the second simulation image are merged into a simulation image corresponding to the color-block image. An image processing apparatus and an electronic device are provided. With the image processing method, the image processing apparatus and the electronic device, distinguishability and resolution of the image are improved, and time required for processing the image is reduced.

A computer-implemented method for performing compressive sensing of light transport matrix includes receiving a 3D dataset comprising image volume data and randomly selecting a plurality of points on a space curve traversing the 3D dataset. A light transport matrix comprising a plurality of light transmittance values is calculated. Each light transmittance value corresponds to light transmittance between a pair of points included in the plurality of points. An optimization problem is solved to determine a plurality of sparse coefficients which reproduce the light transport matrix when the sparse coefficients are multiplied by a predetermined dictionary of basis vectors. Once determined, the sparse coefficients are stored on a computer-readable medium.

A photo sensor array is divided up into multiple blocks that are operated with different exposure times. A prediction algorithm is used to predict the overall light brightness of each block and determine the exposure time of each block. Each block may also include memory to store the exposure time for the pixels in the block as well as analog-to-digital resolution for the block.

An automatic optical inspection (AOI) method for inspecting defects on a surface of an object is provided. The method includes: providing at least two different illumination systems; acquiring, by at least one detector, at least two pieces of image information of the object, each piece of image information being acquired under illumination of a corresponding one of the illumination systems; obtaining at least two pieces of surface defect information of the object by analyzing the acquired at least two pieces of image information using a computer and storing at least one of the obtained at least two pieces of surface defect information by the computer; and combining, by the computer, all of the at least two pieces of surface defect information to de-duplicate the at least two pieces of surface defect information and obtain a piece of combined surface defect information.

Embodiments of the disclosure provide methods and systems for processing a neural network associated with an input matrix having a first number of elements. The method can include: dividing the input matrix into a plurality of vectors, each vector having a second number of elements; grouping the plurality of vectors into a first group of vectors and a second group of vectors; and pruning the first group of vectors and the second group of vectors.

A method and system for detection of retinal hemorrhages using head computed tomography incorporating deep learning includes obtaining a patient head computed tomography image, segmenting globes using a deep-learning model, rotating the scans using the angle between globes, cropping and masking the globes, and stacking the globes to form 3D individual images that are analyzed for presence of retinal hemorrhage.