Digital Video Content Fingerprinting Based on Scale Invariant Interest Region Detection with an Array of Anisotropic Filters

摘要

Video sequence processing is described with various filtering rules applied to extract dominant features for content based video sequence identification. Active regions are determined in video frames of a video sequence. Video frames are selected in response to temporal statistical characteristics of the determined active regions. A two pass analysis is used to detect a set of initial interest points and interest regions in the selected video frames to reduce the effective area of images that are refined by complex filters that provide accurate region characterizations resistant to image distortion for identification of the video frames in the video sequence. Extracted features and descriptors are robust with respect to image scaling, aspect ratio change, rotation, camera viewpoint change, illumination and contrast change, video compression/decompression artifacts and noise. Compact, representative signatures are generated for video sequences to provide effective query video matching and retrieval in a large video database.

主权项

1. A method of image scale-space analysis that applies an array of anisotropic filters for interest region determination, the method comprising:
forming an array of elliptic-shaped anisotropic second order partial derivative Gaussian filters with a first scale parameter in the x direction (sx) and a second scale parameter in the y direction (sy) as scale parameters (sx, sy); forming an array of rectangular-shaped anisotropic second order partial derivative Gaussian filters with finite spatial support according to the (sx, sy) scale parameters to approximate the elliptic-shaped anisotropic second order partial derivative Gaussian filters; analyzing scale space for a selected image frame by the array of rectangular-shaped anisotropic second order partial derivative Gaussian filters of finite spatial support to determine at least one interest point corresponding to different (sx, sy) scale parameters, wherein an interest point identifies a location of a distinct image region in the selected image frame; and convolving a region of pixels in a surrounding neighborhood of the determined at least one interest point with the array of rectangular anisotropic second order partial derivative Gaussian filters to produce at least one interest point result that is resistant to image distortion.