A computer-implemented video classification method and system are disclosed. The method includes receiving an input video including a sequence of frames. At least one transformation of the input video is generated, each transformation including a sequence of frames. For the input video and each transformation, local descriptors are extracted from the respective sequence of frames. The local descriptors of the input video and each transformation are aggregated to form an aggregated feature vector with a first set of processing layers learned using unsupervised learning. An output classification value is generated for the input video, based on the aggregated feature vector with a second set of processing layers learned using supervised learning.

A computer-implemented video classification method and system are disclosed. The method includes receiving an input video including a sequence of frames. At least one transformation of the input video is generated, each transformation including a sequence of frames. For the input video and each transformation, local descriptors are extracted from the respective sequence of frames. The local descriptors of the input video and each transformation are aggregated to form an aggregated feature vector with a first set of processing layers learned using unsupervised learning. An output classification value is generated for the input video, based on the aggregated feature vector with a second set of processing layers learned using supervised learning.

An image processing apparatus counts at least one of the number of pixels having an identical color to a target pixel, the number of pixels having a similar color to the target pixel, and the number of pixels having a different color from the target pixel in a target window, and determines an attribute of the target pixel based on a result of the counting.

Techniques related to content adaptive parametric transforms for coding video are described.

Disclosed is a method for automatically optimizing point cloud data quality, including the following steps of: acquiring initial point cloud data for a target to be reconstructed, to obtain an initial discrete point cloud; performing preliminary data cleaning on the obtained initial discrete point cloud to obtain a Locally Optimal Projection operator (LOP) sampling model; obtaining a Possion reconstruction point cloud model by using a Possion surface reconstruction method on the obtained initial discrete point cloud; performing iterative closest point algorithm registration on the obtained Possion reconstruction point cloud model and the obtained initial discrete point cloud; and for each point on a currently registered model, calculating a weight of a surrounding point within a certain radius distance region of a position corresponding to the point for the point on the obtained LOP sampling model, and comparing the weight with a threshold, to determine whether a region where the point is located requires repeated scanning. Further disclosed is a system for automatically optimizing point cloud data quality.

The invention provides a method for instantly recognizing and positioning an object, comprising steps of a) wirelessly searching a wireless identification of the object; b) capturing a plurality of images of the object for each image capture; c) determining a 2D center coordinate (x, y) of the object based on a center coordinate (x.sub.w, y.sub.w) of the wireless identification of the object; d) transforming the captured images of the object to acquire a 3D pattern of the object, and comparing the 3D pattern of the object with 3D patterns pre-stored; and e) if the 3D pattern of the object matches with a pre-stored 3D pattern, calculating and obtaining a 3D center coordinate (x, y, z) of the object to recognize and position the object The invention also provides a system and a processor enabling the method, and use of the system.

Subject matter disclosed herein relates to arrangements and techniques that provide for identifying objects within an image such as the face position of a user of a portable electronic device. An application specific integrated circuit (ASIC) is configured to locate objects within images. The ASIC includes an image node configured to process an image and a search node configured to search the image for an object in the image. The search node includes an integral image generation unit configured to generate an integral image of the image and a Haar feature evaluation unit configured to evaluate search windows of the integral image with respect to Haar-like features. The ASIC also includes an ensemble node configured to confirm the presence of the object in the image.

Subject matter disclosed herein relates to arrangements and techniques that provide for identifying objects within an image such as the face position of a user of a portable electronic device. An application specific integrated circuit (ASIC) is configured to locate objects within images. The ASIC includes an image node configured to process an image and a search node configured to search the image for an object in the image. The search node includes an integral image generation unit configured to generate an integral image of the image and a Haar feature evaluation unit configured to evaluate search windows of the integral image with respect to Haar-like features. The ASIC also includes an ensemble node configured to confirm the presence of the object in the image.

Rescaling or reconstructing of a digital image may be accomplished by directional interpolation, so that interpolation is done in the direction perpendicular to the gradientthe direction in which the change in pixel values is the smallest. Each pixel is generated by interpolation in the output image as a weighted average of nearby pixels, in which the weighting is done in the direction of the gradient. The interpolation is accomplished with an adaptive filter that has an elliptical frequency response determined by the direction of the gradient. The filter uses filter coefficients that are a function of the direction. Rather than storing coefficients for each of several directions, three filter coefficients are storedone set for non-directional filter, one for one direction such as 45 degrees, and another for another direction such as 135 degrees. A blending of the filter coefficients is used.

In a system for determining liveness of an image presented for authentication, a reference signal is rendered on a display, and a reflection of the rendered signal from a target is analyzed to determine liveness thereof. The analysis includes spatially and/or temporally band pass filtering the reflected signal, and determining RGB values for each frame in the reflected signal and/or each pixel in one or more frames of the reflected signal. Frame level and/or pixel-by-pixel correlations between the determined RGB values and the rendered signal are computed, and a determination of whether an image presented is live or fake is made using either or both correlations.